2025-11-07 13:52:28.754437: 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 13:52:28.766396: 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 00:00:1762519948.780554 2856325 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762519948.785013 2856325 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762519948.795595 2856325 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762519948.795618 2856325 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762519948.795620 2856325 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762519948.795622 2856325 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:52:28.799000: 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 13:52:31,898	INFO worker.py:1927 -- Started a local Ray instance.
2025-11-07 13:52:32,592	INFO tune.py:253 -- Initializing Ray automatically. For cluster usage or custom Ray initialization, call `ray.init(...)` before `Tuner(...)`.
2025-11-07 13:52:32,656	INFO trial.py:182 -- Creating a new dirname dir_a058a_744a because trial dirname 'dir_a058a' already exists.
2025-11-07 13:52:32,659	INFO trial.py:182 -- Creating a new dirname dir_a058a_cd18 because trial dirname 'dir_a058a' already exists.
2025-11-07 13:52:32,661	INFO trial.py:182 -- Creating a new dirname dir_a058a_d5af because trial dirname 'dir_a058a' already exists.
2025-11-07 13:52:32,663	INFO trial.py:182 -- Creating a new dirname dir_a058a_7ade because trial dirname 'dir_a058a' already exists.
2025-11-07 13:52:32,665	INFO trial.py:182 -- Creating a new dirname dir_a058a_b628 because trial dirname 'dir_a058a' already exists.
2025-11-07 13:52:32,667	INFO trial.py:182 -- Creating a new dirname dir_a058a_6ebc because trial dirname 'dir_a058a' already exists.
2025-11-07 13:52:32,669	INFO trial.py:182 -- Creating a new dirname dir_a058a_1d1d because trial dirname 'dir_a058a' already exists.
2025-11-07 13:52:32,671	INFO trial.py:182 -- Creating a new dirname dir_a058a_2b7d because trial dirname 'dir_a058a' already exists.
2025-11-07 13:52:32,674	INFO trial.py:182 -- Creating a new dirname dir_a058a_68a6 because trial dirname 'dir_a058a' already exists.
2025-11-07 13:52:32,677	INFO trial.py:182 -- Creating a new dirname dir_a058a_0189 because trial dirname 'dir_a058a' already exists.
2025-11-07 13:52:32,680	INFO trial.py:182 -- Creating a new dirname dir_a058a_6022 because trial dirname 'dir_a058a' already exists.
2025-11-07 13:52:32,683	INFO trial.py:182 -- Creating a new dirname dir_a058a_164f because trial dirname 'dir_a058a' already exists.
2025-11-07 13:52:32,686	INFO trial.py:182 -- Creating a new dirname dir_a058a_acf2 because trial dirname 'dir_a058a' already exists.
2025-11-07 13:52:32,689	INFO trial.py:182 -- Creating a new dirname dir_a058a_819d because trial dirname 'dir_a058a' already exists.
2025-11-07 13:52:32,692	INFO trial.py:182 -- Creating a new dirname dir_a058a_c162 because trial dirname 'dir_a058a' already exists.
2025-11-07 13:52:32,695	INFO trial.py:182 -- Creating a new dirname dir_a058a_0343 because trial dirname 'dir_a058a' already exists.
2025-11-07 13:52:32,699	INFO trial.py:182 -- Creating a new dirname dir_a058a_30cb because trial dirname 'dir_a058a' already exists.
2025-11-07 13:52:32,702	INFO trial.py:182 -- Creating a new dirname dir_a058a_7b34 because trial dirname 'dir_a058a' already exists.
2025-11-07 13:52:32,712	INFO trial.py:182 -- Creating a new dirname dir_a058a_459f because trial dirname 'dir_a058a' already exists.
1 GPU(s) detected and VRAM set to crossover mode..
Se lanza la búsqueda de hiperparámetros óptimos del modelo
╭─────────────────────────────────────────────────────────────────────╮
│ Configuration for experiment     CAPTURE24_hyperparameters_tuning   │
├─────────────────────────────────────────────────────────────────────┤
│ Search algorithm                 BasicVariantGenerator              │
│ Scheduler                        FIFOScheduler                      │
│ Number of trials                 20                                 │
╰─────────────────────────────────────────────────────────────────────╯

View detailed results here: /mnt/nvme1n2/git/uniovi-simur-wearablepermed-data/output/Paper_results/cases_dataset_C/case_C_CAPTURE24_acc_17_classes/CAPTURE24_hyperparameters_tuning
To visualize your results with TensorBoard, run: `tensorboard --logdir /tmp/ray/session_2025-11-07_13-52-31_173867_2856325/artifacts/2025-11-07_13-52-32/CAPTURE24_hyperparameters_tuning/driver_artifacts`

Trial status: 20 PENDING
Current time: 2025-11-07 13:52:32. Total running time: 0s
Logical resource usage: 0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status       N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs │
├─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_a058a    PENDING            3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16 │
│ trial_a058a    PENDING            3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21 │
│ trial_a058a    PENDING            3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15 │
│ trial_a058a    PENDING            2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26 │
│ trial_a058a    PENDING            2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28 │
│ trial_a058a    PENDING            2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22 │
│ trial_a058a    PENDING            2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25 │
│ trial_a058a    PENDING            3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15 │
│ trial_a058a    PENDING            3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21 │
│ trial_a058a    PENDING            3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26 │
│ trial_a058a    PENDING            3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24 │
│ trial_a058a    PENDING            2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28 │
│ trial_a058a    PENDING            2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25 │
│ trial_a058a    PENDING            2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23 │
│ trial_a058a    PENDING            3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23 │
│ trial_a058a    PENDING            2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27 │
│ trial_a058a    PENDING            3   adam            relu                                   16                 64                  3                 1          0.000164705         24 │
│ trial_a058a    PENDING            2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24 │
│ trial_a058a    PENDING            3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21 │
│ trial_a058a    PENDING            3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯

Trial trial_a058a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_a058a config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            16 │
│ funcion_activacion              relu │
│ num_resblocks                      0 │
│ numero_filtros                    16 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00002 │
╰──────────────────────────────────────╯
Trial trial_a058a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_a058a config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            26 │
│ funcion_activacion              tanh │
│ num_resblocks                      1 │
│ numero_filtros                    16 │
│ optimizador                     adam │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00003 │
╰──────────────────────────────────────╯
Trial trial_a058a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_a058a config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            26 │
│ funcion_activacion              relu │
│ num_resblocks                      1 │
│ numero_filtros                    32 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00005 │
╰──────────────────────────────────────╯
Trial trial_a058a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_a058a config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            21 │
│ funcion_activacion              tanh │
│ num_resblocks                      0 │
│ numero_filtros                    32 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00003 │
╰──────────────────────────────────────╯
Trial trial_a058a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_a058a config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            22 │
│ funcion_activacion              tanh │
│ num_resblocks                      0 │
│ numero_filtros                    64 │
│ optimizador                     adam │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00001 │
╰──────────────────────────────────────╯
Trial trial_a058a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_a058a config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            24 │
│ funcion_activacion              tanh │
│ num_resblocks                      1 │
│ numero_filtros                    32 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00001 │
╰──────────────────────────────────────╯
Trial trial_a058a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_a058a config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            25 │
│ funcion_activacion              relu │
│ num_resblocks                      0 │
│ numero_filtros                    64 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00018 │
╰──────────────────────────────────────╯
Trial trial_a058a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_a058a config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            28 │
│ funcion_activacion              tanh │
│ num_resblocks                      1 │
│ numero_filtros                    64 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00002 │
╰──────────────────────────────────────╯
Trial trial_a058a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_a058a config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            28 │
│ funcion_activacion              tanh │
│ num_resblocks                      0 │
│ numero_filtros                    32 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00011 │
╰──────────────────────────────────────╯
Trial trial_a058a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_a058a config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            23 │
│ funcion_activacion              tanh │
│ num_resblocks                      0 │
│ numero_filtros                    16 │
│ optimizador                     adam │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00003 │
╰──────────────────────────────────────╯
Trial trial_a058a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_a058a config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            23 │
│ funcion_activacion              relu │
│ num_resblocks                      1 │
│ numero_filtros                    64 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00015 │
╰──────────────────────────────────────╯
Trial trial_a058a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_a058a config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            15 │
│ funcion_activacion              tanh │
│ num_resblocks                      0 │
│ numero_filtros                    32 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje              0.0002 │
╰──────────────────────────────────────╯
Trial trial_a058a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_a058a config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            15 │
│ funcion_activacion              relu │
│ num_resblocks                      0 │
│ numero_filtros                    32 │
│ optimizador                     adam │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00001 │
╰──────────────────────────────────────╯
Trial trial_a058a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_a058a config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            21 │
│ funcion_activacion              relu │
│ num_resblocks                      0 │
│ numero_filtros                    32 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00002 │
╰──────────────────────────────────────╯
Trial trial_a058a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_a058a config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            25 │
│ funcion_activacion              relu │
│ num_resblocks                      0 │
│ numero_filtros                    16 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00005 │
╰──────────────────────────────────────╯
Trial trial_a058a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_a058a config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            24 │
│ funcion_activacion              tanh │
│ num_resblocks                      0 │
│ numero_filtros                    64 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00001 │
╰──────────────────────────────────────╯
Trial trial_a058a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_a058a config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            21 │
│ funcion_activacion              tanh │
│ num_resblocks                      1 │
│ numero_filtros                    16 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00001 │
╰──────────────────────────────────────╯
Trial trial_a058a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_a058a config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            24 │
│ funcion_activacion              relu │
│ num_resblocks                      1 │
│ numero_filtros                    64 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00016 │
╰──────────────────────────────────────╯
Trial trial_a058a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_a058a config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            27 │
│ funcion_activacion              tanh │
│ num_resblocks                      1 │
│ numero_filtros                    16 │
│ optimizador                     adam │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00002 │
╰──────────────────────────────────────╯
Trial trial_a058a started with configuration:
[36m(train_cnn_ray_tune pid=2857943)[0m 2025-11-07 13:52:36.009416: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
[36m(train_cnn_ray_tune pid=2857943)[0m 2025-11-07 13:52:36.031250: 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=2857944)[0m WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
[36m(train_cnn_ray_tune pid=2857944)[0m E0000 00:00:1762519955.983948 2859091 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=2857944)[0m E0000 00:00:1762519955.991899 2859091 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=2857944)[0m W0000 00:00:1762519956.011435 2859091 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=2857944)[0m W0000 00:00:1762519956.011474 2859091 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=2857944)[0m W0000 00:00:1762519956.011477 2859091 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=2857944)[0m W0000 00:00:1762519956.011480 2859091 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=2857944)[0m 2025-11-07 13:52:36.017458: 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=2857944)[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=2857944)[0m 2025-11-07 13:52:39.133526: 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=2857944)[0m 2025-11-07 13:52:39.133578: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:167] env: CUDA_VISIBLE_DEVICES=""
[36m(train_cnn_ray_tune pid=2857944)[0m 2025-11-07 13:52:39.133587: 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=2857944)[0m 2025-11-07 13:52:39.133592: 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=2857944)[0m 2025-11-07 13:52:39.133597: 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=2857944)[0m 2025-11-07 13:52:39.133601: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:190] hostname: simur-MS-7B94
[36m(train_cnn_ray_tune pid=2857944)[0m 2025-11-07 13:52:39.133807: 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=2857944)[0m 2025-11-07 13:52:39.133839: 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=2857944)[0m 2025-11-07 13:52:39.133844: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:291] kernel version seems to match DSO: 570.133.7
╭──────────────────────────────────────╮
│ Trial trial_a058a config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            24 │
│ funcion_activacion              relu │
│ num_resblocks                      0 │
│ numero_filtros                    16 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00003 │
╰──────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857944)[0m Epoch 1/16
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31:20[0m 3s/step - accuracy: 0.0938 - loss: 3.1609
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 28ms/step - accuracy: 0.0781 - loss: 3.2812
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32:09[0m 3s/step - accuracy: 0.0625 - loss: 3.4587
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 29ms/step - accuracy: 0.0800 - loss: 3.3474
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 28ms/step - accuracy: 0.0697 - loss: 3.3632
[1m  6/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 27ms/step - accuracy: 0.0763 - loss: 3.3509
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 30ms/step - accuracy: 0.0495 - loss: 3.2834  
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 31ms/step - accuracy: 0.0462 - loss: 3.3942
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.0447 - loss: 3.4561
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m  12/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.0440 - loss: 3.4542
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m  14/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 28ms/step - accuracy: 0.0443 - loss: 3.4487
[1m  17/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.0463 - loss: 3.4453
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m  20/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 27ms/step - accuracy: 0.0491 - loss: 3.4362
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 27ms/step - accuracy: 0.0511 - loss: 3.4292
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 27ms/step - accuracy: 0.0533 - loss: 3.4246
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 37ms/step - accuracy: 0.0208 - loss: 3.5959 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 39ms/step - accuracy: 0.0292 - loss: 3.6061
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 27ms/step - accuracy: 0.0546 - loss: 3.4218
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.0557 - loss: 3.4200
[36m(train_cnn_ray_tune pid=2857952)[0m Epoch 1/24[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=2857961)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:22[0m 71ms/step - accuracy: 0.0000e+00 - loss: 2.9919 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:18[0m 67ms/step - accuracy: 0.0069 - loss: 3.0961    
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 62ms/step - accuracy: 0.0130 - loss: 3.1877
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.0163 - loss: 3.2978
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 51ms/step - accuracy: 0.0226 - loss: 3.3361 
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 58ms/step - accuracy: 0.2344 - loss: 2.7147 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 47ms/step - accuracy: 0.1875 - loss: 2.9029 
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 62ms/step - accuracy: 0.0039 - loss: 3.7161    
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 64ms/step - accuracy: 0.0081 - loss: 3.7251
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:40:00[0m 5s/step - accuracy: 0.0625 - loss: 3.5575
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 60ms/step - accuracy: 0.0781 - loss: 3.4128 [32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:25:01[0m 7s/step - accuracy: 0.0625 - loss: 3.0883[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:21[0m 70ms/step - accuracy: 0.0971 - loss: 3.1680
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 66ms/step - accuracy: 0.1000 - loss: 3.1588
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  7/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 84ms/step - accuracy: 0.0416 - loss: 3.4481[32m [repeated 195x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m143/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 35ms/step - accuracy: 0.1321 - loss: 2.9509
[1m144/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 35ms/step - accuracy: 0.1322 - loss: 2.9498[32m [repeated 170x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 62ms/step - accuracy: 0.1001 - loss: 3.1679
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 62ms/step - accuracy: 0.0990 - loss: 3.1754
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 66ms/step - accuracy: 0.0956 - loss: 3.1859
[1m  12/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 65ms/step - accuracy: 0.0937 - loss: 3.1916
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:47[0m 92ms/step - accuracy: 0.0781 - loss: 3.2013 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 31ms/step - accuracy: 0.0529 - loss: 3.4464
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 31ms/step - accuracy: 0.0529 - loss: 3.4456[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  16/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 64ms/step - accuracy: 0.0886 - loss: 3.2168
[1m  17/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 64ms/step - accuracy: 0.0877 - loss: 3.2215
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 45ms/step - accuracy: 0.0627 - loss: 3.4411
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 45ms/step - accuracy: 0.0628 - loss: 3.4404
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 45ms/step - accuracy: 0.0629 - loss: 3.4398
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 50ms/step - accuracy: 0.0447 - loss: 3.5551[32m [repeated 160x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  18/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 64ms/step - accuracy: 0.0869 - loss: 3.2262
[1m  19/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 63ms/step - accuracy: 0.0861 - loss: 3.2303
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  20/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 63ms/step - accuracy: 0.0857 - loss: 3.2324
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 63ms/step - accuracy: 0.0853 - loss: 3.2342
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 63ms/step - accuracy: 0.0851 - loss: 3.2360
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 63ms/step - accuracy: 0.0847 - loss: 3.2379
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  14/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 51ms/step - accuracy: 0.0314 - loss: 3.6611 
[1m  15/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.0324 - loss: 3.6555
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 63ms/step - accuracy: 0.0844 - loss: 3.2397
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 63ms/step - accuracy: 0.0840 - loss: 3.2418
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 63ms/step - accuracy: 0.0838 - loss: 3.2432
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.0837 - loss: 3.2442
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.0836 - loss: 3.2452
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.0836 - loss: 3.2455
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:19[0m 68ms/step - accuracy: 0.0000e+00 - loss: 3.7740 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 60ms/step - accuracy: 0.0000e+00 - loss: 3.7282[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  32/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.0830 - loss: 3.2470
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.0829 - loss: 3.2473
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  31/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.0833 - loss: 3.2466[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.0832 - loss: 3.2467
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.0835 - loss: 3.2463
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m243/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.0794 - loss: 3.2580 
[1m245/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.0794 - loss: 3.2577
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m247/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.0795 - loss: 3.2574
[1m248/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.0795 - loss: 3.2573
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m250/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.0796 - loss: 3.2570
[1m252/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.0797 - loss: 3.2567
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 41/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 74ms/step - accuracy: 0.0776 - loss: 3.3683
[1m 42/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 73ms/step - accuracy: 0.0777 - loss: 3.3677
[1m 43/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 73ms/step - accuracy: 0.0778 - loss: 3.3670
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m254/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.0798 - loss: 3.2563
[1m256/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.0798 - loss: 3.2560
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 65ms/step - accuracy: 0.0854 - loss: 3.2420
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 65ms/step - accuracy: 0.0856 - loss: 3.2417
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m258/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.0799 - loss: 3.2557
[1m260/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.0800 - loss: 3.2554
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m262/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.0800 - loss: 3.2551
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 66ms/step - accuracy: 0.0860 - loss: 3.2414
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 67ms/step - accuracy: 0.0862 - loss: 3.2410
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m265/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.0801 - loss: 3.2546
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m267/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.0802 - loss: 3.2543
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m269/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.0803 - loss: 3.2540
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m271/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.0803 - loss: 3.2537
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m273/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.0804 - loss: 3.2534
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m275/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.0805 - loss: 3.2531
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m277/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.0805 - loss: 3.2528
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m279/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.0806 - loss: 3.2524
[1m281/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.0807 - loss: 3.2521
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  57/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 67ms/step - accuracy: 0.0878 - loss: 3.2387
[1m  58/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 67ms/step - accuracy: 0.0881 - loss: 3.2381
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m283/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0808 - loss: 3.2518
[1m285/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0808 - loss: 3.2515
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  59/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 67ms/step - accuracy: 0.0883 - loss: 3.2375
[1m  60/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 67ms/step - accuracy: 0.0886 - loss: 3.2369
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m287/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0809 - loss: 3.2511
[1m289/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0810 - loss: 3.2508
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m292/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0811 - loss: 3.2503
[1m294/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0812 - loss: 3.2500
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  62/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 67ms/step - accuracy: 0.0891 - loss: 3.2363
[1m  63/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 68ms/step - accuracy: 0.0893 - loss: 3.2359
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m296/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0812 - loss: 3.2496
[1m298/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0813 - loss: 3.2493
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m300/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0814 - loss: 3.2489
[1m302/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0814 - loss: 3.2486
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  66/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 68ms/step - accuracy: 0.0901 - loss: 3.2344
[1m  67/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 68ms/step - accuracy: 0.0904 - loss: 3.2337
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m304/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0815 - loss: 3.2482
[1m306/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0816 - loss: 3.2478
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  68/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 67ms/step - accuracy: 0.0906 - loss: 3.2331
[1m  69/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 67ms/step - accuracy: 0.0909 - loss: 3.2323
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m308/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0816 - loss: 3.2475
[1m310/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0817 - loss: 3.2471
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  70/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 67ms/step - accuracy: 0.0911 - loss: 3.2317
[1m  71/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 67ms/step - accuracy: 0.0914 - loss: 3.2311
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m312/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0818 - loss: 3.2467
[1m314/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0818 - loss: 3.2464
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 67ms/step - accuracy: 0.0916 - loss: 3.2305
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 67ms/step - accuracy: 0.0918 - loss: 3.2298
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m317/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m7s[0m 30ms/step - accuracy: 0.0819 - loss: 3.2458
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m319/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m7s[0m 30ms/step - accuracy: 0.0820 - loss: 3.2455
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m321/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m7s[0m 30ms/step - accuracy: 0.0821 - loss: 3.2451
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m322/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 30ms/step - accuracy: 0.0821 - loss: 3.2449
[1m323/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 30ms/step - accuracy: 0.0821 - loss: 3.2448
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m325/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 30ms/step - accuracy: 0.0822 - loss: 3.2444
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m326/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 30ms/step - accuracy: 0.0822 - loss: 3.2442
[1m327/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 30ms/step - accuracy: 0.0822 - loss: 3.2441
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m261/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m12s[0m 39ms/step - accuracy: 0.0797 - loss: 3.3091[32m [repeated 270x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m146/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 57ms/step - accuracy: 0.0713 - loss: 3.3200
[1m148/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 57ms/step - accuracy: 0.0714 - loss: 3.3193[32m [repeated 227x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m328/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 30ms/step - accuracy: 0.0823 - loss: 3.2439
[1m329/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 30ms/step - accuracy: 0.0823 - loss: 3.2437
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 67ms/step - accuracy: 0.0945 - loss: 3.2228
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 67ms/step - accuracy: 0.0948 - loss: 3.2220
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m330/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.0823 - loss: 3.2435
[1m332/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.0824 - loss: 3.2432
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 67ms/step - accuracy: 0.0951 - loss: 3.2213
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 67ms/step - accuracy: 0.0954 - loss: 3.2206
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  88/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 67ms/step - accuracy: 0.0962 - loss: 3.2184
[1m  89/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 67ms/step - accuracy: 0.0964 - loss: 3.2177
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m28s[0m 32ms/step - accuracy: 0.0991 - loss: 3.2019
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m28s[0m 32ms/step - accuracy: 0.0991 - loss: 3.2018[32m [repeated 166x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  90/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 67ms/step - accuracy: 0.0967 - loss: 3.2171
[1m  91/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 67ms/step - accuracy: 0.0969 - loss: 3.2164
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m29s[0m 31ms/step - accuracy: 0.0588 - loss: 3.4009
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m29s[0m 31ms/step - accuracy: 0.0589 - loss: 3.4002
[1m 219/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m29s[0m 31ms/step - accuracy: 0.0590 - loss: 3.3994[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  92/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 67ms/step - accuracy: 0.0972 - loss: 3.2159
[1m  93/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 67ms/step - accuracy: 0.0974 - loss: 3.2153
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m41s[0m 44ms/step - accuracy: 0.0821 - loss: 3.2896[32m [repeated 222x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  96/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 66ms/step - accuracy: 0.0981 - loss: 3.2135
[1m  97/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 66ms/step - accuracy: 0.0984 - loss: 3.2128
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  98/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 66ms/step - accuracy: 0.0987 - loss: 3.2122
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 66ms/step - accuracy: 0.0989 - loss: 3.2116
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 66ms/step - accuracy: 0.0991 - loss: 3.2110
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 66ms/step - accuracy: 0.0994 - loss: 3.2105
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 66ms/step - accuracy: 0.0996 - loss: 3.2099
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 66ms/step - accuracy: 0.0998 - loss: 3.2093
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 66ms/step - accuracy: 0.1000 - loss: 3.2087
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 66ms/step - accuracy: 0.1002 - loss: 3.2080
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 66ms/step - accuracy: 0.1004 - loss: 3.2074
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 66ms/step - accuracy: 0.1006 - loss: 3.2067
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  95/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 66ms/step - accuracy: 0.0979 - loss: 3.2141[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 66ms/step - accuracy: 0.1011 - loss: 3.2048
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 66ms/step - accuracy: 0.1013 - loss: 3.2041
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 66ms/step - accuracy: 0.1015 - loss: 3.2035
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 66ms/step - accuracy: 0.1017 - loss: 3.2028
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 66ms/step - accuracy: 0.1019 - loss: 3.2022
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 66ms/step - accuracy: 0.1021 - loss: 3.2015
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 66ms/step - accuracy: 0.1023 - loss: 3.2008
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 66ms/step - accuracy: 0.1025 - loss: 3.2002
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m349/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 35ms/step - accuracy: 0.1076 - loss: 3.0642
[1m352/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 35ms/step - accuracy: 0.1078 - loss: 3.0631[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 66ms/step - accuracy: 0.1027 - loss: 3.1995
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 66ms/step - accuracy: 0.1029 - loss: 3.1988
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m159/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 54ms/step - accuracy: 0.1256 - loss: 3.0005
[1m160/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 54ms/step - accuracy: 0.1256 - loss: 2.9999
[1m161/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 54ms/step - accuracy: 0.1257 - loss: 2.9993[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m406/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 31ms/step - accuracy: 0.0843 - loss: 3.2309[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m332/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 40ms/step - accuracy: 0.0829 - loss: 3.2803 
[1m334/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.0830 - loss: 3.2795
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 68ms/step - accuracy: 0.1044 - loss: 3.1932
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 67ms/step - accuracy: 0.1046 - loss: 3.1926
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 68ms/step - accuracy: 0.1047 - loss: 3.1919
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 68ms/step - accuracy: 0.1049 - loss: 3.1913
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 68ms/step - accuracy: 0.1057 - loss: 3.1879
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 68ms/step - accuracy: 0.1059 - loss: 3.1873
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 138/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 68ms/step - accuracy: 0.1062 - loss: 3.1858
[1m 139/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 68ms/step - accuracy: 0.1064 - loss: 3.1851
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 143/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 68ms/step - accuracy: 0.1070 - loss: 3.1822
[1m 144/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 68ms/step - accuracy: 0.1072 - loss: 3.1814
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 147/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 68ms/step - accuracy: 0.1077 - loss: 3.1792
[1m 148/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 68ms/step - accuracy: 0.1078 - loss: 3.1785
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 149/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 68ms/step - accuracy: 0.1080 - loss: 3.1778
[1m 150/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 68ms/step - accuracy: 0.1082 - loss: 3.1771
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 68ms/step - accuracy: 0.1083 - loss: 3.1763
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 68ms/step - accuracy: 0.1085 - loss: 3.1756
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m286/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 50ms/step - accuracy: 0.0715 - loss: 3.3323[32m [repeated 213x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m233/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m20s[0m 57ms/step - accuracy: 0.0787 - loss: 3.2878
[1m234/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m20s[0m 57ms/step - accuracy: 0.0788 - loss: 3.2875[32m [repeated 178x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 69ms/step - accuracy: 0.1091 - loss: 3.1726
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 69ms/step - accuracy: 0.1092 - loss: 3.1718
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 69ms/step - accuracy: 0.1095 - loss: 3.1703
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 69ms/step - accuracy: 0.1096 - loss: 3.1695
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 303/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m41s[0m 48ms/step - accuracy: 0.0727 - loss: 3.3575
[1m 305/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m41s[0m 48ms/step - accuracy: 0.0728 - loss: 3.3570[32m [repeated 166x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m352/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 37ms/step - accuracy: 0.0626 - loss: 3.4381
[1m354/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 37ms/step - accuracy: 0.0626 - loss: 3.4375
[1m355/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 37ms/step - accuracy: 0.0626 - loss: 3.4372
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m47s[0m 50ms/step - accuracy: 0.0683 - loss: 3.3901
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m47s[0m 50ms/step - accuracy: 0.0684 - loss: 3.3897
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m47s[0m 50ms/step - accuracy: 0.0684 - loss: 3.3893
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m36s[0m 43ms/step - accuracy: 0.0819 - loss: 3.2881[32m [repeated 219x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 69ms/step - accuracy: 0.1099 - loss: 3.1680
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 69ms/step - accuracy: 0.1100 - loss: 3.1672
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 69ms/step - accuracy: 0.1101 - loss: 3.1665
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 69ms/step - accuracy: 0.1103 - loss: 3.1658
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 69ms/step - accuracy: 0.1104 - loss: 3.1650
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 69ms/step - accuracy: 0.1105 - loss: 3.1643
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 173/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 69ms/step - accuracy: 0.1113 - loss: 3.1598
[1m 174/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 69ms/step - accuracy: 0.1115 - loss: 3.1590
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 175/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 69ms/step - accuracy: 0.1116 - loss: 3.1582
[1m 176/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 69ms/step - accuracy: 0.1117 - loss: 3.1575
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 177/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 69ms/step - accuracy: 0.1118 - loss: 3.1567
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 69ms/step - accuracy: 0.1119 - loss: 3.1559
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 172/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 69ms/step - accuracy: 0.1112 - loss: 3.1605[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 180/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 69ms/step - accuracy: 0.1122 - loss: 3.1544
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 69ms/step - accuracy: 0.1123 - loss: 3.1536
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 69ms/step - accuracy: 0.1127 - loss: 3.1513
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 69ms/step - accuracy: 0.1128 - loss: 3.1505
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 69ms/step - accuracy: 0.1129 - loss: 3.1498
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 68ms/step - accuracy: 0.1130 - loss: 3.1491
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m407/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 43ms/step - accuracy: 0.1588 - loss: 2.7677
[1m408/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 43ms/step - accuracy: 0.1589 - loss: 2.7672[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 69ms/step - accuracy: 0.1131 - loss: 3.1484
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 69ms/step - accuracy: 0.1132 - loss: 3.1477
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m168/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m27s[0m 67ms/step - accuracy: 0.0777 - loss: 3.3241
[1m169/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m27s[0m 67ms/step - accuracy: 0.0777 - loss: 3.3238
[1m170/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m27s[0m 67ms/step - accuracy: 0.0778 - loss: 3.3235[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 68ms/step - accuracy: 0.1133 - loss: 3.1469
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 68ms/step - accuracy: 0.1134 - loss: 3.1463
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 68ms/step - accuracy: 0.1135 - loss: 3.1456
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 68ms/step - accuracy: 0.1136 - loss: 3.1449
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 68ms/step - accuracy: 0.1137 - loss: 3.1442
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 68ms/step - accuracy: 0.1138 - loss: 3.1435
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m489/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 36ms/step - accuracy: 0.1125 - loss: 3.0192[32m [repeated 108x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 68ms/step - accuracy: 0.1139 - loss: 3.1428
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 68ms/step - accuracy: 0.1140 - loss: 3.1421
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 68ms/step - accuracy: 0.1143 - loss: 3.1400
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 68ms/step - accuracy: 0.1144 - loss: 3.1393
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 68ms/step - accuracy: 0.1145 - loss: 3.1386
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 68ms/step - accuracy: 0.1146 - loss: 3.1379
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 68ms/step - accuracy: 0.1148 - loss: 3.1365
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 68ms/step - accuracy: 0.1149 - loss: 3.1358
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 68ms/step - accuracy: 0.1150 - loss: 3.1351
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 68ms/step - accuracy: 0.1151 - loss: 3.1344
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 68ms/step - accuracy: 0.1152 - loss: 3.1338
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 68ms/step - accuracy: 0.1153 - loss: 3.1331
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m28s[0m 39ms/step - accuracy: 0.0874 - loss: 3.1737
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m28s[0m 39ms/step - accuracy: 0.0874 - loss: 3.1734
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m28s[0m 39ms/step - accuracy: 0.0875 - loss: 3.1732
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 68ms/step - accuracy: 0.1158 - loss: 3.1297
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 68ms/step - accuracy: 0.1159 - loss: 3.1290

Trial status: 20 RUNNING
Current time: 2025-11-07 13:53:02. 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_a058a    RUNNING            3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21 │
│ trial_a058a    RUNNING            3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15 │
│ trial_a058a    RUNNING            2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26 │
│ trial_a058a    RUNNING            2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28 │
│ trial_a058a    RUNNING            2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22 │
│ trial_a058a    RUNNING            2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21 │
│ trial_a058a    RUNNING            3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24 │
│ trial_a058a    RUNNING            2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28 │
│ trial_a058a    RUNNING            2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25 │
│ trial_a058a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23 │
│ trial_a058a    RUNNING            3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23 │
│ trial_a058a    RUNNING            2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27 │
│ trial_a058a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000164705         24 │
│ trial_a058a    RUNNING            2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24 │
│ trial_a058a    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21 │
│ trial_a058a    RUNNING            3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 219/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 68ms/step - accuracy: 0.1162 - loss: 3.1270
[1m 220/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 68ms/step - accuracy: 0.1163 - loss: 3.1264
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 221/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 68ms/step - accuracy: 0.1164 - loss: 3.1257
[1m 222/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 68ms/step - accuracy: 0.1165 - loss: 3.1250
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 223/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 68ms/step - accuracy: 0.1166 - loss: 3.1244
[1m 224/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 68ms/step - accuracy: 0.1167 - loss: 3.1237
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 225/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 68ms/step - accuracy: 0.1168 - loss: 3.1230
[1m 226/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 68ms/step - accuracy: 0.1169 - loss: 3.1224
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 227/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 68ms/step - accuracy: 0.1170 - loss: 3.1217
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 68ms/step - accuracy: 0.1171 - loss: 3.1211
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m373/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 52ms/step - accuracy: 0.0728 - loss: 3.3192[32m [repeated 119x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m234/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m23s[0m 67ms/step - accuracy: 0.0793 - loss: 3.3008
[1m235/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m23s[0m 67ms/step - accuracy: 0.0793 - loss: 3.3005[32m [repeated 147x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 68ms/step - accuracy: 0.1172 - loss: 3.1204
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 68ms/step - accuracy: 0.1173 - loss: 3.1198
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 68ms/step - accuracy: 0.1174 - loss: 3.1191
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 68ms/step - accuracy: 0.1175 - loss: 3.1185
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 68ms/step - accuracy: 0.1176 - loss: 3.1179
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:03[0m 68ms/step - accuracy: 0.1177 - loss: 3.1172
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m30s[0m 42ms/step - accuracy: 0.0828 - loss: 3.2842
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m29s[0m 42ms/step - accuracy: 0.0828 - loss: 3.2842[32m [repeated 155x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m466/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 43ms/step - accuracy: 0.1628 - loss: 2.7425
[1m467/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 43ms/step - accuracy: 0.1629 - loss: 2.7420
[1m468/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 43ms/step - accuracy: 0.1630 - loss: 2.7416[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m29s[0m 42ms/step - accuracy: 0.0828 - loss: 3.2841[32m [repeated 238x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:02[0m 68ms/step - accuracy: 0.1184 - loss: 3.1122
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:02[0m 68ms/step - accuracy: 0.1185 - loss: 3.1115
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:02[0m 67ms/step - accuracy: 0.1189 - loss: 3.1090
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:02[0m 67ms/step - accuracy: 0.1190 - loss: 3.1084
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 249/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:01[0m 67ms/step - accuracy: 0.1191 - loss: 3.1077
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:01[0m 67ms/step - accuracy: 0.1191 - loss: 3.1071
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 254/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:01[0m 67ms/step - accuracy: 0.1195 - loss: 3.1045
[1m 255/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:01[0m 67ms/step - accuracy: 0.1196 - loss: 3.1039
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:01[0m 67ms/step - accuracy: 0.1197 - loss: 3.1032[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:01[0m 67ms/step - accuracy: 0.1199 - loss: 3.1020
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:01[0m 68ms/step - accuracy: 0.1200 - loss: 3.1013
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:01[0m 67ms/step - accuracy: 0.1203 - loss: 3.0995
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:00[0m 67ms/step - accuracy: 0.1203 - loss: 3.0989
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m514/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 44ms/step - accuracy: 0.1659 - loss: 2.7240
[1m516/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 44ms/step - accuracy: 0.1660 - loss: 2.7233[32m [repeated 94x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:00[0m 67ms/step - accuracy: 0.1207 - loss: 3.0964
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:00[0m 67ms/step - accuracy: 0.1208 - loss: 3.0958
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m347/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 57ms/step - accuracy: 0.0868 - loss: 3.2498
[1m348/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 57ms/step - accuracy: 0.0869 - loss: 3.2495
[1m349/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 57ms/step - accuracy: 0.0869 - loss: 3.2492[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:00[0m 67ms/step - accuracy: 0.1209 - loss: 3.0951
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:00[0m 67ms/step - accuracy: 0.1210 - loss: 3.0945
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:00[0m 67ms/step - accuracy: 0.1210 - loss: 3.0939
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:00[0m 67ms/step - accuracy: 0.1211 - loss: 3.0933
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m26s[0m 39ms/step - accuracy: 0.0885 - loss: 3.2021 - val_accuracy: 0.1793 - val_loss: 2.6412
[36m(train_cnn_ray_tune pid=2857957)[0m Epoch 2/24
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:00[0m 67ms/step - accuracy: 0.1212 - loss: 3.0927
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m59s[0m 67ms/step - accuracy: 0.1213 - loss: 3.0921 
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m528/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 44ms/step - accuracy: 0.1667 - loss: 2.7189[32m [repeated 130x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 102ms/step - accuracy: 0.1250 - loss: 2.6591
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 35ms/step - accuracy: 0.1042 - loss: 2.7798 
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 32ms/step - accuracy: 0.0698 - loss: 3.3089
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 32ms/step - accuracy: 0.0699 - loss: 3.3085
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 32ms/step - accuracy: 0.0699 - loss: 3.3083
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m355/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m15s[0m 67ms/step - accuracy: 0.1585 - loss: 2.8769[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m408/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 57ms/step - accuracy: 0.0901 - loss: 3.2315
[1m409/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 57ms/step - accuracy: 0.0901 - loss: 3.2312[32m [repeated 106x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m410/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 57ms/step - accuracy: 0.0902 - loss: 3.2309 
[1m411/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 57ms/step - accuracy: 0.0902 - loss: 3.2306
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 33ms/step - accuracy: 0.0737 - loss: 3.2805
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 33ms/step - accuracy: 0.0737 - loss: 3.2803
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 33ms/step - accuracy: 0.0737 - loss: 3.2802
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m33s[0m 50ms/step - accuracy: 0.0810 - loss: 3.3052
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m33s[0m 50ms/step - accuracy: 0.0810 - loss: 3.3050[32m [repeated 190x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m417/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 55ms/step - accuracy: 0.1360 - loss: 2.8906
[1m418/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 55ms/step - accuracy: 0.1360 - loss: 2.8903
[1m419/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 55ms/step - accuracy: 0.1361 - loss: 2.8900
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m24s[0m 42ms/step - accuracy: 0.0841 - loss: 3.2794[32m [repeated 220x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:00[0m 67ms/step - accuracy: 0.1205 - loss: 3.0976[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m511/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 52ms/step - accuracy: 0.0750 - loss: 3.3001
[1m512/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 52ms/step - accuracy: 0.0750 - loss: 3.3000[32m [repeated 87x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m31s[0m 43ms/step - accuracy: 0.0676 - loss: 3.3771 - val_accuracy: 0.1462 - val_loss: 2.7465[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m Epoch 2/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 108ms/step - accuracy: 0.0625 - loss: 3.0828
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m501/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 49ms/step - accuracy: 0.0765 - loss: 3.3026[32m [repeated 131x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 61ms/step - accuracy: 0.1250 - loss: 2.6041
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 21ms/step - accuracy: 0.1224 - loss: 2.6722
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 34ms/step - accuracy: 0.0851 - loss: 3.0492  
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 38ms/step - accuracy: 0.0817 - loss: 3.0843
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m13s[0m 34ms/step - accuracy: 0.0751 - loss: 3.2689
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m13s[0m 34ms/step - accuracy: 0.0751 - loss: 3.2686
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m13s[0m 34ms/step - accuracy: 0.0752 - loss: 3.2683
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m12s[0m 34ms/step - accuracy: 0.0754 - loss: 3.2660
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m12s[0m 34ms/step - accuracy: 0.0755 - loss: 3.2659
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m12s[0m 34ms/step - accuracy: 0.0755 - loss: 3.2657
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1027 - loss: 3.1376
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1027 - loss: 3.1373
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1028 - loss: 3.1370
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1028 - loss: 3.1368
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1028 - loss: 3.1366
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1028 - loss: 3.1364
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m428/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 66ms/step - accuracy: 0.1626 - loss: 2.8408
[1m429/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 66ms/step - accuracy: 0.1626 - loss: 2.8404
[1m430/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 66ms/step - accuracy: 0.1627 - loss: 2.8399
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1029 - loss: 3.1361
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1029 - loss: 3.1359
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1029 - loss: 3.1358
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1029 - loss: 3.1356
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1029 - loss: 3.1354
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1029 - loss: 3.1352
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.1030 - loss: 3.1350
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.1030 - loss: 3.1348
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m 28/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 43ms/step - accuracy: 0.1454 - loss: 2.8870[32m [repeated 104x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m 10/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 46ms/step - accuracy: 0.2159 - loss: 2.3172
[1m 12/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 45ms/step - accuracy: 0.2175 - loss: 2.3089[32m [repeated 113x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m432/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 66ms/step - accuracy: 0.1628 - loss: 2.8390 
[1m433/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 66ms/step - accuracy: 0.1629 - loss: 2.8386
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.1030 - loss: 3.1346
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.1030 - loss: 3.1344
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.1030 - loss: 3.1342
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.1030 - loss: 3.1340
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.1031 - loss: 3.1338
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.1031 - loss: 3.1336
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.1031 - loss: 3.1332
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.1031 - loss: 3.1330
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m50s[0m 66ms/step - accuracy: 0.1307 - loss: 3.0255
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m50s[0m 66ms/step - accuracy: 0.1307 - loss: 3.0250[32m [repeated 160x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.1032 - loss: 3.1328
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m20s[0m 43ms/step - accuracy: 0.0854 - loss: 3.2741[32m [repeated 278x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.1032 - loss: 3.1326
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.1032 - loss: 3.1324
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.1032 - loss: 3.1322
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.1032 - loss: 3.1320
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.1033 - loss: 3.1317
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.1033 - loss: 3.1315
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.1033 - loss: 3.1312
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.1033 - loss: 3.1310
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.1034 - loss: 3.1307
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.1034 - loss: 3.1305
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.1034 - loss: 3.1303
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.1034 - loss: 3.1300
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.1034 - loss: 3.1298
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.1035 - loss: 3.1296
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.1035 - loss: 3.1295
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.1035 - loss: 3.1289
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m539/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 57ms/step - accuracy: 0.0957 - loss: 3.1975
[1m540/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 57ms/step - accuracy: 0.0958 - loss: 3.1972[32m [repeated 94x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 51ms/step - accuracy: 0.1699 - loss: 2.6997 - val_accuracy: 0.2122 - val_loss: 2.3201[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m Epoch 2/25[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 127ms/step - accuracy: 0.1875 - loss: 2.4642[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m548/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 57ms/step - accuracy: 0.0961 - loss: 3.1953[32m [repeated 102x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 34ms/step - accuracy: 0.0781 - loss: 3.2447[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 32ms/step - accuracy: 0.1045 - loss: 3.1196
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 31ms/step - accuracy: 0.1046 - loss: 3.1193[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m211/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m12s[0m 34ms/step - accuracy: 0.1020 - loss: 3.0649[32m [repeated 147x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m128/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m19s[0m 42ms/step - accuracy: 0.2337 - loss: 2.2564
[1m130/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m19s[0m 42ms/step - accuracy: 0.2338 - loss: 2.2562[32m [repeated 114x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m15s[0m 43ms/step - accuracy: 0.0866 - loss: 3.2685
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m15s[0m 43ms/step - accuracy: 0.0866 - loss: 3.2684[32m [repeated 143x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m29s[0m 52ms/step - accuracy: 0.0707 - loss: 3.3412[32m [repeated 206x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.0680 - loss: 3.4001 
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.0680 - loss: 3.3999
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:35[0m 163ms/step - accuracy: 0.0938 - loss: 2.9476
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 54ms/step - accuracy: 0.0859 - loss: 3.0100  
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m315/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 38ms/step - accuracy: 0.1561 - loss: 2.6667
[1m316/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 38ms/step - accuracy: 0.1561 - loss: 2.6666
[1m317/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 38ms/step - accuracy: 0.1562 - loss: 2.6665
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m495/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 67ms/step - accuracy: 0.0899 - loss: 3.2236
[1m496/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 67ms/step - accuracy: 0.0899 - loss: 3.2233[32m [repeated 82x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m42s[0m 65ms/step - accuracy: 0.1374 - loss: 2.9789
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m42s[0m 65ms/step - accuracy: 0.1375 - loss: 2.9785
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m42s[0m 65ms/step - accuracy: 0.1375 - loss: 2.9781
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m40s[0m 57ms/step - accuracy: 0.0783 - loss: 3.2856 - val_accuracy: 0.1580 - val_loss: 2.6362[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m Epoch 2/26[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 103ms/step - accuracy: 0.0938 - loss: 2.9505
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m564/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 65ms/step - accuracy: 0.1691 - loss: 2.7857[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m570/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 65ms/step - accuracy: 0.1694 - loss: 2.7835
[1m571/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 65ms/step - accuracy: 0.1694 - loss: 2.7831
[1m572/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 65ms/step - accuracy: 0.1694 - loss: 2.7828
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m304/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1045 - loss: 3.0568 
[1m305/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1046 - loss: 3.0568
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:24[0m 145ms/step - accuracy: 0.2188 - loss: 2.3684
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 64ms/step - accuracy: 0.2188 - loss: 2.3842  
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 41ms/step - accuracy: 0.2148 - loss: 2.4193
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 38ms/step - accuracy: 0.1046 - loss: 3.0735[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 34ms/step - accuracy: 0.0804 - loss: 3.2251
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 34ms/step - accuracy: 0.0804 - loss: 3.2248[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m248/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m14s[0m 42ms/step - accuracy: 0.2376 - loss: 2.2429[32m [repeated 126x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m 28/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 47ms/step - accuracy: 0.1801 - loss: 2.4918
[1m 29/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 47ms/step - accuracy: 0.1799 - loss: 2.4933[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m39s[0m 64ms/step - accuracy: 0.1402 - loss: 2.9592
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m38s[0m 64ms/step - accuracy: 0.1402 - loss: 2.9589[32m [repeated 100x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m17s[0m 49ms/step - accuracy: 0.0903 - loss: 3.2400[32m [repeated 156x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.0875 - loss: 3.2631 
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.0875 - loss: 3.2630
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m577/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 66ms/step - accuracy: 0.0932 - loss: 3.2030
[1m578/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 66ms/step - accuracy: 0.0932 - loss: 3.2028[32m [repeated 114x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m20s[0m 49ms/step - accuracy: 0.0888 - loss: 3.2512
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m20s[0m 49ms/step - accuracy: 0.0888 - loss: 3.2510
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m20s[0m 49ms/step - accuracy: 0.0888 - loss: 3.2508
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m43s[0m 66ms/step - accuracy: 0.0976 - loss: 3.1864 - val_accuracy: 0.1610 - val_loss: 2.5484[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m Epoch 2/21[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 66ms/step - accuracy: 0.0935 - loss: 3.2014[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m46s[0m 35ms/step - accuracy: 0.1060 - loss: 3.1064 - val_accuracy: 0.1795 - val_loss: 2.5161
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:42[0m 88ms/step - accuracy: 0.1875 - loss: 3.3141
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 33ms/step - accuracy: 0.1667 - loss: 3.1527 
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 118ms/step - accuracy: 0.2812 - loss: 2.4589
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m343/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 41ms/step - accuracy: 0.2393 - loss: 2.2338 
[1m345/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 41ms/step - accuracy: 0.2394 - loss: 2.2337
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 45ms/step - accuracy: 0.1011 - loss: 3.2064 
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 45ms/step - accuracy: 0.1011 - loss: 3.2062
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 38ms/step - accuracy: 0.1078 - loss: 3.0543[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 41ms/step - accuracy: 0.0882 - loss: 3.2584
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 41ms/step - accuracy: 0.0882 - loss: 3.2583[32m [repeated 70x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 119ms/step - accuracy: 0.1875 - loss: 2.5546
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m132/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m22s[0m 49ms/step - accuracy: 0.1822 - loss: 2.5090[32m [repeated 141x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m104/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m24s[0m 50ms/step - accuracy: 0.1607 - loss: 2.7994
[1m105/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m24s[0m 50ms/step - accuracy: 0.1607 - loss: 2.7993[32m [repeated 119x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m11s[0m 49ms/step - accuracy: 0.0929 - loss: 3.2218
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m11s[0m 49ms/step - accuracy: 0.0929 - loss: 3.2214[32m [repeated 82x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m32s[0m 63ms/step - accuracy: 0.1445 - loss: 2.9270[32m [repeated 124x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.1341 - loss: 2.9040 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.1314 - loss: 2.8820
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m437/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 41ms/step - accuracy: 0.2405 - loss: 2.2268
[1m439/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 41ms/step - accuracy: 0.2405 - loss: 2.2266[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m51s[0m 74ms/step - accuracy: 0.0935 - loss: 3.2011 - val_accuracy: 0.1526 - val_loss: 2.5657[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m Epoch 2/24[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m233/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m16s[0m 48ms/step - accuracy: 0.1149 - loss: 2.9808
[1m234/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m16s[0m 48ms/step - accuracy: 0.1149 - loss: 2.9808
[1m235/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m16s[0m 48ms/step - accuracy: 0.1149 - loss: 2.9807
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m450/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 41ms/step - accuracy: 0.2407 - loss: 2.2258[32m [repeated 87x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m50s[0m 38ms/step - accuracy: 0.0812 - loss: 3.2187 - val_accuracy: 0.1471 - val_loss: 2.5822
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 132ms/step - accuracy: 0.2812 - loss: 2.6759
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 54ms/step - accuracy: 0.2656 - loss: 2.7274  
Trial status: 20 RUNNING
Current time: 2025-11-07 13:53:32. 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_a058a    RUNNING            3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21 │
│ trial_a058a    RUNNING            3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15 │
│ trial_a058a    RUNNING            2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26 │
│ trial_a058a    RUNNING            2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28 │
│ trial_a058a    RUNNING            2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22 │
│ trial_a058a    RUNNING            2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21 │
│ trial_a058a    RUNNING            3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24 │
│ trial_a058a    RUNNING            2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28 │
│ trial_a058a    RUNNING            2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25 │
│ trial_a058a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23 │
│ trial_a058a    RUNNING            3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23 │
│ trial_a058a    RUNNING            2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27 │
│ trial_a058a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000164705         24 │
│ trial_a058a    RUNNING            2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24 │
│ trial_a058a    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21 │
│ trial_a058a    RUNNING            3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m8s[0m 49ms/step - accuracy: 0.0945 - loss: 3.2107
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m8s[0m 49ms/step - accuracy: 0.0945 - loss: 3.2105
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m8s[0m 49ms/step - accuracy: 0.0945 - loss: 3.2104
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 49ms/step - accuracy: 0.0946 - loss: 3.2101[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 45ms/step - accuracy: 0.1025 - loss: 3.1922
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 45ms/step - accuracy: 0.1025 - loss: 3.1920[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:31[0m 79ms/step - accuracy: 0.1250 - loss: 2.9442[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m148/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m14s[0m 32ms/step - accuracy: 0.1483 - loss: 2.7177[32m [repeated 178x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 37/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 63ms/step - accuracy: 0.1622 - loss: 2.8644
[1m 38/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 63ms/step - accuracy: 0.1620 - loss: 2.8643[32m [repeated 127x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m12s[0m 51ms/step - accuracy: 0.0742 - loss: 3.3156
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m12s[0m 51ms/step - accuracy: 0.0742 - loss: 3.3156[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m28s[0m 31ms/step - accuracy: 0.1479 - loss: 2.8009
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m28s[0m 31ms/step - accuracy: 0.1479 - loss: 2.8008
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m28s[0m 31ms/step - accuracy: 0.1479 - loss: 2.8007
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m12s[0m 51ms/step - accuracy: 0.0742 - loss: 3.3155[32m [repeated 116x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m56s[0m 45ms/step - accuracy: 0.0697 - loss: 3.3816 - val_accuracy: 0.1040 - val_loss: 2.8911
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 30ms/step - accuracy: 0.0764 - loss: 3.2107 
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m553/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 42ms/step - accuracy: 0.1408 - loss: 2.8677
[1m555/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 42ms/step - accuracy: 0.1408 - loss: 2.8676[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m23s[0m 40ms/step - accuracy: 0.1089 - loss: 3.0413 - val_accuracy: 0.1369 - val_loss: 2.6717[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m Epoch 2/16[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 50/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 64ms/step - accuracy: 0.1593 - loss: 2.8677
[1m 51/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 63ms/step - accuracy: 0.1591 - loss: 2.8678
[1m 52/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 63ms/step - accuracy: 0.1589 - loss: 2.8681[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m560/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 42ms/step - accuracy: 0.2422 - loss: 2.2165[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 39ms/step - accuracy: 0.1250 - loss: 3.2180  
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 33ms/step - accuracy: 0.1363 - loss: 3.1436
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m8s[0m 51ms/step - accuracy: 0.0749 - loss: 3.3101[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m8s[0m 51ms/step - accuracy: 0.0750 - loss: 3.3100
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m8s[0m 51ms/step - accuracy: 0.0750 - loss: 3.3099[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:48[0m 144ms/step - accuracy: 0.1250 - loss: 3.3585[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m168/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m26s[0m 63ms/step - accuracy: 0.2350 - loss: 2.2952[32m [repeated 247x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m116/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m29s[0m 63ms/step - accuracy: 0.1553 - loss: 2.8723
[1m117/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m29s[0m 64ms/step - accuracy: 0.1553 - loss: 2.8722[32m [repeated 175x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m22s[0m 63ms/step - accuracy: 0.1511 - loss: 2.8806
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m22s[0m 63ms/step - accuracy: 0.1511 - loss: 2.8804[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m27s[0m 63ms/step - accuracy: 0.1479 - loss: 2.9030
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m27s[0m 63ms/step - accuracy: 0.1479 - loss: 2.9027
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m27s[0m 63ms/step - accuracy: 0.1479 - loss: 2.9024
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m  67/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 35ms/step - accuracy: 0.1595 - loss: 2.8408[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 47ms/step - accuracy: 0.0868 - loss: 3.3247  
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m59s[0m 47ms/step - accuracy: 0.0889 - loss: 3.2535 - val_accuracy: 0.1308 - val_loss: 2.7508[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m413/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 51ms/step - accuracy: 0.1075 - loss: 3.0594
[1m414/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 51ms/step - accuracy: 0.1075 - loss: 3.0594[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 48ms/step - accuracy: 0.2425 - loss: 2.2143 - val_accuracy: 0.2176 - val_loss: 2.1706[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m Epoch 3/25[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m114/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m15s[0m 33ms/step - accuracy: 0.1159 - loss: 2.9537
[1m116/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m15s[0m 33ms/step - accuracy: 0.1159 - loss: 2.9540
[1m119/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 33ms/step - accuracy: 0.1160 - loss: 2.9546[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m377/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 34ms/step - accuracy: 0.1501 - loss: 2.7225[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 51ms/step - accuracy: 0.0758 - loss: 3.3037[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m17s[0m 63ms/step - accuracy: 0.1536 - loss: 2.8625
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m17s[0m 63ms/step - accuracy: 0.1537 - loss: 2.8623
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m17s[0m 63ms/step - accuracy: 0.1537 - loss: 2.8620
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 50ms/step - accuracy: 0.0758 - loss: 3.3034
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 50ms/step - accuracy: 0.0758 - loss: 3.3033[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 113ms/step - accuracy: 0.2500 - loss: 2.4772[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m202/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m23s[0m 62ms/step - accuracy: 0.1551 - loss: 2.8666[32m [repeated 159x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m249/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m20s[0m 62ms/step - accuracy: 0.2379 - loss: 2.2754
[1m250/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m20s[0m 62ms/step - accuracy: 0.2379 - loss: 2.2752[32m [repeated 158x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 37ms/step - accuracy: 0.1045 - loss: 3.1732
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 37ms/step - accuracy: 0.1045 - loss: 3.1728[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:58[0m 102ms/step - accuracy: 0.1250 - loss: 3.1970
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 39ms/step - accuracy: 0.1285 - loss: 3.1893  
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 221/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m31s[0m 34ms/step - accuracy: 0.1689 - loss: 2.7579[32m [repeated 185x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m317/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.1787 - loss: 2.5213 
[1m319/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.1787 - loss: 2.5212
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m426/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 52ms/step - accuracy: 0.1604 - loss: 2.7929
[1m427/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 52ms/step - accuracy: 0.1604 - loss: 2.7928
[1m428/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 52ms/step - accuracy: 0.1604 - loss: 2.7928
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m64s[0m 51ms/step - accuracy: 0.1033 - loss: 3.1845 - val_accuracy: 0.1634 - val_loss: 2.5514
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m515/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 51ms/step - accuracy: 0.1079 - loss: 3.0582
[1m516/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 51ms/step - accuracy: 0.1079 - loss: 3.0581[32m [repeated 105x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m Epoch 2/22
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m233/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 61ms/step - accuracy: 0.1550 - loss: 2.8649
[1m234/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m21s[0m 61ms/step - accuracy: 0.1550 - loss: 2.8648
[1m235/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m21s[0m 61ms/step - accuracy: 0.1549 - loss: 2.8647[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m448/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 52ms/step - accuracy: 0.1605 - loss: 2.7918[32m [repeated 128x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 50ms/step - accuracy: 0.0763 - loss: 3.2996[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 50ms/step - accuracy: 0.0763 - loss: 3.3001
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 50ms/step - accuracy: 0.0763 - loss: 3.3000[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m286/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m17s[0m 60ms/step - accuracy: 0.1548 - loss: 2.8610[32m [repeated 65x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m290/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m17s[0m 60ms/step - accuracy: 0.1548 - loss: 2.8608
[1m291/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m17s[0m 60ms/step - accuracy: 0.1548 - loss: 2.8607[32m [repeated 83x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m69s[0m 56ms/step - accuracy: 0.0976 - loss: 3.1884 - val_accuracy: 0.1580 - val_loss: 2.5191
[36m(train_cnn_ray_tune pid=2857962)[0m Epoch 2/21
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m11s[0m 62ms/step - accuracy: 0.1571 - loss: 2.8385
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m11s[0m 62ms/step - accuracy: 0.1571 - loss: 2.8383[32m [repeated 171x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:07[0m 109ms/step - accuracy: 0.2500 - loss: 2.6750
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 41ms/step - accuracy: 0.1362 - loss: 2.9415[32m [repeated 163x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 58ms/step - accuracy: 0.2014 - loss: 2.8273 
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 49ms/step - accuracy: 0.1740 - loss: 2.8712 
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m30s[0m 52ms/step - accuracy: 0.1175 - loss: 2.9641 - val_accuracy: 0.1673 - val_loss: 2.5374
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 41ms/step - accuracy: 0.1111 - loss: 3.1586  
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 35ms/step - accuracy: 0.1251 - loss: 3.0552
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m542/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 51ms/step - accuracy: 0.1611 - loss: 2.7872
[1m544/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 51ms/step - accuracy: 0.1611 - loss: 2.7871[32m [repeated 123x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m344/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 62ms/step - accuracy: 0.2411 - loss: 2.2566
[1m345/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 61ms/step - accuracy: 0.2412 - loss: 2.2564
[1m346/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 61ms/step - accuracy: 0.2412 - loss: 2.2563[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m554/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 51ms/step - accuracy: 0.1611 - loss: 2.7867[32m [repeated 121x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 62ms/step - accuracy: 0.1590 - loss: 2.8242[32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 29ms/step - accuracy: 0.1484 - loss: 2.7736
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 29ms/step - accuracy: 0.1484 - loss: 2.7736[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 11/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 52ms/step - accuracy: 0.1459 - loss: 2.9586[32m [repeated 107x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 76/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 43ms/step - accuracy: 0.1262 - loss: 2.8964
[1m 77/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 43ms/step - accuracy: 0.1262 - loss: 2.8959[32m [repeated 89x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:08:15[0m 13s/step - accuracy: 0.3125 - loss: 2.1624
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 38ms/step - accuracy: 0.3073 - loss: 2.0640   
[36m(train_cnn_ray_tune pid=2857955)[0m Epoch 3/24[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m74s[0m 57ms/step - accuracy: 0.0763 - loss: 3.2995 - val_accuracy: 0.1228 - val_loss: 2.7461
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m12s[0m 31ms/step - accuracy: 0.1224 - loss: 2.9057
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m12s[0m 31ms/step - accuracy: 0.1224 - loss: 2.9057[32m [repeated 150x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 93ms/step - accuracy: 0.1875 - loss: 2.7881[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m29s[0m 37ms/step - accuracy: 0.1064 - loss: 3.1358[32m [repeated 170x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 46ms/step - accuracy: 0.1111 - loss: 3.2100  
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 44ms/step - accuracy: 0.1192 - loss: 3.1550
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 57ms/step - accuracy: 0.1083 - loss: 3.0564 - val_accuracy: 0.1369 - val_loss: 2.5944[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 33ms/step - accuracy: 0.2448 - loss: 2.6446  
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 34ms/step - accuracy: 0.2206 - loss: 2.6528
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m417/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 60ms/step - accuracy: 0.1542 - loss: 2.8538 
[1m418/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 60ms/step - accuracy: 0.1542 - loss: 2.8537
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m464/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 60ms/step - accuracy: 0.2445 - loss: 2.2398
[1m465/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 60ms/step - accuracy: 0.2445 - loss: 2.2397[32m [repeated 60x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m408/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 60ms/step - accuracy: 0.1542 - loss: 2.8543
[1m409/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 60ms/step - accuracy: 0.1542 - loss: 2.8542
[1m410/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 60ms/step - accuracy: 0.1542 - loss: 2.8542[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m475/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 60ms/step - accuracy: 0.2448 - loss: 2.2385[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 62ms/step - accuracy: 0.1615 - loss: 2.8066[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 30ms/step - accuracy: 0.1492 - loss: 2.7655
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 30ms/step - accuracy: 0.1492 - loss: 2.7654[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m 47/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 60ms/step - accuracy: 0.2162 - loss: 2.3250[32m [repeated 134x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m 17/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 55ms/step - accuracy: 0.1557 - loss: 2.6472
[1m 18/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 56ms/step - accuracy: 0.1567 - loss: 2.6460[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 55ms/step - accuracy: 0.1094 - loss: 2.6058  
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 36ms/step - accuracy: 0.1257 - loss: 2.6038
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 110ms/step - accuracy: 0.1250 - loss: 2.7862
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 58ms/step - accuracy: 0.1250 - loss: 2.7789  [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m Epoch 4/28[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m24s[0m 38ms/step - accuracy: 0.1071 - loss: 3.1290
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m24s[0m 38ms/step - accuracy: 0.1071 - loss: 3.1288[32m [repeated 130x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 127ms/step - accuracy: 0.0938 - loss: 2.6642[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 221/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m43s[0m 46ms/step - accuracy: 0.1267 - loss: 2.8873[32m [repeated 201x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 43ms/step - accuracy: 0.1781 - loss: 2.5107 - val_accuracy: 0.1932 - val_loss: 2.3336[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m513/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 40ms/step - accuracy: 0.1501 - loss: 2.7388
[1m514/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 40ms/step - accuracy: 0.1501 - loss: 2.7388
[1m515/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 40ms/step - accuracy: 0.1501 - loss: 2.7388
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m495/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 61ms/step - accuracy: 0.1541 - loss: 2.8483
[1m496/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 61ms/step - accuracy: 0.1541 - loss: 2.8483[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m117/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m24s[0m 53ms/step - accuracy: 0.1237 - loss: 3.0037
[1m118/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m24s[0m 53ms/step - accuracy: 0.1237 - loss: 3.0036
[1m119/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m24s[0m 53ms/step - accuracy: 0.1237 - loss: 3.0036[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m533/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 40ms/step - accuracy: 0.1501 - loss: 2.7382[32m [repeated 73x across cluster][0m
Trial status: 20 RUNNING
Current time: 2025-11-07 13:54:02. 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_a058a    RUNNING            3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21 │
│ trial_a058a    RUNNING            3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15 │
│ trial_a058a    RUNNING            2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26 │
│ trial_a058a    RUNNING            2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28 │
│ trial_a058a    RUNNING            2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22 │
│ trial_a058a    RUNNING            2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21 │
│ trial_a058a    RUNNING            3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24 │
│ trial_a058a    RUNNING            2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28 │
│ trial_a058a    RUNNING            2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25 │
│ trial_a058a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23 │
│ trial_a058a    RUNNING            3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23 │
│ trial_a058a    RUNNING            2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27 │
│ trial_a058a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000164705         24 │
│ trial_a058a    RUNNING            2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24 │
│ trial_a058a    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21 │
│ trial_a058a    RUNNING            3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 32ms/step - accuracy: 0.1220 - loss: 2.9012[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 32ms/step - accuracy: 0.1220 - loss: 2.9010
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 32ms/step - accuracy: 0.1220 - loss: 2.9010[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m199/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 35ms/step - accuracy: 0.1404 - loss: 2.8658[32m [repeated 174x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m228/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m15s[0m 43ms/step - accuracy: 0.2649 - loss: 2.0648
[1m230/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m15s[0m 43ms/step - accuracy: 0.2649 - loss: 2.0647[32m [repeated 156x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m19s[0m 38ms/step - accuracy: 0.1076 - loss: 3.1236
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m19s[0m 38ms/step - accuracy: 0.1076 - loss: 3.1236[32m [repeated 112x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m12s[0m 34ms/step - accuracy: 0.1760 - loss: 2.6912[32m [repeated 186x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m39s[0m 33ms/step - accuracy: 0.1495 - loss: 2.7613 - val_accuracy: 0.1969 - val_loss: 2.4178
[36m(train_cnn_ray_tune pid=2857965)[0m Epoch 3/25
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m522/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 60ms/step - accuracy: 0.1541 - loss: 2.8463
[1m523/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 60ms/step - accuracy: 0.1541 - loss: 2.8463
[1m524/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 60ms/step - accuracy: 0.1541 - loss: 2.8462
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:49[0m 94ms/step - accuracy: 0.2500 - loss: 3.0096
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 25ms/step - accuracy: 0.2227 - loss: 2.7294 
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m355/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.1283 - loss: 2.8564 
[1m357/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 43ms/step - accuracy: 0.1284 - loss: 2.8562
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m489/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 32ms/step - accuracy: 0.1692 - loss: 2.6406
[1m492/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 32ms/step - accuracy: 0.1692 - loss: 2.6406[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m26s[0m 45ms/step - accuracy: 0.1500 - loss: 2.7367 - val_accuracy: 0.1669 - val_loss: 2.4325
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m116/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m27s[0m 58ms/step - accuracy: 0.2169 - loss: 2.3332
[1m117/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m26s[0m 58ms/step - accuracy: 0.2169 - loss: 2.3332
[1m118/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m26s[0m 58ms/step - accuracy: 0.2169 - loss: 2.3332
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 82ms/step - accuracy: 0.0625 - loss: 2.9305
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 28ms/step - accuracy: 0.1389 - loss: 2.7744
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m294/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.1381 - loss: 2.8643[32m [repeated 65x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.1764 - loss: 2.6869 
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.1764 - loss: 2.6868
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 62ms/step - accuracy: 0.2891 - loss: 1.9568  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 62ms/step - accuracy: 0.2865 - loss: 1.9682
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 34ms/step - accuracy: 0.1766 - loss: 2.6851[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 34ms/step - accuracy: 0.1766 - loss: 2.6844
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 34ms/step - accuracy: 0.1766 - loss: 2.6843[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m223/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 50ms/step - accuracy: 0.1705 - loss: 2.6449[32m [repeated 164x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m249/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 52ms/step - accuracy: 0.2179 - loss: 2.3268
[1m250/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 52ms/step - accuracy: 0.2179 - loss: 2.3268[32m [repeated 139x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 24ms/step - accuracy: 0.1581 - loss: 2.6263
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 24ms/step - accuracy: 0.1581 - loss: 2.6262[32m [repeated 130x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m13s[0m 37ms/step - accuracy: 0.1084 - loss: 3.1183[32m [repeated 179x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 62ms/step - accuracy: 0.2344 - loss: 2.0008 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 63ms/step - accuracy: 0.2257 - loss: 2.0495
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 59ms/step - accuracy: 0.2375 - loss: 2.0878
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 60ms/step - accuracy: 0.2418 - loss: 2.0904
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 39/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 61ms/step - accuracy: 0.2665 - loss: 2.0445
[1m 40/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 61ms/step - accuracy: 0.2665 - loss: 2.0450
[1m 41/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 61ms/step - accuracy: 0.2665 - loss: 2.0455
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 53ms/step - accuracy: 0.2479 - loss: 2.1112
[1m  12/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.2477 - loss: 2.1160
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.2471 - loss: 2.1201
[1m  14/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.2464 - loss: 2.1236
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  15/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 56ms/step - accuracy: 0.2458 - loss: 2.1252
[1m  16/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.2460 - loss: 2.1255
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m89s[0m 70ms/step - accuracy: 0.1624 - loss: 2.7998 - val_accuracy: 0.2287 - val_loss: 2.2122
[36m(train_cnn_ray_tune pid=2857952)[0m Epoch 3/24[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:34[0m 163ms/step - accuracy: 0.1562 - loss: 2.8172[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  17/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 58ms/step - accuracy: 0.2465 - loss: 2.1245[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m41s[0m 35ms/step - accuracy: 0.1219 - loss: 2.8986 - val_accuracy: 0.1608 - val_loss: 2.5119
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  18/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.2469 - loss: 2.1247
[1m  19/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.2472 - loss: 2.1250
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m284/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.1383 - loss: 2.8646 
[1m286/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.1382 - loss: 2.8646
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 43ms/step - accuracy: 0.1319 - loss: 2.8821 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 38ms/step - accuracy: 0.1323 - loss: 2.8370
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.2459 - loss: 2.1322
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.2456 - loss: 2.1340
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.2452 - loss: 2.1364
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.2445 - loss: 2.1394
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m439/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 33ms/step - accuracy: 0.1359 - loss: 2.8617
[1m441/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 33ms/step - accuracy: 0.1359 - loss: 2.8617[32m [repeated 84x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.2439 - loss: 2.1424
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 61ms/step - accuracy: 0.2433 - loss: 2.1457
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m21s[0m 36ms/step - accuracy: 0.1689 - loss: 2.6390 - val_accuracy: 0.2185 - val_loss: 2.3873[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  30/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.2426 - loss: 2.1490
[1m  31/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.2420 - loss: 2.1519
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m357/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 36ms/step - accuracy: 0.1858 - loss: 2.4525[32m [repeated 93x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  32/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.2415 - loss: 2.1544
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.2409 - loss: 2.1570
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.2404 - loss: 2.1595
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.2399 - loss: 2.1623
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.2395 - loss: 2.1647
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.2393 - loss: 2.1670
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.2389 - loss: 2.1693
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 63ms/step - accuracy: 0.2387 - loss: 2.1715
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 63ms/step - accuracy: 0.2377 - loss: 2.1779
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 63ms/step - accuracy: 0.2374 - loss: 2.1797
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  45/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 63ms/step - accuracy: 0.2371 - loss: 2.1824
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 64ms/step - accuracy: 0.2369 - loss: 2.1839
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m28s[0m 45ms/step - accuracy: 0.1314 - loss: 2.8730
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m28s[0m 45ms/step - accuracy: 0.1314 - loss: 2.8729
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m28s[0m 45ms/step - accuracy: 0.1315 - loss: 2.8729
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 64ms/step - accuracy: 0.2367 - loss: 2.1855
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 64ms/step - accuracy: 0.2365 - loss: 2.1869
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 64ms/step - accuracy: 0.2363 - loss: 2.1882
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 64ms/step - accuracy: 0.2361 - loss: 2.1895
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 64ms/step - accuracy: 0.2359 - loss: 2.1908
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 64ms/step - accuracy: 0.2357 - loss: 2.1922
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 64ms/step - accuracy: 0.2355 - loss: 2.1938
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 64ms/step - accuracy: 0.2354 - loss: 2.1953
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 34ms/step - accuracy: 0.1772 - loss: 2.6781[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 34ms/step - accuracy: 0.1772 - loss: 2.6777
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 34ms/step - accuracy: 0.1772 - loss: 2.6776[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  60/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 65ms/step - accuracy: 0.2343 - loss: 2.2038
[1m  61/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 65ms/step - accuracy: 0.2341 - loss: 2.2050
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  62/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 65ms/step - accuracy: 0.2339 - loss: 2.2061
[1m  63/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 65ms/step - accuracy: 0.2337 - loss: 2.2073
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  64/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 65ms/step - accuracy: 0.2336 - loss: 2.2084
[1m  65/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 66ms/step - accuracy: 0.2334 - loss: 2.2094
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m 72/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 39ms/step - accuracy: 0.1745 - loss: 2.6141[32m [repeated 148x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m309/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m14s[0m 52ms/step - accuracy: 0.1714 - loss: 2.6425
[1m310/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m14s[0m 52ms/step - accuracy: 0.1714 - loss: 2.6425[32m [repeated 140x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  66/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 65ms/step - accuracy: 0.2333 - loss: 2.2105
[1m  67/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 65ms/step - accuracy: 0.2331 - loss: 2.2116
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 306/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 29ms/step - accuracy: 0.1565 - loss: 2.6317
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 28ms/step - accuracy: 0.1565 - loss: 2.6318[32m [repeated 130x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 34ms/step - accuracy: 0.1219 - loss: 2.8196[32m [repeated 135x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 64ms/step - accuracy: 0.2313 - loss: 2.2201
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 64ms/step - accuracy: 0.2311 - loss: 2.2209
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 64ms/step - accuracy: 0.2305 - loss: 2.2235
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 64ms/step - accuracy: 0.2303 - loss: 2.2243
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 65ms/step - accuracy: 0.2298 - loss: 2.2258
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 65ms/step - accuracy: 0.2297 - loss: 2.2265
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 65ms/step - accuracy: 0.2295 - loss: 2.2271
[1m  86/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 65ms/step - accuracy: 0.2293 - loss: 2.2277
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  87/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 65ms/step - accuracy: 0.2291 - loss: 2.2283
[1m  88/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 65ms/step - accuracy: 0.2290 - loss: 2.2288
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  89/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 65ms/step - accuracy: 0.2288 - loss: 2.2293
[1m  90/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 65ms/step - accuracy: 0.2287 - loss: 2.2298
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m338/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m12s[0m 52ms/step - accuracy: 0.1716 - loss: 2.6420
[1m339/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m12s[0m 52ms/step - accuracy: 0.1716 - loss: 2.6420
[1m340/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m12s[0m 52ms/step - accuracy: 0.1716 - loss: 2.6420
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  91/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 65ms/step - accuracy: 0.2285 - loss: 2.2303
[1m  92/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 65ms/step - accuracy: 0.2284 - loss: 2.2308
[36m(train_cnn_ray_tune pid=2857957)[0m Epoch 5/24[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  93/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 65ms/step - accuracy: 0.2283 - loss: 2.2313
[1m  94/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 65ms/step - accuracy: 0.2281 - loss: 2.2318
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 93ms/step - accuracy: 0.1562 - loss: 2.5580[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 65ms/step - accuracy: 0.2301 - loss: 2.2251[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  95/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 65ms/step - accuracy: 0.2280 - loss: 2.2324
[1m  96/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 65ms/step - accuracy: 0.2278 - loss: 2.2329
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  97/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 65ms/step - accuracy: 0.2277 - loss: 2.2334
[1m  98/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 65ms/step - accuracy: 0.2275 - loss: 2.2339
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m529/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 43ms/step - accuracy: 0.2658 - loss: 2.0506
[1m531/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 43ms/step - accuracy: 0.2659 - loss: 2.0505[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m537/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 42ms/step - accuracy: 0.2659 - loss: 2.0503[32m [repeated 146x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 64ms/step - accuracy: 0.2255 - loss: 2.2407
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 64ms/step - accuracy: 0.2254 - loss: 2.2412
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 64ms/step - accuracy: 0.2252 - loss: 2.2417
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 64ms/step - accuracy: 0.2251 - loss: 2.2422
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 64ms/step - accuracy: 0.2244 - loss: 2.2446
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 64ms/step - accuracy: 0.2243 - loss: 2.2450
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 64ms/step - accuracy: 0.2242 - loss: 2.2454
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 64ms/step - accuracy: 0.2240 - loss: 2.2459
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 64ms/step - accuracy: 0.2239 - loss: 2.2463
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 64ms/step - accuracy: 0.2238 - loss: 2.2468
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 64ms/step - accuracy: 0.2237 - loss: 2.2472
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 64ms/step - accuracy: 0.2236 - loss: 2.2476
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 64ms/step - accuracy: 0.2230 - loss: 2.2495
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 64ms/step - accuracy: 0.2229 - loss: 2.2499
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 64ms/step - accuracy: 0.2228 - loss: 2.2502
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 64ms/step - accuracy: 0.2228 - loss: 2.2506
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 64ms/step - accuracy: 0.2227 - loss: 2.2509
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 64ms/step - accuracy: 0.2226 - loss: 2.2513
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 38ms/step - accuracy: 0.1094 - loss: 3.1120[32m [repeated 97x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 64ms/step - accuracy: 0.2225 - loss: 2.2516
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 64ms/step - accuracy: 0.2224 - loss: 2.2519
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 38ms/step - accuracy: 0.1095 - loss: 3.1118
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 38ms/step - accuracy: 0.1095 - loss: 3.1117[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 140/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 64ms/step - accuracy: 0.2222 - loss: 2.2528
[1m 141/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 64ms/step - accuracy: 0.2221 - loss: 2.2530
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 142/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 64ms/step - accuracy: 0.2220 - loss: 2.2533
[1m 143/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 64ms/step - accuracy: 0.2219 - loss: 2.2535
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m396/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 53ms/step - accuracy: 0.1719 - loss: 2.6416 
[1m397/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 53ms/step - accuracy: 0.1719 - loss: 2.6416
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m133/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m30s[0m 67ms/step - accuracy: 0.1558 - loss: 2.7969[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m308/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m11s[0m 40ms/step - accuracy: 0.1596 - loss: 2.6725
[1m310/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m11s[0m 40ms/step - accuracy: 0.1596 - loss: 2.6725[32m [repeated 136x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 147/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 64ms/step - accuracy: 0.2216 - loss: 2.2546
[1m 149/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 64ms/step - accuracy: 0.2215 - loss: 2.2551
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 64ms/step - accuracy: 0.2214 - loss: 2.2556
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 64ms/step - accuracy: 0.2214 - loss: 2.2558
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m23s[0m 46ms/step - accuracy: 0.1321 - loss: 2.8689
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m23s[0m 46ms/step - accuracy: 0.1321 - loss: 2.8689[32m [repeated 104x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m20s[0m 29ms/step - accuracy: 0.1560 - loss: 2.6348[32m [repeated 133x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 64ms/step - accuracy: 0.2212 - loss: 2.2564
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 64ms/step - accuracy: 0.2212 - loss: 2.2566
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m23s[0m 39ms/step - accuracy: 0.1343 - loss: 2.8612 - val_accuracy: 0.1702 - val_loss: 2.5577
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 64ms/step - accuracy: 0.2211 - loss: 2.2568
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 64ms/step - accuracy: 0.2211 - loss: 2.2570
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 64ms/step - accuracy: 0.2210 - loss: 2.2574
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 64ms/step - accuracy: 0.2210 - loss: 2.2576
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 64ms/step - accuracy: 0.2209 - loss: 2.2578
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 64ms/step - accuracy: 0.2209 - loss: 2.2580
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 64ms/step - accuracy: 0.2208 - loss: 2.2582
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 64ms/step - accuracy: 0.2208 - loss: 2.2584
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 64ms/step - accuracy: 0.2208 - loss: 2.2585
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 64ms/step - accuracy: 0.2207 - loss: 2.2587
[36m(train_cnn_ray_tune pid=2857964)[0m Epoch 4/26[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 52ms/step - accuracy: 0.1406 - loss: 2.7274  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 60ms/step - accuracy: 0.1354 - loss: 2.7577
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 174/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 64ms/step - accuracy: 0.2205 - loss: 2.2596
[1m 175/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 64ms/step - accuracy: 0.2205 - loss: 2.2597
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 122ms/step - accuracy: 0.1250 - loss: 2.7775[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 173/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 64ms/step - accuracy: 0.2205 - loss: 2.2594[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 64ms/step - accuracy: 0.2203 - loss: 2.2603
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 64ms/step - accuracy: 0.2203 - loss: 2.2604
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 64ms/step - accuracy: 0.2202 - loss: 2.2604
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 64ms/step - accuracy: 0.2202 - loss: 2.2605
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 64ms/step - accuracy: 0.2202 - loss: 2.2606
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 64ms/step - accuracy: 0.2201 - loss: 2.2607
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m373/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 40ms/step - accuracy: 0.1595 - loss: 2.6712
[1m375/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 40ms/step - accuracy: 0.1595 - loss: 2.6711[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 64ms/step - accuracy: 0.2201 - loss: 2.2608
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 64ms/step - accuracy: 0.2201 - loss: 2.2609
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m448/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 53ms/step - accuracy: 0.1721 - loss: 2.6418[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 63ms/step - accuracy: 0.2199 - loss: 2.2613
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 63ms/step - accuracy: 0.2199 - loss: 2.2614
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 64ms/step - accuracy: 0.2199 - loss: 2.2615
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 63ms/step - accuracy: 0.2198 - loss: 2.2616
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 63ms/step - accuracy: 0.2197 - loss: 2.2619
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 63ms/step - accuracy: 0.2197 - loss: 2.2620
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m46s[0m 39ms/step - accuracy: 0.1776 - loss: 2.6733 - val_accuracy: 0.2183 - val_loss: 2.3607
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:58[0m 101ms/step - accuracy: 0.3750 - loss: 1.9687
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 52ms/step - accuracy: 0.3438 - loss: 2.0956 
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1362 - loss: 2.9121 
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1362 - loss: 2.9121
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 34ms/step - accuracy: 0.3021 - loss: 2.1770 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 31ms/step - accuracy: 0.2830 - loss: 2.2278
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 63ms/step - accuracy: 0.2193 - loss: 2.2629
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 63ms/step - accuracy: 0.2193 - loss: 2.2630
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 64ms/step - accuracy: 0.2192 - loss: 2.2631
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 64ms/step - accuracy: 0.2192 - loss: 2.2632
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.1100 - loss: 3.1083[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 64ms/step - accuracy: 0.2191 - loss: 2.2633
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 64ms/step - accuracy: 0.2191 - loss: 2.2634
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 64ms/step - accuracy: 0.2191 - loss: 2.2634
[1m 219/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 64ms/step - accuracy: 0.2191 - loss: 2.2635
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1362 - loss: 2.9117
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1362 - loss: 2.9117[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m314/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.1726 - loss: 2.5972 
[1m316/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.1726 - loss: 2.5971
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m 33/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 45ms/step - accuracy: 0.2994 - loss: 1.9962[32m [repeated 120x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m251/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m21s[0m 65ms/step - accuracy: 0.2801 - loss: 2.0416
[1m252/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m21s[0m 65ms/step - accuracy: 0.2801 - loss: 2.0416[32m [repeated 108x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 225/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 64ms/step - accuracy: 0.2189 - loss: 2.2638
[1m 226/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 64ms/step - accuracy: 0.2189 - loss: 2.2638
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 227/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 64ms/step - accuracy: 0.2189 - loss: 2.2638
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 64ms/step - accuracy: 0.2189 - loss: 2.2639
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 64ms/step - accuracy: 0.2188 - loss: 2.2639
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 64ms/step - accuracy: 0.2188 - loss: 2.2640
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m18s[0m 46ms/step - accuracy: 0.1325 - loss: 2.8654
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m18s[0m 46ms/step - accuracy: 0.1325 - loss: 2.8654[32m [repeated 118x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m27s[0m 50ms/step - accuracy: 0.1110 - loss: 3.0951[32m [repeated 126x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 64ms/step - accuracy: 0.2188 - loss: 2.2640
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m59s[0m 64ms/step - accuracy: 0.2188 - loss: 2.2641 
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m 45/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 45ms/step - accuracy: 0.2998 - loss: 1.9832
[1m 46/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 45ms/step - accuracy: 0.2997 - loss: 1.9826
[1m 47/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 45ms/step - accuracy: 0.2997 - loss: 1.9819
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 42ms/step - accuracy: 0.1881 - loss: 2.4451 - val_accuracy: 0.2087 - val_loss: 2.3105[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 38ms/step - accuracy: 0.2014 - loss: 2.7159  
[36m(train_cnn_ray_tune pid=2857944)[0m Epoch 3/16[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 61ms/step - accuracy: 0.3125 - loss: 2.2230  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 57ms/step - accuracy: 0.2986 - loss: 2.2134
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:07[0m 109ms/step - accuracy: 0.1875 - loss: 2.5462[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 224/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 64ms/step - accuracy: 0.2189 - loss: 2.2637[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m420/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 36ms/step - accuracy: 0.1723 - loss: 2.5945
[1m422/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 36ms/step - accuracy: 0.1723 - loss: 2.5945
[1m424/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 36ms/step - accuracy: 0.1723 - loss: 2.5944
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m542/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 53ms/step - accuracy: 0.1722 - loss: 2.6414
[1m543/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 53ms/step - accuracy: 0.1722 - loss: 2.6414[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m582/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 53ms/step - accuracy: 0.2179 - loss: 2.3163[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m49s[0m 42ms/step - accuracy: 0.1002 - loss: 3.0961 - val_accuracy: 0.1656 - val_loss: 2.6844
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m19s[0m 32ms/step - accuracy: 0.1246 - loss: 2.8003
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m19s[0m 32ms/step - accuracy: 0.1246 - loss: 2.8003
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m19s[0m 32ms/step - accuracy: 0.1246 - loss: 2.8002
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 42ms/step - accuracy: 0.1363 - loss: 2.9090[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 42ms/step - accuracy: 0.1363 - loss: 2.9090
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 42ms/step - accuracy: 0.1363 - loss: 2.9090[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m146/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m19s[0m 45ms/step - accuracy: 0.2938 - loss: 1.9747[32m [repeated 179x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m289/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m19s[0m 66ms/step - accuracy: 0.1607 - loss: 2.7660
[1m290/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m19s[0m 66ms/step - accuracy: 0.1608 - loss: 2.7659[32m [repeated 118x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m54s[0m 64ms/step - accuracy: 0.2173 - loss: 2.2671
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m54s[0m 64ms/step - accuracy: 0.2173 - loss: 2.2671[32m [repeated 153x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m23s[0m 50ms/step - accuracy: 0.1116 - loss: 3.0914[32m [repeated 190x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m328/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 63ms/step - accuracy: 0.2814 - loss: 2.0372
[1m329/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 63ms/step - accuracy: 0.2814 - loss: 2.0372
[1m330/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 63ms/step - accuracy: 0.2814 - loss: 2.0371
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m36s[0m 61ms/step - accuracy: 0.1272 - loss: 2.9614 - val_accuracy: 0.1536 - val_loss: 2.5278
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m51s[0m 43ms/step - accuracy: 0.1100 - loss: 3.1078 - val_accuracy: 0.1489 - val_loss: 2.6774
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.1582 - loss: 2.6265 
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.1582 - loss: 2.6265
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 32ms/step - accuracy: 0.0660 - loss: 3.2548  
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 60ms/step - accuracy: 0.2179 - loss: 2.3161 - val_accuracy: 0.2059 - val_loss: 2.2762
[36m(train_cnn_ray_tune pid=2857958)[0m Epoch 4/15[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 122ms/step - accuracy: 0.0625 - loss: 2.3392[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 67ms/step - accuracy: 0.0703 - loss: 2.3366  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 58ms/step - accuracy: 0.0885 - loss: 2.3337
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m579/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 35ms/step - accuracy: 0.1731 - loss: 2.5882
[1m581/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 35ms/step - accuracy: 0.1731 - loss: 2.5881[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m319/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.1318 - loss: 2.8249 
[1m321/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.1318 - loss: 2.8248
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 35ms/step - accuracy: 0.1731 - loss: 2.5880[32m [repeated 46x across cluster][0m
Trial status: 20 RUNNING
Current time: 2025-11-07 13:54:33. 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_a058a    RUNNING            3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21 │
│ trial_a058a    RUNNING            3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15 │
│ trial_a058a    RUNNING            2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26 │
│ trial_a058a    RUNNING            2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28 │
│ trial_a058a    RUNNING            2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22 │
│ trial_a058a    RUNNING            2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21 │
│ trial_a058a    RUNNING            3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24 │
│ trial_a058a    RUNNING            2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28 │
│ trial_a058a    RUNNING            2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25 │
│ trial_a058a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23 │
│ trial_a058a    RUNNING            3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23 │
│ trial_a058a    RUNNING            2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27 │
│ trial_a058a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000164705         24 │
│ trial_a058a    RUNNING            2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24 │
│ trial_a058a    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21 │
│ trial_a058a    RUNNING            3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 30ms/step - accuracy: 0.1587 - loss: 2.6241[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 46ms/step - accuracy: 0.1334 - loss: 2.8587
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 46ms/step - accuracy: 0.1334 - loss: 2.8587[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m 11/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 42ms/step - accuracy: 0.1765 - loss: 2.6676[32m [repeated 170x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m 64/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 51ms/step - accuracy: 0.1994 - loss: 2.2475
[1m 65/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 51ms/step - accuracy: 0.1995 - loss: 2.2476[32m [repeated 164x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 39ms/step - accuracy: 0.1251 - loss: 3.0161
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 39ms/step - accuracy: 0.1250 - loss: 3.0162[32m [repeated 141x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m17s[0m 50ms/step - accuracy: 0.1121 - loss: 3.0880[32m [repeated 194x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m23s[0m 40ms/step - accuracy: 0.1731 - loss: 2.5879 - val_accuracy: 0.2070 - val_loss: 2.3606[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m Epoch 6/24[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 91ms/step - accuracy: 0.1875 - loss: 2.6675[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 52ms/step - accuracy: 0.1328 - loss: 2.5862  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 52ms/step - accuracy: 0.1302 - loss: 2.5965[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m457/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 63ms/step - accuracy: 0.2824 - loss: 2.0312
[1m458/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 63ms/step - accuracy: 0.2824 - loss: 2.0311[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m468/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 36ms/step - accuracy: 0.1325 - loss: 2.8196[32m [repeated 42x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1257 - loss: 2.7925 
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1257 - loss: 2.7925
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 30ms/step - accuracy: 0.1595 - loss: 2.6195[32m [repeated 60x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m45s[0m 64ms/step - accuracy: 0.2183 - loss: 2.2648
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m45s[0m 64ms/step - accuracy: 0.2183 - loss: 2.2647
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m45s[0m 64ms/step - accuracy: 0.2183 - loss: 2.2647
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 47ms/step - accuracy: 0.1338 - loss: 2.8552
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 47ms/step - accuracy: 0.1339 - loss: 2.8551[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m190/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 54ms/step - accuracy: 0.1398 - loss: 2.8355[32m [repeated 229x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m152/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 55ms/step - accuracy: 0.2140 - loss: 2.2354
[1m153/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 55ms/step - accuracy: 0.2141 - loss: 2.2353[32m [repeated 146x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 221/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m39s[0m 42ms/step - accuracy: 0.1259 - loss: 3.0013
[1m 223/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m39s[0m 42ms/step - accuracy: 0.1259 - loss: 3.0011[32m [repeated 98x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m32s[0m 40ms/step - accuracy: 0.1301 - loss: 2.9274[32m [repeated 205x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m56s[0m 48ms/step - accuracy: 0.1362 - loss: 2.9067 - val_accuracy: 0.1787 - val_loss: 2.4965
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.2188 - loss: 2.4085 
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 50ms/step - accuracy: 0.1953 - loss: 2.5395 
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 50ms/step - accuracy: 0.1874 - loss: 2.6256 
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 47ms/step - accuracy: 0.1842 - loss: 2.6493
[36m(train_cnn_ray_tune pid=2857961)[0m Epoch 3/22
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:55[0m 151ms/step - accuracy: 0.2500 - loss: 2.2738
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m484/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 65ms/step - accuracy: 0.1625 - loss: 2.7480
[1m486/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 65ms/step - accuracy: 0.1625 - loss: 2.7479[32m [repeated 111x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m543/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 63ms/step - accuracy: 0.2829 - loss: 2.0272[32m [repeated 149x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m148/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 56ms/step - accuracy: 0.1659 - loss: 2.6113
[1m149/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 56ms/step - accuracy: 0.1659 - loss: 2.6113
[1m150/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 56ms/step - accuracy: 0.1659 - loss: 2.6113
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.1129 - loss: 3.0832 
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.1129 - loss: 3.0832
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 32ms/step - accuracy: 0.1260 - loss: 2.7894[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 32ms/step - accuracy: 0.1261 - loss: 2.7893
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 32ms/step - accuracy: 0.1261 - loss: 2.7892[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m181/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 56ms/step - accuracy: 0.1668 - loss: 2.6111[32m [repeated 142x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m246/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 55ms/step - accuracy: 0.2209 - loss: 2.2251
[1m248/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 55ms/step - accuracy: 0.2210 - loss: 2.2249[32m [repeated 100x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m33s[0m 41ms/step - accuracy: 0.1264 - loss: 2.9926
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m33s[0m 41ms/step - accuracy: 0.1264 - loss: 2.9925[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m27s[0m 41ms/step - accuracy: 0.1294 - loss: 2.9246[32m [repeated 163x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 43ms/step - accuracy: 0.1332 - loss: 2.8167 - val_accuracy: 0.1782 - val_loss: 2.5232
[36m(train_cnn_ray_tune pid=2857956)[0m Epoch 6/27
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 98ms/step - accuracy: 0.0938 - loss: 2.7042
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m193/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 56ms/step - accuracy: 0.1671 - loss: 2.6106
[1m194/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 56ms/step - accuracy: 0.1671 - loss: 2.6105
[1m195/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 56ms/step - accuracy: 0.1672 - loss: 2.6105
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m40s[0m 35ms/step - accuracy: 0.1599 - loss: 2.6175 - val_accuracy: 0.2015 - val_loss: 2.3365
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 37ms/step - accuracy: 0.1319 - loss: 2.5210 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 34ms/step - accuracy: 0.1429 - loss: 2.5153
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m567/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 65ms/step - accuracy: 0.1628 - loss: 2.7433
[1m568/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 65ms/step - accuracy: 0.1628 - loss: 2.7432[32m [repeated 107x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m349/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 35ms/step - accuracy: 0.1876 - loss: 2.5102[32m [repeated 122x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 50ms/step - accuracy: 0.1134 - loss: 3.0803[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 50ms/step - accuracy: 0.1134 - loss: 3.0803
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 50ms/step - accuracy: 0.1134 - loss: 3.0802[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 101ms/step - accuracy: 0.3438 - loss: 2.0392
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 53ms/step - accuracy: 0.3203 - loss: 1.9895 
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m289/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 52ms/step - accuracy: 0.1704 - loss: 2.6015
[1m290/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 52ms/step - accuracy: 0.1705 - loss: 2.6013
[1m291/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 52ms/step - accuracy: 0.1705 - loss: 2.6012
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m355/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 52ms/step - accuracy: 0.2251 - loss: 2.2178[32m [repeated 150x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m134/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m14s[0m 33ms/step - accuracy: 0.1289 - loss: 2.7955
[1m136/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m14s[0m 33ms/step - accuracy: 0.1290 - loss: 2.7953[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m40s[0m 43ms/step - accuracy: 0.1448 - loss: 2.8085
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m40s[0m 43ms/step - accuracy: 0.1448 - loss: 2.8086[32m [repeated 121x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m16s[0m 37ms/step - accuracy: 0.1982 - loss: 2.5023[32m [repeated 169x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m41s[0m 71ms/step - accuracy: 0.2830 - loss: 2.0255 - val_accuracy: 0.2498 - val_loss: 2.1038[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m Epoch 4/23[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 111ms/step - accuracy: 0.2500 - loss: 2.5778[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m30s[0m 61ms/step - accuracy: 0.2217 - loss: 2.2570
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m30s[0m 61ms/step - accuracy: 0.2218 - loss: 2.2569
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m30s[0m 61ms/step - accuracy: 0.2218 - loss: 2.2569
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 41ms/step - accuracy: 0.1632 - loss: 2.5333  
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m61s[0m 52ms/step - accuracy: 0.1344 - loss: 2.8515 - val_accuracy: 0.1693 - val_loss: 2.4454
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m403/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 52ms/step - accuracy: 0.2262 - loss: 2.2151
[1m404/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 52ms/step - accuracy: 0.2263 - loss: 2.2151[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m506/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 34ms/step - accuracy: 0.1876 - loss: 2.5085[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m42s[0m 36ms/step - accuracy: 0.1264 - loss: 2.7864 - val_accuracy: 0.1661 - val_loss: 2.4630
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 28ms/step - accuracy: 0.1389 - loss: 2.7492  
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 37ms/step - accuracy: 0.1432 - loss: 2.7653
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 50ms/step - accuracy: 0.1137 - loss: 3.0782[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 50ms/step - accuracy: 0.1137 - loss: 3.0782
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 50ms/step - accuracy: 0.1137 - loss: 3.0782[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:51[0m 192ms/step - accuracy: 0.1875 - loss: 2.8091
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 63ms/step - accuracy: 0.2031 - loss: 2.7503  [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m141/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 37ms/step - accuracy: 0.2101 - loss: 2.3539[32m [repeated 162x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m382/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 53ms/step - accuracy: 0.1730 - loss: 2.5929
[1m383/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 53ms/step - accuracy: 0.1730 - loss: 2.5928[32m [repeated 138x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m20s[0m 38ms/step - accuracy: 0.1262 - loss: 2.9924
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m20s[0m 38ms/step - accuracy: 0.1262 - loss: 2.9925[32m [repeated 153x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  98/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 46ms/step - accuracy: 0.1652 - loss: 2.7017[32m [repeated 195x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m42s[0m 73ms/step - accuracy: 0.1629 - loss: 2.7422 - val_accuracy: 0.1880 - val_loss: 2.4273[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m Epoch 4/23[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:32[0m 130ms/step - accuracy: 0.1250 - loss: 2.7216[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m397/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 53ms/step - accuracy: 0.1733 - loss: 2.5919 
[1m398/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 53ms/step - accuracy: 0.1733 - loss: 2.5919
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m494/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 53ms/step - accuracy: 0.2282 - loss: 2.2101
[1m496/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 53ms/step - accuracy: 0.2282 - loss: 2.2100[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m498/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 53ms/step - accuracy: 0.2283 - loss: 2.2099[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m22s[0m 29ms/step - accuracy: 0.1883 - loss: 2.5303
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m22s[0m 29ms/step - accuracy: 0.1883 - loss: 2.5301
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 29ms/step - accuracy: 0.1883 - loss: 2.5300
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 37ms/step - accuracy: 0.1987 - loss: 2.4984[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 37ms/step - accuracy: 0.1987 - loss: 2.4983
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 37ms/step - accuracy: 0.1987 - loss: 2.4983[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m169/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m25s[0m 61ms/step - accuracy: 0.2959 - loss: 1.9332[32m [repeated 155x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m106/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m30s[0m 64ms/step - accuracy: 0.1767 - loss: 2.6981
[1m107/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m30s[0m 64ms/step - accuracy: 0.1767 - loss: 2.6978[32m [repeated 117x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m15s[0m 39ms/step - accuracy: 0.1259 - loss: 2.9940
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m15s[0m 39ms/step - accuracy: 0.1259 - loss: 2.9941[32m [repeated 140x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m20s[0m 30ms/step - accuracy: 0.1888 - loss: 2.5265[32m [repeated 232x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m23s[0m 39ms/step - accuracy: 0.1879 - loss: 2.5078 - val_accuracy: 0.2141 - val_loss: 2.3218
[36m(train_cnn_ray_tune pid=2857957)[0m Epoch 7/24
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m52s[0m 89ms/step - accuracy: 0.1562 - loss: 2.3659
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m66s[0m 57ms/step - accuracy: 0.1137 - loss: 3.0781 - val_accuracy: 0.1539 - val_loss: 2.6432
[36m(train_cnn_ray_tune pid=2857950)[0m Epoch 3/15
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3:34[0m 184ms/step - accuracy: 0.2500 - loss: 2.7656
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:30[0m 77ms/step - accuracy: 0.2344 - loss: 2.7564 
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:17[0m 66ms/step - accuracy: 0.2188 - loss: 2.7347
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.2062 - loss: 2.7459
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.2049 - loss: 2.7556
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.2037 - loss: 2.7610
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.2007 - loss: 2.7707
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.1977 - loss: 2.7816
[1m  10/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.1941 - loss: 2.7933
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.1915 - loss: 2.8025
[1m  12/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.1885 - loss: 2.8127
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.1855 - loss: 2.8216
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  15/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.1789 - loss: 2.8435
[1m  16/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.1758 - loss: 2.8548
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  17/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 57ms/step - accuracy: 0.1732 - loss: 2.8640
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  19/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.1706 - loss: 2.8774
[1m  20/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.1694 - loss: 2.8824
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.1671 - loss: 2.8933
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.1650 - loss: 2.9040
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.1644 - loss: 2.9081
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m582/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 53ms/step - accuracy: 0.2296 - loss: 2.2056
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 53ms/step - accuracy: 0.2297 - loss: 2.2055[32m [repeated 78x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.1638 - loss: 2.9122
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.1625 - loss: 2.9186
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  30/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.1618 - loss: 2.9227
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m517/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 54ms/step - accuracy: 0.1757 - loss: 2.5842[32m [repeated 108x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 48ms/step - accuracy: 0.1688 - loss: 2.6249 - val_accuracy: 0.1804 - val_loss: 2.3772
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  32/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.1614 - loss: 2.9260 
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.1613 - loss: 2.9293
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 53ms/step - accuracy: 0.1613 - loss: 2.9300 
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 44ms/step - accuracy: 0.1719 - loss: 2.5148  
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 40ms/step - accuracy: 0.1594 - loss: 2.5535
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m276/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m13s[0m 43ms/step - accuracy: 0.3026 - loss: 1.8893
[1m277/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m13s[0m 43ms/step - accuracy: 0.3026 - loss: 1.8893
[1m278/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m13s[0m 43ms/step - accuracy: 0.3026 - loss: 1.8893
Trial status: 20 RUNNING
Current time: 2025-11-07 13:55:03. 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_a058a    RUNNING            3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21 │
│ trial_a058a    RUNNING            3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15 │
│ trial_a058a    RUNNING            2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26 │
│ trial_a058a    RUNNING            2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28 │
│ trial_a058a    RUNNING            2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22 │
│ trial_a058a    RUNNING            2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21 │
│ trial_a058a    RUNNING            3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24 │
│ trial_a058a    RUNNING            2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28 │
│ trial_a058a    RUNNING            2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25 │
│ trial_a058a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23 │
│ trial_a058a    RUNNING            3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23 │
│ trial_a058a    RUNNING            2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27 │
│ trial_a058a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000164705         24 │
│ trial_a058a    RUNNING            2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24 │
│ trial_a058a    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21 │
│ trial_a058a    RUNNING            3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 37ms/step - accuracy: 0.1990 - loss: 2.4958[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 37ms/step - accuracy: 0.1990 - loss: 2.4956
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 37ms/step - accuracy: 0.1990 - loss: 2.4955[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m205/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 34ms/step - accuracy: 0.1953 - loss: 2.4504[32m [repeated 143x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m316/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m11s[0m 43ms/step - accuracy: 0.3027 - loss: 1.8889
[1m317/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m11s[0m 43ms/step - accuracy: 0.3027 - loss: 1.8889[32m [repeated 134x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m39s[0m 47ms/step - accuracy: 0.1543 - loss: 2.7284
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m39s[0m 47ms/step - accuracy: 0.1543 - loss: 2.7284[32m [repeated 138x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m11s[0m 39ms/step - accuracy: 0.1256 - loss: 2.9952[32m [repeated 208x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m Epoch 5/24[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:32[0m 158ms/step - accuracy: 0.1875 - loss: 2.4894[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:18[0m 135ms/step - accuracy: 0.2812 - loss: 2.2952
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 55ms/step - accuracy: 0.2734 - loss: 2.3062  
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m459/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 39ms/step - accuracy: 0.2123 - loss: 2.3317
[1m461/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 39ms/step - accuracy: 0.2123 - loss: 2.3317[32m [repeated 60x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m371/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 43ms/step - accuracy: 0.3027 - loss: 1.8883[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 59ms/step - accuracy: 0.2297 - loss: 2.2055 - val_accuracy: 0.2250 - val_loss: 2.2293[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m292/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.1964 - loss: 2.4511 
[1m294/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.1964 - loss: 2.4511
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m37s[0m 47ms/step - accuracy: 0.1538 - loss: 2.7289
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m37s[0m 47ms/step - accuracy: 0.1538 - loss: 2.7289
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m37s[0m 47ms/step - accuracy: 0.1538 - loss: 2.7289
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m262/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m20s[0m 63ms/step - accuracy: 0.2948 - loss: 1.9388
[1m263/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 63ms/step - accuracy: 0.2948 - loss: 1.9389
[1m264/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 63ms/step - accuracy: 0.2948 - loss: 1.9389
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 40ms/step - accuracy: 0.1253 - loss: 2.9963[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 40ms/step - accuracy: 0.1295 - loss: 2.9130
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 40ms/step - accuracy: 0.1295 - loss: 2.9129[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m 75/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 53ms/step - accuracy: 0.2606 - loss: 2.1269
[1m 76/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 53ms/step - accuracy: 0.2605 - loss: 2.1269
[1m 77/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 53ms/step - accuracy: 0.2603 - loss: 2.1270
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 65ms/step - accuracy: 0.1476 - loss: 2.5821[32m [repeated 186x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m257/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m21s[0m 65ms/step - accuracy: 0.1757 - loss: 2.6765
[1m258/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m21s[0m 65ms/step - accuracy: 0.1757 - loss: 2.6765[32m [repeated 138x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 30ms/step - accuracy: 0.1902 - loss: 2.5104
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 30ms/step - accuracy: 0.1902 - loss: 2.5103[32m [repeated 134x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 30ms/step - accuracy: 0.1902 - loss: 2.5102[32m [repeated 175x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━
[36m(train_cnn_ray_tune pid=2857951)[0m Epoch 5/21[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m [0m [1m6s[0m 40ms/step - accuracy: 0.1253 - loss: 2.9965[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m48s[0m 41ms/step - accuracy: 0.1992 - loss: 2.4944 - val_accuracy: 0.2209 - val_loss: 2.2864
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.1902 - loss: 2.5088 
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.1902 - loss: 2.5088
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 52ms/step - accuracy: 0.1875 - loss: 2.3417 
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 48ms/step - accuracy: 0.1979 - loss: 2.3525 
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m425/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 49ms/step - accuracy: 0.1534 - loss: 2.7000
[1m427/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 49ms/step - accuracy: 0.1535 - loss: 2.7000[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m434/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 34ms/step - accuracy: 0.1969 - loss: 2.4515[32m [repeated 92x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 60ms/step - accuracy: 0.1771 - loss: 2.5797 - val_accuracy: 0.2194 - val_loss: 2.2862[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m33s[0m 47ms/step - accuracy: 0.1526 - loss: 2.7312
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m33s[0m 47ms/step - accuracy: 0.1526 - loss: 2.7312
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m33s[0m 47ms/step - accuracy: 0.1526 - loss: 2.7313[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 40ms/step - accuracy: 0.1251 - loss: 2.9970[32m [repeated 74x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 62ms/step - accuracy: 0.2264 - loss: 2.2436
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 62ms/step - accuracy: 0.2264 - loss: 2.2436[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m297/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m18s[0m 65ms/step - accuracy: 0.1756 - loss: 2.6735
[1m298/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m18s[0m 65ms/step - accuracy: 0.1756 - loss: 2.6734
[1m299/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m18s[0m 65ms/step - accuracy: 0.1756 - loss: 2.6733
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m334/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 65ms/step - accuracy: 0.1757 - loss: 2.6706[32m [repeated 179x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m162/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 56ms/step - accuracy: 0.2578 - loss: 2.1253
[1m163/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 56ms/step - accuracy: 0.2578 - loss: 2.1252[32m [repeated 152x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.1302 - loss: 2.7346
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.1302 - loss: 2.7345[32m [repeated 107x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m16s[0m 44ms/step - accuracy: 0.1458 - loss: 2.8000[32m [repeated 146x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m Epoch 7/28[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 99ms/step - accuracy: 0.1562 - loss: 2.2804[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 30ms/step - accuracy: 0.1903 - loss: 2.5039
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 30ms/step - accuracy: 0.1903 - loss: 2.5039
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 30ms/step - accuracy: 0.1903 - loss: 2.5039
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m428/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 64ms/step - accuracy: 0.2948 - loss: 1.9398 
[1m429/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 64ms/step - accuracy: 0.2948 - loss: 1.9398
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m434/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 64ms/step - accuracy: 0.2948 - loss: 1.9398
[1m435/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 64ms/step - accuracy: 0.2948 - loss: 1.9397[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m531/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 49ms/step - accuracy: 0.1539 - loss: 2.6970[32m [repeated 70x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 43ms/step - accuracy: 0.2126 - loss: 2.3280 - val_accuracy: 0.1932 - val_loss: 2.2719
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m52s[0m 45ms/step - accuracy: 0.1296 - loss: 2.9117 - val_accuracy: 0.1813 - val_loss: 2.5662
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m29s[0m 47ms/step - accuracy: 0.1517 - loss: 2.7328
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m29s[0m 47ms/step - accuracy: 0.1517 - loss: 2.7328
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m29s[0m 47ms/step - accuracy: 0.1516 - loss: 2.7328
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 33ms/step - accuracy: 0.1736 - loss: 2.5704 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.1774 - loss: 2.6249
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m222/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m20s[0m 56ms/step - accuracy: 0.2582 - loss: 2.1226
[1m223/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m20s[0m 56ms/step - accuracy: 0.2582 - loss: 2.1226
[1m224/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m20s[0m 56ms/step - accuracy: 0.2583 - loss: 2.1225
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m3s[0m 62ms/step - accuracy: 0.2272 - loss: 2.2411[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m468/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 64ms/step - accuracy: 0.2949 - loss: 1.9391
[1m469/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 64ms/step - accuracy: 0.2949 - loss: 1.9391
[1m470/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 64ms/step - accuracy: 0.2949 - loss: 1.9391
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 30ms/step - accuracy: 0.1903 - loss: 2.5014
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 30ms/step - accuracy: 0.1903 - loss: 2.5013[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m29s[0m 49ms/step - accuracy: 0.3024 - loss: 1.8864 - val_accuracy: 0.2605 - val_loss: 2.0192
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:22[0m 142ms/step - accuracy: 0.2188 - loss: 2.0052
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 51ms/step - accuracy: 0.2422 - loss: 2.0034  
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m136/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 37ms/step - accuracy: 0.2135 - loss: 2.3015[32m [repeated 180x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m413/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m11s[0m 65ms/step - accuracy: 0.1760 - loss: 2.6658
[1m414/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m11s[0m 65ms/step - accuracy: 0.1760 - loss: 2.6658[32m [repeated 161x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m38s[0m 50ms/step - accuracy: 0.1407 - loss: 2.9581
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m38s[0m 50ms/step - accuracy: 0.1407 - loss: 2.9581[32m [repeated 93x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 226/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m35s[0m 38ms/step - accuracy: 0.2015 - loss: 2.4273[32m [repeated 184x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m Epoch 6/25[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:45[0m 90ms/step - accuracy: 0.2500 - loss: 2.3251
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:39[0m 170ms/step - accuracy: 0.1562 - loss: 2.4768
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 56ms/step - accuracy: 0.1562 - loss: 2.5289  
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 42ms/step - accuracy: 0.1667 - loss: 2.4802
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 62ms/step - accuracy: 0.2275 - loss: 2.2399
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 62ms/step - accuracy: 0.2276 - loss: 2.2399
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 62ms/step - accuracy: 0.2276 - loss: 2.2399
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m306/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1474 - loss: 2.7305 
[1m307/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1474 - loss: 2.7305
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m447/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 66ms/step - accuracy: 0.1762 - loss: 2.6642
[1m448/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 66ms/step - accuracy: 0.1762 - loss: 2.6642[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m516/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 64ms/step - accuracy: 0.2951 - loss: 1.9381[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m52s[0m 45ms/step - accuracy: 0.1250 - loss: 2.9971 - val_accuracy: 0.1528 - val_loss: 2.6468
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.2083 - loss: 2.8706  
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 44ms/step - accuracy: 0.1454 - loss: 2.7986[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.1316 - loss: 2.7265
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.1316 - loss: 2.7264[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m21s[0m 47ms/step - accuracy: 0.1503 - loss: 2.7353
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m21s[0m 48ms/step - accuracy: 0.1503 - loss: 2.7353
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m21s[0m 48ms/step - accuracy: 0.1503 - loss: 2.7353
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 56ms/step - accuracy: 0.1540 - loss: 2.6958 - val_accuracy: 0.1846 - val_loss: 2.4170[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 130ms/step - accuracy: 0.1250 - loss: 2.6583
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 66ms/step - accuracy: 0.1406 - loss: 2.6566  
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m126/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m14s[0m 32ms/step - accuracy: 0.2091 - loss: 2.4168[32m [repeated 156x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m278/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m16s[0m 55ms/step - accuracy: 0.1968 - loss: 2.4923
[1m279/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m16s[0m 55ms/step - accuracy: 0.1968 - loss: 2.4922[32m [repeated 143x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m20s[0m 47ms/step - accuracy: 0.1502 - loss: 2.7354
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m20s[0m 47ms/step - accuracy: 0.1502 - loss: 2.7354[32m [repeated 100x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m  63/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 38ms/step - accuracy: 0.1463 - loss: 2.9366[32m [repeated 137x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m Epoch 6/26[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:03[0m 106ms/step - accuracy: 0.1875 - loss: 2.8743
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m310/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.2173 - loss: 2.2939 
[1m311/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.2174 - loss: 2.2938
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m306/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 55ms/step - accuracy: 0.1973 - loss: 2.4911
[1m307/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 55ms/step - accuracy: 0.1973 - loss: 2.4910
[1m308/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 55ms/step - accuracy: 0.1974 - loss: 2.4910
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:35[0m 82ms/step - accuracy: 0.4375 - loss: 2.4633
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 39ms/step - accuracy: 0.3507 - loss: 2.3484 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 32ms/step - accuracy: 0.2908 - loss: 2.3638
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m517/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 35ms/step - accuracy: 0.1468 - loss: 2.7290
[1m519/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 35ms/step - accuracy: 0.1468 - loss: 2.7290[32m [repeated 105x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m417/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 54ms/step - accuracy: 0.1396 - loss: 2.8223[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m40s[0m 34ms/step - accuracy: 0.1904 - loss: 2.4994 - val_accuracy: 0.2135 - val_loss: 2.2780
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 44ms/step - accuracy: 0.1450 - loss: 2.7978[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 32ms/step - accuracy: 0.1321 - loss: 2.7232
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 32ms/step - accuracy: 0.1321 - loss: 2.7231[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m136/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m20s[0m 45ms/step - accuracy: 0.1555 - loss: 2.6601[32m [repeated 100x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m376/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 54ms/step - accuracy: 0.1986 - loss: 2.4886
[1m378/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 54ms/step - accuracy: 0.1987 - loss: 2.4885[32m [repeated 118x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 48ms/step - accuracy: 0.1727 - loss: 2.5749 - val_accuracy: 0.1846 - val_loss: 2.3614
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m34s[0m 36ms/step - accuracy: 0.1370 - loss: 2.9557
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m34s[0m 36ms/step - accuracy: 0.1369 - loss: 2.9558[32m [repeated 130x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 142/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 26ms/step - accuracy: 0.1901 - loss: 2.4647[32m [repeated 148x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 103ms/step - accuracy: 0.1250 - loss: 2.8890
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 52ms/step - accuracy: 0.1484 - loss: 2.7980  
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m80s[0m 69ms/step - accuracy: 0.2277 - loss: 2.2394 - val_accuracy: 0.2498 - val_loss: 2.1242
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 59ms/step - accuracy: 0.1979 - loss: 2.0343
[36m(train_cnn_ray_tune pid=2857963)[0m Epoch 3/24[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 58ms/step - accuracy: 0.2108 - loss: 2.0306
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.2248 - loss: 2.0308
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 53ms/step - accuracy: 0.2279 - loss: 2.0349
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  10/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.2317 - loss: 2.0534
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 55ms/step - accuracy: 0.2324 - loss: 2.0609
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m398/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 53ms/step - accuracy: 0.1991 - loss: 2.4876 
[1m400/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 53ms/step - accuracy: 0.1992 - loss: 2.4875[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  12/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 55ms/step - accuracy: 0.2317 - loss: 2.0684
[1m  14/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 53ms/step - accuracy: 0.2306 - loss: 2.0811
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  16/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.2315 - loss: 2.0859
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  18/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.2316 - loss: 2.0904
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 54ms/step - accuracy: 0.2914 - loss: 2.0661
[1m  6/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 54ms/step - accuracy: 0.2931 - loss: 2.0300
[1m  7/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 54ms/step - accuracy: 0.2959 - loss: 2.0055
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  20/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.2309 - loss: 2.0961
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.2304 - loss: 2.0996
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.2302 - loss: 2.1031
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.2303 - loss: 2.1061
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.2302 - loss: 2.1089
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.2303 - loss: 2.1107
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 108ms/step - accuracy: 0.1250 - loss: 2.7497
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.2304 - loss: 2.1125
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.2304 - loss: 2.1152
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.2304 - loss: 2.1193
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  31/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.2304 - loss: 2.1228
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  32/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.2304 - loss: 2.1242
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.2305 - loss: 2.1258
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.2304 - loss: 2.1274
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m426/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 53ms/step - accuracy: 0.1998 - loss: 2.4863
[1m427/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 53ms/step - accuracy: 0.1998 - loss: 2.4862[32m [repeated 113x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.2300 - loss: 2.1305
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m371/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.2100 - loss: 2.4093[32m [repeated 120x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.2297 - loss: 2.1322
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.2295 - loss: 2.1339
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.2292 - loss: 2.1355
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.2290 - loss: 2.1368
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.2285 - loss: 2.1396
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.2281 - loss: 2.1411
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  44/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.2279 - loss: 2.1425
[1m  45/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.2276 - loss: 2.1440
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.2274 - loss: 2.1454
Trial status: 20 RUNNING
Current time: 2025-11-07 13:55:33. 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_a058a    RUNNING            3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21 │
│ trial_a058a    RUNNING            3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15 │
│ trial_a058a    RUNNING            2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26 │
│ trial_a058a    RUNNING            2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28 │
│ trial_a058a    RUNNING            2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22 │
│ trial_a058a    RUNNING            2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21 │
│ trial_a058a    RUNNING            3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24 │
│ trial_a058a    RUNNING            2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28 │
│ trial_a058a    RUNNING            2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25 │
│ trial_a058a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23 │
│ trial_a058a    RUNNING            3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23 │
│ trial_a058a    RUNNING            2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27 │
│ trial_a058a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000164705         24 │
│ trial_a058a    RUNNING            2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24 │
│ trial_a058a    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21 │
│ trial_a058a    RUNNING            3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.2269 - loss: 2.1480
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.2264 - loss: 2.1505
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.2263 - loss: 2.1521
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.2262 - loss: 2.1527
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.2263 - loss: 2.1532
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.2263 - loss: 2.1537
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.2263 - loss: 2.1542
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  57/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.2264 - loss: 2.1546
[1m  58/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.2264 - loss: 2.1550
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  59/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.2265 - loss: 2.1554
[1m  60/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.2265 - loss: 2.1558
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  61/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.2266 - loss: 2.1562
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  62/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.2266 - loss: 2.1564
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  63/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.2267 - loss: 2.1567
[1m  64/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.2268 - loss: 2.1569
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  66/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.2269 - loss: 2.1572
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  67/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.2270 - loss: 2.1573
[1m  68/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.2271 - loss: 2.1574
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 43ms/step - accuracy: 0.1449 - loss: 2.7977[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  69/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.2272 - loss: 2.1575
[1m  71/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.2274 - loss: 2.1577
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.2274 - loss: 2.1578
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 43ms/step - accuracy: 0.1449 - loss: 2.7977
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 43ms/step - accuracy: 0.1449 - loss: 2.7977[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.2275 - loss: 2.1578
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.2276 - loss: 2.1578
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.2276 - loss: 2.1578
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 57ms/step - accuracy: 0.2277 - loss: 2.1577
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 57ms/step - accuracy: 0.2277 - loss: 2.1577
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m118/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m17s[0m 38ms/step - accuracy: 0.1706 - loss: 2.5792[32m [repeated 114x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 66/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 58ms/step - accuracy: 0.3100 - loss: 1.8644
[1m 67/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 58ms/step - accuracy: 0.3100 - loss: 1.8645[32m [repeated 87x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 57ms/step - accuracy: 0.2278 - loss: 2.1577
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 57ms/step - accuracy: 0.2278 - loss: 2.1578
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 57ms/step - accuracy: 0.2278 - loss: 2.1580
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 57ms/step - accuracy: 0.2277 - loss: 2.1581
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m23s[0m 39ms/step - accuracy: 0.1468 - loss: 2.7276 - val_accuracy: 0.1791 - val_loss: 2.4706[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  86/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.2278 - loss: 2.1586
[1m  87/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.2278 - loss: 2.1587
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m29s[0m 36ms/step - accuracy: 0.1355 - loss: 2.9550
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m29s[0m 36ms/step - accuracy: 0.1355 - loss: 2.9549[32m [repeated 132x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m22s[0m 49ms/step - accuracy: 0.1386 - loss: 2.9506[32m [repeated 164x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 107ms/step - accuracy: 0.2188 - loss: 2.5167
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 58ms/step - accuracy: 0.2500 - loss: 2.2923  [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m42s[0m 36ms/step - accuracy: 0.1322 - loss: 2.7228 - val_accuracy: 0.1643 - val_loss: 2.4470
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  92/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.2282 - loss: 2.1588[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m Epoch 5/24[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  95/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.2283 - loss: 2.1588
[1m  96/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.2284 - loss: 2.1589
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  97/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.2284 - loss: 2.1590
[1m  98/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.2284 - loss: 2.1592
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.2284 - loss: 2.1593
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.2284 - loss: 2.1594
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.2285 - loss: 2.1595
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.2285 - loss: 2.1597
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.2286 - loss: 2.1598
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.2286 - loss: 2.1599
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.2287 - loss: 2.1605
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.2288 - loss: 2.1606
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m57s[0m 49ms/step - accuracy: 0.1449 - loss: 2.7976 - val_accuracy: 0.1756 - val_loss: 2.4555
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:42[0m 88ms/step - accuracy: 0.1875 - loss: 2.3938
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:15[0m 116ms/step - accuracy: 0.0625 - loss: 2.7903
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.2288 - loss: 2.1611
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.2289 - loss: 2.1613
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 52ms/step - accuracy: 0.0938 - loss: 2.6833 
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m521/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 53ms/step - accuracy: 0.2014 - loss: 2.4821
[1m522/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 53ms/step - accuracy: 0.2014 - loss: 2.4821
[1m523/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 53ms/step - accuracy: 0.2014 - loss: 2.4820
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m425/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 42ms/step - accuracy: 0.3134 - loss: 1.8470
[1m427/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 41ms/step - accuracy: 0.3134 - loss: 1.8470[32m [repeated 110x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.2290 - loss: 2.1625
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.2290 - loss: 2.1627
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m523/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 32ms/step - accuracy: 0.2088 - loss: 2.4090[32m [repeated 116x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.2290 - loss: 2.1629
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.2290 - loss: 2.1630
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.2290 - loss: 2.1632
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.2290 - loss: 2.1634
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.2290 - loss: 2.1636
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.2291 - loss: 2.1637
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.2291 - loss: 2.1639
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.2291 - loss: 2.1640
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.2292 - loss: 2.1645
[1m 138/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.2292 - loss: 2.1646
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 140/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.2293 - loss: 2.1649
[1m 141/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.2293 - loss: 2.1650
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 142/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.2293 - loss: 2.1652
[1m 143/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.2293 - loss: 2.1653
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 146/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.2294 - loss: 2.1657
[1m 147/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.2294 - loss: 2.1659
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 148/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.2295 - loss: 2.1660
[1m 149/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.2295 - loss: 2.1662
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.2295 - loss: 2.1665
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.2295 - loss: 2.1666
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 46ms/step - accuracy: 0.1496 - loss: 2.7338[32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 59ms/step - accuracy: 0.2296 - loss: 2.1667 
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 59ms/step - accuracy: 0.2296 - loss: 2.1668
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 46ms/step - accuracy: 0.1496 - loss: 2.7338
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 46ms/step - accuracy: 0.1496 - loss: 2.7338[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m 27/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 43ms/step - accuracy: 0.2174 - loss: 2.2771[32m [repeated 151x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 70/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 65ms/step - accuracy: 0.1788 - loss: 2.6104
[1m 71/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 65ms/step - accuracy: 0.1788 - loss: 2.6104[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m363/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 45ms/step - accuracy: 0.1556 - loss: 2.6701 
[1m364/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 45ms/step - accuracy: 0.1556 - loss: 2.6701
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 59ms/step - accuracy: 0.1402 - loss: 2.8215 - val_accuracy: 0.1850 - val_loss: 2.4677[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m19s[0m 28ms/step - accuracy: 0.1916 - loss: 2.4429
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m19s[0m 28ms/step - accuracy: 0.1917 - loss: 2.4428[32m [repeated 157x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m25s[0m 36ms/step - accuracy: 0.1349 - loss: 2.9534[32m [repeated 184x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 112ms/step - accuracy: 0.1875 - loss: 2.5478
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 56ms/step - accuracy: 0.1719 - loss: 2.5893  
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 150/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.2295 - loss: 2.1663[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m Epoch 6/24[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 116ms/step - accuracy: 0.2500 - loss: 1.8927[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 59ms/step - accuracy: 0.0938 - loss: 2.6746  
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 47ms/step - accuracy: 0.1315 - loss: 2.5733
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m538/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 42ms/step - accuracy: 0.3137 - loss: 1.8470
[1m539/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 42ms/step - accuracy: 0.3137 - loss: 1.8470[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m414/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 46ms/step - accuracy: 0.1557 - loss: 2.6695[32m [repeated 65x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 82/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 55ms/step - accuracy: 0.1634 - loss: 2.7522
[1m 83/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 55ms/step - accuracy: 0.1633 - loss: 2.7523
[1m 84/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 55ms/step - accuracy: 0.1632 - loss: 2.7525
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 35ms/step - accuracy: 0.2066 - loss: 2.4077[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 46ms/step - accuracy: 0.1496 - loss: 2.7329
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 46ms/step - accuracy: 0.1496 - loss: 2.7329[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m100/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m26s[0m 54ms/step - accuracy: 0.1615 - loss: 2.7552[32m [repeated 176x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m148/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m28s[0m 64ms/step - accuracy: 0.1788 - loss: 2.6064
[1m149/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m28s[0m 65ms/step - accuracy: 0.1788 - loss: 2.6063[32m [repeated 143x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m335/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 40ms/step - accuracy: 0.1746 - loss: 2.5543 
[1m337/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 40ms/step - accuracy: 0.1746 - loss: 2.5541
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 60ms/step - accuracy: 0.2023 - loss: 2.4790 - val_accuracy: 0.2302 - val_loss: 2.2497[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 253/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m54s[0m 59ms/step - accuracy: 0.2326 - loss: 2.1660
[1m 254/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m54s[0m 59ms/step - accuracy: 0.2326 - loss: 2.1660[32m [repeated 150x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m20s[0m 37ms/step - accuracy: 0.1338 - loss: 2.9553[32m [repeated 227x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m Epoch 6/21[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 125ms/step - accuracy: 0.0938 - loss: 2.7561[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 47ms/step - accuracy: 0.1076 - loss: 2.7399  
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 49ms/step - accuracy: 0.1198 - loss: 2.7160
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m421/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 40ms/step - accuracy: 0.1761 - loss: 2.5473
[1m422/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 40ms/step - accuracy: 0.1761 - loss: 2.5472
[1m423/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 40ms/step - accuracy: 0.1761 - loss: 2.5472
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m416/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 37ms/step - accuracy: 0.1499 - loss: 2.6866
[1m418/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 37ms/step - accuracy: 0.1499 - loss: 2.6866[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m520/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 46ms/step - accuracy: 0.1558 - loss: 2.6673[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 120ms/step - accuracy: 0.3438 - loss: 1.8594
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 53ms/step - accuracy: 0.3359 - loss: 1.8230  
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 35ms/step - accuracy: 0.2072 - loss: 2.4048[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 35ms/step - accuracy: 0.2072 - loss: 2.4047
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 35ms/step - accuracy: 0.2073 - loss: 2.4047[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m284/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 40ms/step - accuracy: 0.2332 - loss: 2.2429[32m [repeated 201x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m228/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m22s[0m 64ms/step - accuracy: 0.1784 - loss: 2.6030
[1m229/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m22s[0m 64ms/step - accuracy: 0.1784 - loss: 2.6029[32m [repeated 158x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m29s[0m 49ms/step - accuracy: 0.3139 - loss: 1.8466 - val_accuracy: 0.2809 - val_loss: 1.9927
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m49s[0m 60ms/step - accuracy: 0.2359 - loss: 2.1590
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m49s[0m 60ms/step - accuracy: 0.2360 - loss: 2.1589[32m [repeated 136x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m16s[0m 38ms/step - accuracy: 0.1332 - loss: 2.9555[32m [repeated 189x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m Epoch 7/25
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m61s[0m 52ms/step - accuracy: 0.1496 - loss: 2.7329 - val_accuracy: 0.1717 - val_loss: 2.4184
[36m(train_cnn_ray_tune pid=2857962)[0m Epoch 4/21
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 65ms/step - accuracy: 0.0972 - loss: 2.6458
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 65ms/step - accuracy: 0.1042 - loss: 2.6463
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 65ms/step - accuracy: 0.1133 - loss: 2.6418
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 66ms/step - accuracy: 0.1187 - loss: 2.6439
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:21[0m 71ms/step - accuracy: 0.1235 - loss: 2.6404
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:17[0m 67ms/step - accuracy: 0.1287 - loss: 2.6426
[1m  10/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 66ms/step - accuracy: 0.1321 - loss: 2.6407
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 66ms/step - accuracy: 0.1346 - loss: 2.6368
[1m  12/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 65ms/step - accuracy: 0.1368 - loss: 2.6329
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 64ms/step - accuracy: 0.1377 - loss: 2.6302
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  15/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 61ms/step - accuracy: 0.1381 - loss: 2.6274
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m557/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 37ms/step - accuracy: 0.1503 - loss: 2.6827
[1m559/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 37ms/step - accuracy: 0.1503 - loss: 2.6827[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  16/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 60ms/step - accuracy: 0.1382 - loss: 2.6257
[1m  18/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.1395 - loss: 2.6230
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m347/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 40ms/step - accuracy: 0.2342 - loss: 2.2406[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  19/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.1402 - loss: 2.6223
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.1413 - loss: 2.6211
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.1424 - loss: 2.6199
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.1428 - loss: 2.6198
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.1438 - loss: 2.6184
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.1448 - loss: 2.6178
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  30/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.1459 - loss: 2.6174
[1m  32/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 53ms/step - accuracy: 0.1468 - loss: 2.6188 
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:22[0m 122ms/step - accuracy: 0.1250 - loss: 2.6106
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:19[0m 68ms/step - accuracy: 0.0938 - loss: 2.6311 
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 53ms/step - accuracy: 0.1492 - loss: 2.6237 
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 29ms/step - accuracy: 0.1944 - loss: 2.4294[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m31s[0m 53ms/step - accuracy: 0.1558 - loss: 2.6662 - val_accuracy: 0.2030 - val_loss: 2.3950
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m297/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m18s[0m 65ms/step - accuracy: 0.1784 - loss: 2.6001
[1m298/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m18s[0m 65ms/step - accuracy: 0.1784 - loss: 2.6000
[1m299/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m18s[0m 65ms/step - accuracy: 0.1784 - loss: 2.6000
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 121ms/step - accuracy: 0.1875 - loss: 2.2774
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 29ms/step - accuracy: 0.1944 - loss: 2.4294
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 29ms/step - accuracy: 0.1944 - loss: 2.4293[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m305/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m18s[0m 65ms/step - accuracy: 0.1785 - loss: 2.5996[32m [repeated 186x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m182/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 56ms/step - accuracy: 0.2048 - loss: 2.4366
[1m183/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 56ms/step - accuracy: 0.2048 - loss: 2.4365[32m [repeated 148x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m11s[0m 38ms/step - accuracy: 0.1331 - loss: 2.9549
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m11s[0m 38ms/step - accuracy: 0.1330 - loss: 2.9549[32m [repeated 84x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m32s[0m 44ms/step - accuracy: 0.1462 - loss: 2.7609[32m [repeated 173x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m Epoch 9/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.1330 - loss: 2.9545 
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.1330 - loss: 2.9544
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m476/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 39ms/step - accuracy: 0.2356 - loss: 2.2371
[1m478/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 39ms/step - accuracy: 0.2356 - loss: 2.2370[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m451/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 34ms/step - accuracy: 0.2099 - loss: 2.3836[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m501/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 39ms/step - accuracy: 0.2357 - loss: 2.2366
[1m502/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 39ms/step - accuracy: 0.2358 - loss: 2.2366
[1m503/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 39ms/step - accuracy: 0.2358 - loss: 2.2366
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m506/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 39ms/step - accuracy: 0.2358 - loss: 2.2365
[1m507/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 39ms/step - accuracy: 0.2358 - loss: 2.2365
[1m508/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 39ms/step - accuracy: 0.2358 - loss: 2.2365
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m47s[0m 41ms/step - accuracy: 0.2077 - loss: 2.4026 - val_accuracy: 0.2359 - val_loss: 2.2363
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 46ms/step - accuracy: 0.2222 - loss: 2.5045  
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 42ms/step - accuracy: 0.2446 - loss: 2.4751
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 38ms/step - accuracy: 0.1330 - loss: 2.9539[32m [repeated 106x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 47ms/step - accuracy: 0.1774 - loss: 2.5407 - val_accuracy: 0.1933 - val_loss: 2.3375[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m263/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m17s[0m 54ms/step - accuracy: 0.2690 - loss: 2.0221
[1m264/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m17s[0m 54ms/step - accuracy: 0.2691 - loss: 2.0220
[1m265/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m17s[0m 54ms/step - accuracy: 0.2691 - loss: 2.0220
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:18[0m 119ms/step - accuracy: 0.1875 - loss: 2.4693[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 29ms/step - accuracy: 0.1947 - loss: 2.4262
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 29ms/step - accuracy: 0.1947 - loss: 2.4261[32m [repeated 65x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m268/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m13s[0m 44ms/step - accuracy: 0.3319 - loss: 1.7853[32m [repeated 227x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m274/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m17s[0m 56ms/step - accuracy: 0.2062 - loss: 2.4268
[1m275/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m17s[0m 56ms/step - accuracy: 0.2062 - loss: 2.4267[32m [repeated 157x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 37ms/step - accuracy: 0.2376 - loss: 2.3703
[1m  44/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 36ms/step - accuracy: 0.2370 - loss: 2.3695[32m [repeated 91x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m12s[0m 33ms/step - accuracy: 0.1512 - loss: 2.6593[32m [repeated 141x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m Epoch 5/26[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m403/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 55ms/step - accuracy: 0.1522 - loss: 2.7740 
[1m404/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 55ms/step - accuracy: 0.1522 - loss: 2.7741
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m495/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 63ms/step - accuracy: 0.3138 - loss: 1.8601
[1m496/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 63ms/step - accuracy: 0.3138 - loss: 1.8601[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m499/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 63ms/step - accuracy: 0.3138 - loss: 1.8601[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.1511 - loss: 2.6591 
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.1511 - loss: 2.6591
Trial status: 20 RUNNING
Current time: 2025-11-07 13:56:03. 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_a058a    RUNNING            3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21 │
│ trial_a058a    RUNNING            3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15 │
│ trial_a058a    RUNNING            2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26 │
│ trial_a058a    RUNNING            2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28 │
│ trial_a058a    RUNNING            2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22 │
│ trial_a058a    RUNNING            2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21 │
│ trial_a058a    RUNNING            3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24 │
│ trial_a058a    RUNNING            2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28 │
│ trial_a058a    RUNNING            2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25 │
│ trial_a058a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23 │
│ trial_a058a    RUNNING            3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23 │
│ trial_a058a    RUNNING            2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27 │
│ trial_a058a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000164705         24 │
│ trial_a058a    RUNNING            2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24 │
│ trial_a058a    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21 │
│ trial_a058a    RUNNING            3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m419/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 55ms/step - accuracy: 0.1521 - loss: 2.7741
[1m420/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 55ms/step - accuracy: 0.1521 - loss: 2.7741
[1m421/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 55ms/step - accuracy: 0.1521 - loss: 2.7741[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 99ms/step - accuracy: 0.1250 - loss: 2.5109
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 31ms/step - accuracy: 0.1892 - loss: 2.4174
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 39ms/step - accuracy: 0.1331 - loss: 2.9523[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m22s[0m 38ms/step - accuracy: 0.2101 - loss: 2.3839 - val_accuracy: 0.2104 - val_loss: 2.2390
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 39ms/step - accuracy: 0.1331 - loss: 2.9524
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 39ms/step - accuracy: 0.1331 - loss: 2.9524[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m218/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m17s[0m 48ms/step - accuracy: 0.1572 - loss: 2.6249[32m [repeated 187x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m365/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m12s[0m 55ms/step - accuracy: 0.2075 - loss: 2.4199
[1m366/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m12s[0m 55ms/step - accuracy: 0.2076 - loss: 2.4198[32m [repeated 135x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m26s[0m 45ms/step - accuracy: 0.2363 - loss: 2.2354 - val_accuracy: 0.2235 - val_loss: 2.2267
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 102ms/step - accuracy: 0.1875 - loss: 2.2877
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m39s[0m 33ms/step - accuracy: 0.1948 - loss: 2.4253 - val_accuracy: 0.2296 - val_loss: 2.2104
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m44s[0m 50ms/step - accuracy: 0.1587 - loss: 2.6555
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m44s[0m 50ms/step - accuracy: 0.1587 - loss: 2.6556[32m [repeated 91x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m22s[0m 44ms/step - accuracy: 0.1483 - loss: 2.7549[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.2396 - loss: 2.4666 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 29ms/step - accuracy: 0.2313 - loss: 2.4505
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m277/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.1550 - loss: 2.6499
[1m279/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.1550 - loss: 2.6499
[1m280/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.1550 - loss: 2.6499
[36m(train_cnn_ray_tune pid=2857965)[0m Epoch 6/25[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m306/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1548 - loss: 2.6507 
[1m308/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1548 - loss: 2.6507
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 64ms/step - accuracy: 0.0972 - loss: 3.0843
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 60ms/step - accuracy: 0.1081 - loss: 3.0137
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 58ms/step - accuracy: 0.1115 - loss: 2.9922
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m407/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 56ms/step - accuracy: 0.2082 - loss: 2.4172
[1m408/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 56ms/step - accuracy: 0.2083 - loss: 2.4171[32m [repeated 84x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 54ms/step - accuracy: 0.1168 - loss: 2.9807
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m320/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1547 - loss: 2.6511[32m [repeated 133x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 52ms/step - accuracy: 0.1263 - loss: 2.9943
[1m  12/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.1266 - loss: 2.9938
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.1265 - loss: 2.9952
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  14/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 56ms/step - accuracy: 0.1267 - loss: 2.9938
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  16/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.1275 - loss: 2.9863
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  18/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.1284 - loss: 2.9834
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  20/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.1300 - loss: 2.9814
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.1307 - loss: 2.9814
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.1313 - loss: 2.9811
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m499/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 65ms/step - accuracy: 0.1803 - loss: 2.5913
[1m500/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 65ms/step - accuracy: 0.1804 - loss: 2.5913
[1m501/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 65ms/step - accuracy: 0.1804 - loss: 2.5912[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.1320 - loss: 2.9804
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.1327 - loss: 2.9781
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 36ms/step - accuracy: 0.1285 - loss: 2.8507  
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:20[0m 120ms/step - accuracy: 0.0625 - loss: 3.1843
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:19[0m 68ms/step - accuracy: 0.0938 - loss: 3.1273 
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 33ms/step - accuracy: 0.1506 - loss: 2.6588[32m [repeated 60x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 33ms/step - accuracy: 0.1506 - loss: 2.6588
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 33ms/step - accuracy: 0.1506 - loss: 2.6588[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m130/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m17s[0m 38ms/step - accuracy: 0.2308 - loss: 2.1992[32m [repeated 112x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m164/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m13s[0m 33ms/step - accuracy: 0.2065 - loss: 2.3652
[1m167/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m13s[0m 33ms/step - accuracy: 0.2066 - loss: 2.3649[32m [repeated 109x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:57[0m 100ms/step - accuracy: 0.0625 - loss: 2.9938[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m51s[0m 44ms/step - accuracy: 0.1462 - loss: 2.8040 - val_accuracy: 0.2028 - val_loss: 2.4609[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  67/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 49ms/step - accuracy: 0.1362 - loss: 2.9222
[1m  68/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 50ms/step - accuracy: 0.1363 - loss: 2.9218[32m [repeated 124x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m37s[0m 49ms/step - accuracy: 0.1592 - loss: 2.6604[32m [repeated 147x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.1331 - loss: 2.9760 
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.1332 - loss: 2.9749[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m Epoch 5/16[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m41s[0m 71ms/step - accuracy: 0.3137 - loss: 1.8606 - val_accuracy: 0.2464 - val_loss: 2.1322
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m405/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 56ms/step - accuracy: 0.2082 - loss: 2.4173 
[1m406/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 56ms/step - accuracy: 0.2082 - loss: 2.4173
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m353/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1801 - loss: 2.5197
[1m355/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1801 - loss: 2.5196[32m [repeated 119x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m510/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 55ms/step - accuracy: 0.2092 - loss: 2.4132[32m [repeated 151x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m493/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 55ms/step - accuracy: 0.2091 - loss: 2.4137
[1m494/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 55ms/step - accuracy: 0.2091 - loss: 2.4137
[1m495/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 55ms/step - accuracy: 0.2091 - loss: 2.4137[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m26s[0m 29ms/step - accuracy: 0.2126 - loss: 2.3767
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m26s[0m 29ms/step - accuracy: 0.2127 - loss: 2.3766
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m26s[0m 29ms/step - accuracy: 0.2127 - loss: 2.3766
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.1094 - loss: 2.9996
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.0820 - loss: 2.9878
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.0756 - loss: 3.0049
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 49ms/step - accuracy: 0.0663 - loss: 3.0477 
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 33ms/step - accuracy: 0.1504 - loss: 2.6587[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.1504 - loss: 2.6587
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.1504 - loss: 2.6587[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 51/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 54ms/step - accuracy: 0.3243 - loss: 1.8355[32m [repeated 93x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m269/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 37ms/step - accuracy: 0.2345 - loss: 2.1966
[1m271/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 37ms/step - accuracy: 0.2345 - loss: 2.1966[32m [repeated 70x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:20[0m 137ms/step - accuracy: 0.2500 - loss: 2.4468[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m51s[0m 44ms/step - accuracy: 0.1331 - loss: 2.9513 - val_accuracy: 0.1495 - val_loss: 2.6048
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m11s[0m 43ms/step - accuracy: 0.1495 - loss: 2.7492
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m11s[0m 43ms/step - accuracy: 0.1495 - loss: 2.7491[32m [repeated 161x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 171/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 49ms/step - accuracy: 0.1403 - loss: 2.8945[32m [repeated 191x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 37/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 48ms/step - accuracy: 0.1640 - loss: 2.7323
[1m 38/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 49ms/step - accuracy: 0.1637 - loss: 2.7329
[1m 39/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 49ms/step - accuracy: 0.1635 - loss: 2.7338
[36m(train_cnn_ray_tune pid=2857955)[0m Epoch 7/24[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m42s[0m 72ms/step - accuracy: 0.1809 - loss: 2.5887 - val_accuracy: 0.2022 - val_loss: 2.3672[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 29ms/step - accuracy: 0.2133 - loss: 2.3752
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 29ms/step - accuracy: 0.2133 - loss: 2.3752
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 29ms/step - accuracy: 0.2133 - loss: 2.3752
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:48[0m 186ms/step - accuracy: 0.2188 - loss: 2.2622
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 74ms/step - accuracy: 0.2656 - loss: 2.1653  
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m342/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 36ms/step - accuracy: 0.2355 - loss: 2.1951
[1m344/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 36ms/step - accuracy: 0.2355 - loss: 2.1950[32m [repeated 114x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m498/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 47ms/step - accuracy: 0.1604 - loss: 2.6208[32m [repeated 133x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 29ms/step - accuracy: 0.2132 - loss: 2.3752
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 29ms/step - accuracy: 0.2132 - loss: 2.3752
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 29ms/step - accuracy: 0.2132 - loss: 2.3753
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m43s[0m 37ms/step - accuracy: 0.1504 - loss: 2.6587 - val_accuracy: 0.1769 - val_loss: 2.4186
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.1279 - loss: 2.7237 
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 43ms/step - accuracy: 0.1498 - loss: 2.7471[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 43ms/step - accuracy: 0.1498 - loss: 2.7470
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 43ms/step - accuracy: 0.1498 - loss: 2.7470[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m134/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m26s[0m 58ms/step - accuracy: 0.3281 - loss: 1.8077[32m [repeated 93x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m 63/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 45ms/step - accuracy: 0.3421 - loss: 1.7822
[1m 65/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 45ms/step - accuracy: 0.3420 - loss: 1.7828[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 111ms/step - accuracy: 0.3438 - loss: 1.5197[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 171/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 39ms/step - accuracy: 0.1123 - loss: 2.9809
[1m 172/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 39ms/step - accuracy: 0.1124 - loss: 2.9807[32m [repeated 164x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m26s[0m 47ms/step - accuracy: 0.1597 - loss: 2.6638[32m [repeated 219x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m25s[0m 47ms/step - accuracy: 0.1598 - loss: 2.6638
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m25s[0m 47ms/step - accuracy: 0.1598 - loss: 2.6638
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m25s[0m 47ms/step - accuracy: 0.1598 - loss: 2.6638
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m 43/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 62ms/step - accuracy: 0.2872 - loss: 2.0080
[1m 44/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 62ms/step - accuracy: 0.2874 - loss: 2.0075
[1m 45/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 62ms/step - accuracy: 0.2876 - loss: 2.0070
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m 16/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 61ms/step - accuracy: 0.1873 - loss: 2.4291
[1m 17/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 61ms/step - accuracy: 0.1879 - loss: 2.4274
[1m 18/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 61ms/step - accuracy: 0.1887 - loss: 2.4264
[36m(train_cnn_ray_tune pid=2857951)[0m Epoch 7/21[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m36s[0m 61ms/step - accuracy: 0.2099 - loss: 2.4110 - val_accuracy: 0.2209 - val_loss: 2.2236[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:57[0m 101ms/step - accuracy: 0.1875 - loss: 2.4412
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 44ms/step - accuracy: 0.1285 - loss: 2.6696  
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m463/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 38ms/step - accuracy: 0.2369 - loss: 2.1935
[1m464/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 38ms/step - accuracy: 0.2369 - loss: 2.1935[32m [repeated 70x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m461/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 38ms/step - accuracy: 0.2369 - loss: 2.1935[32m [repeated 108x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 43ms/step - accuracy: 0.1500 - loss: 2.7448[32m [repeated 31x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 43ms/step - accuracy: 0.1500 - loss: 2.7447
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 43ms/step - accuracy: 0.1500 - loss: 2.7447[32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m213/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m22s[0m 61ms/step - accuracy: 0.3281 - loss: 1.8062[32m [repeated 152x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m126/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m28s[0m 63ms/step - accuracy: 0.1921 - loss: 2.5388
[1m127/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m28s[0m 63ms/step - accuracy: 0.1922 - loss: 2.5386[32m [repeated 160x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:19[0m 136ms/step - accuracy: 0.1562 - loss: 2.4755[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 50ms/step - accuracy: 0.1372 - loss: 2.4040  
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 50ms/step - accuracy: 0.1361 - loss: 2.4203
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m15s[0m 60ms/step - accuracy: 0.2485 - loss: 2.1206
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m15s[0m 60ms/step - accuracy: 0.2485 - loss: 2.1206[32m [repeated 165x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m36s[0m 41ms/step - accuracy: 0.1192 - loss: 2.9587[32m [repeated 240x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 30ms/step - accuracy: 0.2120 - loss: 2.3733
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 30ms/step - accuracy: 0.2120 - loss: 2.3733
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 30ms/step - accuracy: 0.2120 - loss: 2.3733
[36m(train_cnn_ray_tune pid=2857964)[0m Epoch 8/26[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m31s[0m 53ms/step - accuracy: 0.1608 - loss: 2.6196 - val_accuracy: 0.1944 - val_loss: 2.3677[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m573/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.2377 - loss: 2.1926
[1m575/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.2377 - loss: 2.1925[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m583/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.2378 - loss: 2.1925[32m [repeated 31x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 43ms/step - accuracy: 0.1501 - loss: 2.7439[32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 43ms/step - accuracy: 0.1501 - loss: 2.7441
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 43ms/step - accuracy: 0.1501 - loss: 2.7441[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m300/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m12s[0m 43ms/step - accuracy: 0.3433 - loss: 1.7708[32m [repeated 240x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m201/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m24s[0m 64ms/step - accuracy: 0.1922 - loss: 2.5344
[1m202/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m24s[0m 64ms/step - accuracy: 0.1922 - loss: 2.5343[32m [repeated 202x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 97ms/step - accuracy: 0.1562 - loss: 2.4149[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 61ms/step - accuracy: 0.2552 - loss: 2.4790  
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 63ms/step - accuracy: 0.2441 - loss: 2.4918
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m16s[0m 47ms/step - accuracy: 0.1601 - loss: 2.6642
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m16s[0m 47ms/step - accuracy: 0.1601 - loss: 2.6642[32m [repeated 149x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m31s[0m 41ms/step - accuracy: 0.1222 - loss: 2.9453[32m [repeated 262x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m298/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 54ms/step - accuracy: 0.1513 - loss: 2.7509
[1m299/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 54ms/step - accuracy: 0.1513 - loss: 2.7509
[1m300/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 54ms/step - accuracy: 0.1513 - loss: 2.7509
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 59ms/step - accuracy: 0.2708 - loss: 2.1254  
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 65ms/step - accuracy: 0.2656 - loss: 2.1357
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m11s[0m 60ms/step - accuracy: 0.2492 - loss: 2.1184
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m11s[0m 60ms/step - accuracy: 0.2492 - loss: 2.1184
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m11s[0m 60ms/step - accuracy: 0.2492 - loss: 2.1183
[36m(train_cnn_ray_tune pid=2857954)[0m Epoch 10/28[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m24s[0m 33ms/step - accuracy: 0.1499 - loss: 2.6423
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m24s[0m 33ms/step - accuracy: 0.1499 - loss: 2.6423
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m24s[0m 33ms/step - accuracy: 0.1499 - loss: 2.6423
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.2205 - loss: 2.3227 
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.2205 - loss: 2.3226
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m26s[0m 44ms/step - accuracy: 0.2378 - loss: 2.1925 - val_accuracy: 0.2492 - val_loss: 2.2117[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m318/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.1510 - loss: 2.6391 
[1m320/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.1511 - loss: 2.6392
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m357/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 43ms/step - accuracy: 0.3436 - loss: 1.7691
[1m359/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 43ms/step - accuracy: 0.3436 - loss: 1.7690[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m325/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.1511 - loss: 2.6393
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m364/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 43ms/step - accuracy: 0.3436 - loss: 1.7688
Trial status: 20 RUNNING
Current time: 2025-11-07 13:56:33. 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_a058a    RUNNING            3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21 │
│ trial_a058a    RUNNING            3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15 │
│ trial_a058a    RUNNING            2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26 │
│ trial_a058a    RUNNING            2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28 │
│ trial_a058a    RUNNING            2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22 │
│ trial_a058a    RUNNING            2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21 │
│ trial_a058a    RUNNING            3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24 │
│ trial_a058a    RUNNING            2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28 │
│ trial_a058a    RUNNING            2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25 │
│ trial_a058a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23 │
│ trial_a058a    RUNNING            3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23 │
│ trial_a058a    RUNNING            2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27 │
│ trial_a058a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000164705         24 │
│ trial_a058a    RUNNING            2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24 │
│ trial_a058a    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21 │
│ trial_a058a    RUNNING            3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m57s[0m 49ms/step - accuracy: 0.1501 - loss: 2.7439 - val_accuracy: 0.1996 - val_loss: 2.4389
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 52ms/step - accuracy: 0.1250 - loss: 2.7396 
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 53ms/step - accuracy: 0.1393 - loss: 2.7397
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 49ms/step - accuracy: 0.1328 - loss: 2.7671 
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m  17/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.1430 - loss: 2.7881
[1m  18/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.1443 - loss: 2.7854
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m  20/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.1459 - loss: 2.7808
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 48ms/step - accuracy: 0.1468 - loss: 2.7804 
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 37ms/step - accuracy: 0.2206 - loss: 2.3211[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 30ms/step - accuracy: 0.2121 - loss: 2.3668
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 30ms/step - accuracy: 0.2121 - loss: 2.3667[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m255/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 57ms/step - accuracy: 0.2208 - loss: 2.3674[32m [repeated 247x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m276/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 65ms/step - accuracy: 0.1920 - loss: 2.5322
[1m277/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 65ms/step - accuracy: 0.1920 - loss: 2.5322[32m [repeated 206x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:42[0m 139ms/step - accuracy: 0.1250 - loss: 2.6692[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m21s[0m 33ms/step - accuracy: 0.1488 - loss: 2.6411
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 33ms/step - accuracy: 0.1488 - loss: 2.6411[32m [repeated 110x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m26s[0m 42ms/step - accuracy: 0.1242 - loss: 2.9371[32m [repeated 165x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m191/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m19s[0m 48ms/step - accuracy: 0.1662 - loss: 2.5982
[1m192/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m18s[0m 48ms/step - accuracy: 0.1662 - loss: 2.5981
[1m193/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m18s[0m 48ms/step - accuracy: 0.1662 - loss: 2.5980[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m Epoch 5/22
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m12s[0m 48ms/step - accuracy: 0.1601 - loss: 2.6643
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m12s[0m 48ms/step - accuracy: 0.1601 - loss: 2.6643
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m11s[0m 48ms/step - accuracy: 0.1601 - loss: 2.6643[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m400/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 54ms/step - accuracy: 0.1508 - loss: 2.7506 
[1m401/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 54ms/step - accuracy: 0.1508 - loss: 2.7506[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m472/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 43ms/step - accuracy: 0.3443 - loss: 1.7660
[1m473/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 44ms/step - accuracy: 0.3443 - loss: 1.7659[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m421/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 55ms/step - accuracy: 0.1507 - loss: 2.7504
[1m422/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 55ms/step - accuracy: 0.1507 - loss: 2.7504
[1m423/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 55ms/step - accuracy: 0.1507 - loss: 2.7504
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m475/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 43ms/step - accuracy: 0.3443 - loss: 1.7659[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 48ms/step - accuracy: 0.1600 - loss: 2.6637[32m [repeated 111x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 61ms/step - accuracy: 0.2512 - loss: 2.1115
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 61ms/step - accuracy: 0.2512 - loss: 2.1115[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m313/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m12s[0m 47ms/step - accuracy: 0.1666 - loss: 2.5941[32m [repeated 217x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m349/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 66ms/step - accuracy: 0.1920 - loss: 2.5307
[1m350/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 66ms/step - accuracy: 0.1920 - loss: 2.5307[32m [repeated 158x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 34ms/step - accuracy: 0.1482 - loss: 2.6404
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 34ms/step - accuracy: 0.1482 - loss: 2.6404[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m21s[0m 42ms/step - accuracy: 0.1255 - loss: 2.9317[32m [repeated 184x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m375/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 57ms/step - accuracy: 0.2214 - loss: 2.3656
[1m376/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 57ms/step - accuracy: 0.2214 - loss: 2.3656
[1m377/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 57ms/step - accuracy: 0.2214 - loss: 2.3656
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m304/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.2150 - loss: 2.3237 
[1m306/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.2150 - loss: 2.3236
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m458/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 55ms/step - accuracy: 0.2822 - loss: 1.9824
[1m460/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 55ms/step - accuracy: 0.2822 - loss: 1.9824[32m [repeated 106x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m378/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 43ms/step - accuracy: 0.1876 - loss: 2.4683
[1m379/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 43ms/step - accuracy: 0.1876 - loss: 2.4683
[1m380/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 43ms/step - accuracy: 0.1876 - loss: 2.4684[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m462/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 55ms/step - accuracy: 0.2822 - loss: 1.9823[32m [repeated 164x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m405/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 56ms/step - accuracy: 0.2216 - loss: 2.3649 
[1m406/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 56ms/step - accuracy: 0.2216 - loss: 2.3649
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.1636 - loss: 2.7131 
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.1637 - loss: 2.7130
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 47ms/step - accuracy: 0.1600 - loss: 2.6627[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 47ms/step - accuracy: 0.1600 - loss: 2.6627
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 47ms/step - accuracy: 0.1600 - loss: 2.6627[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 43ms/step - accuracy: 0.1511 - loss: 2.6400 - val_accuracy: 0.1791 - val_loss: 2.4241
[36m(train_cnn_ray_tune pid=2857956)[0m Epoch 11/27
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m422/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 66ms/step - accuracy: 0.1919 - loss: 2.5298[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m423/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 66ms/step - accuracy: 0.1919 - loss: 2.5298
[1m424/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 66ms/step - accuracy: 0.1919 - loss: 2.5298[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 88ms/step - accuracy: 0.2500 - loss: 2.3559
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 47ms/step - accuracy: 0.1600 - loss: 2.6626
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 47ms/step - accuracy: 0.1600 - loss: 2.6626
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 47ms/step - accuracy: 0.1600 - loss: 2.6626
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 33ms/step - accuracy: 0.1480 - loss: 2.6391
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 33ms/step - accuracy: 0.1480 - loss: 2.6391[32m [repeated 100x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m15s[0m 41ms/step - accuracy: 0.1266 - loss: 2.9269[32m [repeated 140x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m41s[0m 35ms/step - accuracy: 0.2125 - loss: 2.3633 - val_accuracy: 0.2444 - val_loss: 2.1923
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:49[0m 94ms/step - accuracy: 0.3750 - loss: 2.2442
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 18ms/step - accuracy: 0.3438 - loss: 2.1610 
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m465/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 66ms/step - accuracy: 0.1918 - loss: 2.5298
[1m466/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 66ms/step - accuracy: 0.1918 - loss: 2.5298[32m [repeated 170x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m560/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 55ms/step - accuracy: 0.2825 - loss: 1.9799[32m [repeated 202x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m434/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 66ms/step - accuracy: 0.1919 - loss: 2.5298 
[1m435/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 66ms/step - accuracy: 0.1919 - loss: 2.5298[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 59ms/step - accuracy: 0.3281 - loss: 2.0988 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 58ms/step - accuracy: 0.3299 - loss: 2.0604
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 55ms/step - accuracy: 0.3310 - loss: 2.0253
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 56ms/step - accuracy: 0.3332 - loss: 2.0132
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 58ms/step - accuracy: 0.3289 - loss: 2.0211
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 59ms/step - accuracy: 0.3259 - loss: 2.0209
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 59ms/step - accuracy: 0.3236 - loss: 2.0204
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  10/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 59ms/step - accuracy: 0.3232 - loss: 2.0174
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 59ms/step - accuracy: 0.3222 - loss: 2.0175
[1m  12/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 59ms/step - accuracy: 0.3214 - loss: 2.0169
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m545/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 54ms/step - accuracy: 0.2221 - loss: 2.3616
[1m546/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 54ms/step - accuracy: 0.2221 - loss: 2.3616
[1m547/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 54ms/step - accuracy: 0.2221 - loss: 2.3616
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 59ms/step - accuracy: 0.3207 - loss: 2.0154
[1m  14/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 59ms/step - accuracy: 0.3195 - loss: 2.0139
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 39ms/step - accuracy: 0.1640 - loss: 2.7097[32m [repeated 65x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  15/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.3182 - loss: 2.0125
[1m  16/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 58ms/step - accuracy: 0.3166 - loss: 2.0119
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 33ms/step - accuracy: 0.1481 - loss: 2.6380
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 33ms/step - accuracy: 0.1481 - loss: 2.6380[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m36s[0m 61ms/step - accuracy: 0.1504 - loss: 2.7494 - val_accuracy: 0.1961 - val_loss: 2.4350[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m Epoch 8/24[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m147/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m14s[0m 33ms/step - accuracy: 0.1621 - loss: 2.5944[32m [repeated 42x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m116/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m18s[0m 40ms/step - accuracy: 0.3543 - loss: 1.7246
[1m118/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m18s[0m 40ms/step - accuracy: 0.3543 - loss: 1.7247[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  18/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.3146 - loss: 2.0109
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 119ms/step - accuracy: 0.1250 - loss: 2.5106[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  20/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.3119 - loss: 2.0126
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.3090 - loss: 2.0173
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.3073 - loss: 2.0195
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.3057 - loss: 2.0213
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.3042 - loss: 2.0227
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.3027 - loss: 2.0240
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.3014 - loss: 2.0252
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.3003 - loss: 2.0264
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.2992 - loss: 2.0274
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  30/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.2982 - loss: 2.0281
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m24s[0m 25ms/step - accuracy: 0.2138 - loss: 2.3077
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m24s[0m 25ms/step - accuracy: 0.2137 - loss: 2.3078[32m [repeated 111x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m32s[0m 43ms/step - accuracy: 0.1640 - loss: 2.6993[32m [repeated 132x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  32/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.2963 - loss: 2.0290
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.2947 - loss: 2.0302
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m79s[0m 68ms/step - accuracy: 0.2513 - loss: 2.1109 - val_accuracy: 0.2648 - val_loss: 2.0268[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.2941 - loss: 2.0307
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.2935 - loss: 2.0311
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:49[0m 94ms/step - accuracy: 0.3750 - loss: 2.1204
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 34ms/step - accuracy: 0.2778 - loss: 2.2742 
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.2929 - loss: 2.0312
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.2923 - loss: 2.0316
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.2917 - loss: 2.0320
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.2910 - loss: 2.0325
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m148/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m17s[0m 39ms/step - accuracy: 0.3542 - loss: 1.7274
[1m149/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m17s[0m 40ms/step - accuracy: 0.3542 - loss: 1.7275
[1m150/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m17s[0m 40ms/step - accuracy: 0.3542 - loss: 1.7275
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 55ms/step - accuracy: 0.2905 - loss: 2.0326
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.2899 - loss: 2.0330
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.2893 - loss: 2.0333
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  44/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.2888 - loss: 2.0334
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.2878 - loss: 2.0334
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.2870 - loss: 2.0333
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.2868 - loss: 2.0331
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.2862 - loss: 2.0329
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.2859 - loss: 2.0328
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 55ms/step - accuracy: 0.2854 - loss: 2.0325
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.2848 - loss: 2.0322
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  58/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.2843 - loss: 2.0319
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  59/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.2841 - loss: 2.0315
[1m  60/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.2840 - loss: 2.0311
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  61/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.2838 - loss: 2.0307
[1m  62/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.2836 - loss: 2.0305
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  64/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 54ms/step - accuracy: 0.2831 - loss: 2.0302 
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m552/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 65ms/step - accuracy: 0.1915 - loss: 2.5299
[1m554/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 65ms/step - accuracy: 0.1915 - loss: 2.5299[32m [repeated 102x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m550/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 65ms/step - accuracy: 0.1915 - loss: 2.5299[32m [repeated 99x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:58[0m 102ms/step - accuracy: 0.1250 - loss: 2.8058
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.1406 - loss: 2.7899 
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 47ms/step - accuracy: 0.1367 - loss: 2.7759 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 48ms/step - accuracy: 0.1419 - loss: 2.7511
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 81ms/step - accuracy: 0.2344 - loss: 1.9328  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 67ms/step - accuracy: 0.2396 - loss: 1.9361
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 40ms/step - accuracy: 0.1281 - loss: 2.9209[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 32ms/step - accuracy: 0.1484 - loss: 2.6362
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 32ms/step - accuracy: 0.1484 - loss: 2.6362[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m30s[0m 51ms/step - accuracy: 0.1667 - loss: 2.5901 - val_accuracy: 0.2083 - val_loss: 2.3634[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m Epoch 9/26[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 99/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m24s[0m 51ms/step - accuracy: 0.1438 - loss: 2.7319[32m [repeated 148x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 31/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 57ms/step - accuracy: 0.3012 - loss: 1.8578
[1m 32/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 57ms/step - accuracy: 0.3021 - loss: 1.8563[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 130ms/step - accuracy: 0.2188 - loss: 2.5047[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.1415 - loss: 2.8792 
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.1415 - loss: 2.8792
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  58/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 46ms/step - accuracy: 0.1719 - loss: 2.6083
[1m  60/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 46ms/step - accuracy: 0.1719 - loss: 2.6074[32m [repeated 108x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m29s[0m 33ms/step - accuracy: 0.2286 - loss: 2.2547[32m [repeated 156x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m62s[0m 53ms/step - accuracy: 0.1600 - loss: 2.6623 - val_accuracy: 0.1754 - val_loss: 2.3874
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m370/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 34ms/step - accuracy: 0.1608 - loss: 2.5980
[1m372/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 34ms/step - accuracy: 0.1608 - loss: 2.5980[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m376/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 34ms/step - accuracy: 0.1607 - loss: 2.5980[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 65ms/step - accuracy: 0.2812 - loss: 2.2485  
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 58ms/step - accuracy: 0.2682 - loss: 2.3004[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m51s[0m 43ms/step - accuracy: 0.1644 - loss: 2.7072 - val_accuracy: 0.2170 - val_loss: 2.4038
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:06[0m 109ms/step - accuracy: 0.3750 - loss: 2.3104
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 55ms/step - accuracy: 0.3125 - loss: 2.3665 
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m345/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 40ms/step - accuracy: 0.3551 - loss: 1.7310
[1m346/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 40ms/step - accuracy: 0.3551 - loss: 1.7310
[1m347/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 40ms/step - accuracy: 0.3551 - loss: 1.7310
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.2778 - loss: 2.4546
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 46ms/step - accuracy: 0.2510 - loss: 2.5199 
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m134/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m23s[0m 53ms/step - accuracy: 0.2895 - loss: 1.9118
[1m135/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m23s[0m 53ms/step - accuracy: 0.2895 - loss: 1.9119
[1m136/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m23s[0m 53ms/step - accuracy: 0.2895 - loss: 1.9120
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 35ms/step - accuracy: 0.1042 - loss: 2.6418  
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 31ms/step - accuracy: 0.1269 - loss: 2.6047
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 30ms/step - accuracy: 0.1346 - loss: 2.5935
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 50ms/step - accuracy: 0.1421 - loss: 2.8770[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 40ms/step - accuracy: 0.1286 - loss: 2.9190
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 40ms/step - accuracy: 0.1286 - loss: 2.9189[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m42s[0m 72ms/step - accuracy: 0.1914 - loss: 2.5298 - val_accuracy: 0.2043 - val_loss: 2.3544[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m Epoch 7/23[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m129/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 37ms/step - accuracy: 0.2633 - loss: 2.1212[32m [repeated 174x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m 80/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 55ms/step - accuracy: 0.2223 - loss: 2.3468
[1m 81/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 55ms/step - accuracy: 0.2224 - loss: 2.3463[32m [repeated 188x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:44[0m 141ms/step - accuracy: 0.1250 - loss: 2.5795[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m56s[0m 58ms/step - accuracy: 0.2839 - loss: 2.0164
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m56s[0m 58ms/step - accuracy: 0.2839 - loss: 2.0164[32m [repeated 121x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m17s[0m 28ms/step - accuracy: 0.2130 - loss: 2.3095[32m [repeated 143x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m415/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 41ms/step - accuracy: 0.3553 - loss: 1.7307
[1m416/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 42ms/step - accuracy: 0.3553 - loss: 1.7307[32m [repeated 55x across cluster][0m
Trial status: 20 RUNNING
Current time: 2025-11-07 13:57:03. 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_a058a    RUNNING            3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21 │
│ trial_a058a    RUNNING            3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15 │
│ trial_a058a    RUNNING            2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26 │
│ trial_a058a    RUNNING            2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28 │
│ trial_a058a    RUNNING            2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22 │
│ trial_a058a    RUNNING            2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21 │
│ trial_a058a    RUNNING            3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24 │
│ trial_a058a    RUNNING            2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28 │
│ trial_a058a    RUNNING            2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25 │
│ trial_a058a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23 │
│ trial_a058a    RUNNING            3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23 │
│ trial_a058a    RUNNING            2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27 │
│ trial_a058a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000164705         24 │
│ trial_a058a    RUNNING            2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24 │
│ trial_a058a    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21 │
│ trial_a058a    RUNNING            3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m429/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.2226 - loss: 2.2857[32m [repeated 84x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m42s[0m 36ms/step - accuracy: 0.1484 - loss: 2.6362 - val_accuracy: 0.1708 - val_loss: 2.4101
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 123ms/step - accuracy: 0.0938 - loss: 2.7442
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 74ms/step - accuracy: 0.1016 - loss: 2.6962  
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m155/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 56ms/step - accuracy: 0.2251 - loss: 2.3269
[1m156/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 56ms/step - accuracy: 0.2251 - loss: 2.3268
[1m157/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 56ms/step - accuracy: 0.2252 - loss: 2.3266[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 50ms/step - accuracy: 0.1426 - loss: 2.8755[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 50ms/step - accuracy: 0.1426 - loss: 2.8755
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 50ms/step - accuracy: 0.1426 - loss: 2.8755[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m281/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m16s[0m 53ms/step - accuracy: 0.1502 - loss: 2.7238[32m [repeated 237x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 89/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m32s[0m 65ms/step - accuracy: 0.1703 - loss: 2.5352
[1m 90/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m32s[0m 65ms/step - accuracy: 0.1704 - loss: 2.5350[32m [repeated 153x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m52s[0m 45ms/step - accuracy: 0.1287 - loss: 2.9189 - val_accuracy: 0.1495 - val_loss: 2.5836
[36m(train_cnn_ray_tune pid=2857942)[0m Epoch 6/21
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:46[0m 92ms/step - accuracy: 0.1250 - loss: 2.5741
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m44s[0m 49ms/step - accuracy: 0.1616 - loss: 2.6131
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m44s[0m 49ms/step - accuracy: 0.1615 - loss: 2.6131[32m [repeated 126x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m33s[0m 34ms/step - accuracy: 0.1672 - loss: 2.5769[32m [repeated 237x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 50ms/step - accuracy: 0.1406 - loss: 2.6105 
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m529/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 32ms/step - accuracy: 0.2219 - loss: 2.2871
[1m531/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 32ms/step - accuracy: 0.2219 - loss: 2.2872
[1m533/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 32ms/step - accuracy: 0.2218 - loss: 2.2872
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m344/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 41ms/step - accuracy: 0.2002 - loss: 2.4350 
[1m346/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 41ms/step - accuracy: 0.2001 - loss: 2.4350
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m528/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 42ms/step - accuracy: 0.3561 - loss: 1.7289
[1m529/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 42ms/step - accuracy: 0.3561 - loss: 1.7289[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m530/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 42ms/step - accuracy: 0.3561 - loss: 1.7289[32m [repeated 78x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m23s[0m 40ms/step - accuracy: 0.1593 - loss: 2.6001 - val_accuracy: 0.1795 - val_loss: 2.4111
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 39ms/step - accuracy: 0.2153 - loss: 2.4985  
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 45ms/step - accuracy: 0.2103 - loss: 2.5181
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 50ms/step - accuracy: 0.1426 - loss: 2.8753[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m 43/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 42ms/step - accuracy: 0.1620 - loss: 2.6050[32m [repeated 165x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m256/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 57ms/step - accuracy: 0.2276 - loss: 2.3156
[1m257/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 57ms/step - accuracy: 0.2276 - loss: 2.3155[32m [repeated 173x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m Epoch 13/24[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 122ms/step - accuracy: 0.1562 - loss: 2.2036[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m48s[0m 60ms/step - accuracy: 0.2856 - loss: 2.0155
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m47s[0m 60ms/step - accuracy: 0.2856 - loss: 2.0154[32m [repeated 166x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 45ms/step - accuracy: 0.1535 - loss: 2.8394[32m [repeated 231x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2131 - loss: 2.3065
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2132 - loss: 2.3065
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2132 - loss: 2.3065
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2132 - loss: 2.3065
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2132 - loss: 2.3065
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2132 - loss: 2.3064
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2132 - loss: 2.3064
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2132 - loss: 2.3064
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2132 - loss: 2.3064
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2132 - loss: 2.3063
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m399/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 54ms/step - accuracy: 0.1513 - loss: 2.7214 
[1m400/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 54ms/step - accuracy: 0.1513 - loss: 2.7214[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2132 - loss: 2.3062
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2132 - loss: 2.3062
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2132 - loss: 2.3062
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2132 - loss: 2.3062
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2132 - loss: 2.3061
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2132 - loss: 2.3061
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2132 - loss: 2.3061
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2132 - loss: 2.3061
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2132 - loss: 2.3060
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2132 - loss: 2.3060
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2132 - loss: 2.3060
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2133 - loss: 2.3060
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m480/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 42ms/step - accuracy: 0.1990 - loss: 2.4368
[1m481/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 42ms/step - accuracy: 0.1990 - loss: 2.4368[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2133 - loss: 2.3059
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2133 - loss: 2.3059
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m485/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 42ms/step - accuracy: 0.1989 - loss: 2.4369[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m66s[0m 57ms/step - accuracy: 0.1426 - loss: 2.8753 - val_accuracy: 0.1874 - val_loss: 2.4967
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 30ms/step - accuracy: 0.2133 - loss: 2.3059
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 30ms/step - accuracy: 0.2133 - loss: 2.3059
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m36s[0m 48ms/step - accuracy: 0.1613 - loss: 2.6116
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m36s[0m 48ms/step - accuracy: 0.1613 - loss: 2.6116
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m36s[0m 48ms/step - accuracy: 0.1613 - loss: 2.6116
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:52[0m 148ms/step - accuracy: 0.1875 - loss: 2.8484
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.2031 - loss: 2.7122 
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 30ms/step - accuracy: 0.2133 - loss: 2.3059
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 30ms/step - accuracy: 0.2133 - loss: 2.3058
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 49ms/step - accuracy: 0.1940 - loss: 2.6931 
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m21s[0m 37ms/step - accuracy: 0.2215 - loss: 2.2880 - val_accuracy: 0.2350 - val_loss: 2.1687
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.1814 - loss: 2.6924
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 58ms/step - accuracy: 0.1713 - loss: 2.7175
[1m  10/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 59ms/step - accuracy: 0.1686 - loss: 2.7234
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 61ms/step - accuracy: 0.1651 - loss: 2.7336
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  12/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 61ms/step - accuracy: 0.1618 - loss: 2.7428
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 63ms/step - accuracy: 0.1590 - loss: 2.7514
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m390/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 55ms/step - accuracy: 0.2907 - loss: 1.9199
[1m391/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 55ms/step - accuracy: 0.2907 - loss: 1.9199
[1m392/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 55ms/step - accuracy: 0.2907 - loss: 1.9199
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  14/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 63ms/step - accuracy: 0.1562 - loss: 2.7602
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  15/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 62ms/step - accuracy: 0.1539 - loss: 2.7664
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  17/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.1498 - loss: 2.7783
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  18/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 59ms/step - accuracy: 0.1482 - loss: 2.7831
[1m  19/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 59ms/step - accuracy: 0.1472 - loss: 2.7860
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m29s[0m 49ms/step - accuracy: 0.3565 - loss: 1.7283 - val_accuracy: 0.2779 - val_loss: 2.0584
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  20/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.1462 - loss: 2.7887
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.1454 - loss: 2.7911
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.1446 - loss: 2.7937
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.1432 - loss: 2.7987
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.1423 - loss: 2.8016
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.1414 - loss: 2.8046
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.1407 - loss: 2.8070
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.1403 - loss: 2.8081
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  30/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.1392 - loss: 2.8112
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  31/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.1389 - loss: 2.8122
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.1382 - loss: 2.8144
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.1378 - loss: 2.8156
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.1375 - loss: 2.8166
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 30ms/step - accuracy: 0.2134 - loss: 2.3051[32m [repeated 31x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.1372 - loss: 2.8175
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.1369 - loss: 2.8186
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.1365 - loss: 2.8197
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.1361 - loss: 2.8208
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m349/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 63ms/step - accuracy: 0.3329 - loss: 1.7786[32m [repeated 176x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m254/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m20s[0m 63ms/step - accuracy: 0.1798 - loss: 2.5255
[1m255/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m20s[0m 63ms/step - accuracy: 0.1798 - loss: 2.5255[32m [repeated 144x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.1358 - loss: 2.8218
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.1353 - loss: 2.8237
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.1351 - loss: 2.8244
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  44/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 60ms/step - accuracy: 0.1348 - loss: 2.8253
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  45/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 61ms/step - accuracy: 0.1346 - loss: 2.8260
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 61ms/step - accuracy: 0.1344 - loss: 2.8265
[36m(train_cnn_ray_tune pid=2857959)[0m Epoch 10/25[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 61ms/step - accuracy: 0.1342 - loss: 2.8269
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 61ms/step - accuracy: 0.1340 - loss: 2.8274
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 96ms/step - accuracy: 0.2812 - loss: 1.9302
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m33s[0m 48ms/step - accuracy: 0.1615 - loss: 2.6112
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m33s[0m 48ms/step - accuracy: 0.1615 - loss: 2.6112[32m [repeated 131x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m39s[0m 43ms/step - accuracy: 0.1455 - loss: 2.8524[32m [repeated 182x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 61ms/step - accuracy: 0.1338 - loss: 2.8278
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 43ms/step - accuracy: 0.1610 - loss: 2.6892
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 43ms/step - accuracy: 0.1610 - loss: 2.6892[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.1334 - loss: 2.8285
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.1331 - loss: 2.8288
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.1331 - loss: 2.8289
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.1330 - loss: 2.8288
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  57/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.1330 - loss: 2.8289
[1m  58/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.1330 - loss: 2.8290
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  60/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.1331 - loss: 2.8292
[1m  61/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.1330 - loss: 2.8293
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  62/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.1330 - loss: 2.8294
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  63/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.1330 - loss: 2.8294
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m374/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.1745 - loss: 2.5361 
[1m376/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.1745 - loss: 2.5360
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  65/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.1329 - loss: 2.8296
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  67/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 58ms/step - accuracy: 0.1329 - loss: 2.8300
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  68/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 58ms/step - accuracy: 0.1329 - loss: 2.8302
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  70/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.1329 - loss: 2.8305
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.1330 - loss: 2.8305
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m447/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 55ms/step - accuracy: 0.2909 - loss: 1.9199
[1m448/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 55ms/step - accuracy: 0.2909 - loss: 1.9199
[1m449/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 55ms/step - accuracy: 0.2909 - loss: 1.9199
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 58ms/step - accuracy: 0.1330 - loss: 2.8307
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.1330 - loss: 2.8308
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.1330 - loss: 2.8307
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.1330 - loss: 2.8308
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 57ms/step - accuracy: 0.1330 - loss: 2.8309
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 57ms/step - accuracy: 0.1330 - loss: 2.8309
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 57ms/step - accuracy: 0.1331 - loss: 2.8307
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 57ms/step - accuracy: 0.1332 - loss: 2.8305
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  86/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 57ms/step - accuracy: 0.1333 - loss: 2.8304
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m458/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 55ms/step - accuracy: 0.2909 - loss: 1.9200
[1m459/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 55ms/step - accuracy: 0.2909 - loss: 1.9200[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  88/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1335 - loss: 2.8301
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m475/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 48ms/step - accuracy: 0.1742 - loss: 2.5353[32m [repeated 139x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  89/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1335 - loss: 2.8300
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m42s[0m 61ms/step - accuracy: 0.2864 - loss: 2.0122
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m42s[0m 60ms/step - accuracy: 0.2864 - loss: 2.0122
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m41s[0m 60ms/step - accuracy: 0.2864 - loss: 2.0121
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  90/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1336 - loss: 2.8298
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  91/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.1337 - loss: 2.8296
[1m  93/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1340 - loss: 2.8292
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  95/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1342 - loss: 2.8289
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  97/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1344 - loss: 2.8286
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  98/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1345 - loss: 2.8284
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1346 - loss: 2.8282
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1347 - loss: 2.8281
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1349 - loss: 2.8280
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 56ms/step - accuracy: 0.1351 - loss: 2.8277 
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 56ms/step - accuracy: 0.1352 - loss: 2.8276
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.2302 - loss: 2.2480 
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.2302 - loss: 2.2480
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.2303 - loss: 2.2479[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m425/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 64ms/step - accuracy: 0.3348 - loss: 1.7750[32m [repeated 131x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m326/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 64ms/step - accuracy: 0.1815 - loss: 2.5232
[1m327/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 64ms/step - accuracy: 0.1815 - loss: 2.5232[32m [repeated 136x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 43ms/step - accuracy: 0.1608 - loss: 2.6878
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 43ms/step - accuracy: 0.1608 - loss: 2.6877
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 43ms/step - accuracy: 0.1608 - loss: 2.6877
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m288/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.2278 - loss: 2.2740 
[1m290/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.2278 - loss: 2.2740
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 48ms/step - accuracy: 0.1983 - loss: 2.4376 - val_accuracy: 0.2196 - val_loss: 2.3080
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:29[0m 153ms/step - accuracy: 0.1562 - loss: 2.3696
[36m(train_cnn_ray_tune pid=2857966)[0m Epoch 11/28
[36m(train_cnn_ray_tune pid=2857954)[0m Epoch 12/28
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m34s[0m 42ms/step - accuracy: 0.1430 - loss: 2.8544
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m33s[0m 42ms/step - accuracy: 0.1430 - loss: 2.8545[32m [repeated 121x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m38s[0m 61ms/step - accuracy: 0.2867 - loss: 2.0106[32m [repeated 181x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 43ms/step - accuracy: 0.1608 - loss: 2.6875
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 43ms/step - accuracy: 0.1608 - loss: 2.6875[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 129ms/step - accuracy: 0.3750 - loss: 1.8695
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 51ms/step - accuracy: 0.3359 - loss: 1.9498  
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m463/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 64ms/step - accuracy: 0.3354 - loss: 1.7738
[1m464/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 64ms/step - accuracy: 0.3354 - loss: 1.7738[32m [repeated 102x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m467/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 64ms/step - accuracy: 0.3354 - loss: 1.7737[32m [repeated 135x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m556/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 55ms/step - accuracy: 0.2911 - loss: 1.9202
[1m557/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 55ms/step - accuracy: 0.2911 - loss: 1.9202
[1m558/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 55ms/step - accuracy: 0.2911 - loss: 1.9202
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 36ms/step - accuracy: 0.2306 - loss: 2.2471[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m106/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m18s[0m 38ms/step - accuracy: 0.2767 - loss: 2.0708[32m [repeated 102x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m411/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 63ms/step - accuracy: 0.1829 - loss: 2.5195
[1m412/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 63ms/step - accuracy: 0.1829 - loss: 2.5194[32m [repeated 80x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m323/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.1544 - loss: 2.6192 
[1m325/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.1545 - loss: 2.6192
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m36s[0m 61ms/step - accuracy: 0.1527 - loss: 2.7184 - val_accuracy: 0.2009 - val_loss: 2.4251[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 105ms/step - accuracy: 0.2500 - loss: 2.4836
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m40s[0m 34ms/step - accuracy: 0.2137 - loss: 2.3029 - val_accuracy: 0.2357 - val_loss: 2.1245
[36m(train_cnn_ray_tune pid=2857965)[0m Epoch 8/25[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m49s[0m 54ms/step - accuracy: 0.1409 - loss: 2.8232
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m49s[0m 54ms/step - accuracy: 0.1409 - loss: 2.8231[32m [repeated 111x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m28s[0m 42ms/step - accuracy: 0.1414 - loss: 2.8578[32m [repeated 190x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 36ms/step - accuracy: 0.2306 - loss: 2.2469
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 36ms/step - accuracy: 0.2307 - loss: 2.2469[32m [repeated 31x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3:14[0m 166ms/step - accuracy: 0.3750 - loss: 1.8489
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 33ms/step - accuracy: 0.2812 - loss: 1.9985  
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 32ms/step - accuracy: 0.2481 - loss: 2.0612
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1575 - loss: 2.5969 
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1575 - loss: 2.5969
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m448/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 64ms/step - accuracy: 0.1834 - loss: 2.5180
[1m450/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 64ms/step - accuracy: 0.1834 - loss: 2.5179[32m [repeated 117x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m451/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 64ms/step - accuracy: 0.1834 - loss: 2.5178[32m [repeated 108x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m454/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 64ms/step - accuracy: 0.1835 - loss: 2.5177
[1m455/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 64ms/step - accuracy: 0.1835 - loss: 2.5177
[1m456/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 64ms/step - accuracy: 0.1835 - loss: 2.5176
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m533/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 38ms/step - accuracy: 0.1566 - loss: 2.6121
[1m535/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 38ms/step - accuracy: 0.1566 - loss: 2.6120
[1m536/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 38ms/step - accuracy: 0.1566 - loss: 2.6120
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 56ms/step - accuracy: 0.3906 - loss: 1.7123  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 55ms/step - accuracy: 0.3889 - loss: 1.7204
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.1573 - loss: 2.5967[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m 32/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 50ms/step - accuracy: 0.3354 - loss: 1.8370[32m [repeated 129x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m211/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m16s[0m 44ms/step - accuracy: 0.2010 - loss: 2.4275
[1m214/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m16s[0m 44ms/step - accuracy: 0.2010 - loss: 2.4275[32m [repeated 99x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 39ms/step - accuracy: 0.0069 - loss: 2.9708      
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m36s[0m 62ms/step - accuracy: 0.2912 - loss: 1.9202 - val_accuracy: 0.2549 - val_loss: 2.0281[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m57s[0m 49ms/step - accuracy: 0.1607 - loss: 2.6863 - val_accuracy: 0.1891 - val_loss: 2.4163
[36m(train_cnn_ray_tune pid=2857961)[0m Epoch 6/22[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m29s[0m 61ms/step - accuracy: 0.2872 - loss: 2.0069
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m29s[0m 61ms/step - accuracy: 0.2872 - loss: 2.0069[32m [repeated 129x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m22s[0m 41ms/step - accuracy: 0.1400 - loss: 2.8610[32m [repeated 187x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.1572 - loss: 2.5967
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.1572 - loss: 2.5967[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:05[0m 108ms/step - accuracy: 0.0000e+00 - loss: 2.8402[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m28s[0m 61ms/step - accuracy: 0.2872 - loss: 2.0068
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m28s[0m 61ms/step - accuracy: 0.2872 - loss: 2.0068
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m28s[0m 61ms/step - accuracy: 0.2872 - loss: 2.0068
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 101ms/step - accuracy: 0.3438 - loss: 1.8491
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 37ms/step - accuracy: 0.2500 - loss: 2.0612 
Trial status: 20 RUNNING
Current time: 2025-11-07 13:57:33. 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_a058a    RUNNING            3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21 │
│ trial_a058a    RUNNING            3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15 │
│ trial_a058a    RUNNING            2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26 │
│ trial_a058a    RUNNING            2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28 │
│ trial_a058a    RUNNING            2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22 │
│ trial_a058a    RUNNING            2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21 │
│ trial_a058a    RUNNING            3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24 │
│ trial_a058a    RUNNING            2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28 │
│ trial_a058a    RUNNING            2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25 │
│ trial_a058a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23 │
│ trial_a058a    RUNNING            3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23 │
│ trial_a058a    RUNNING            2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27 │
│ trial_a058a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000164705         24 │
│ trial_a058a    RUNNING            2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24 │
│ trial_a058a    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21 │
│ trial_a058a    RUNNING            3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m430/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 43ms/step - accuracy: 0.3681 - loss: 1.7063
[1m431/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 43ms/step - accuracy: 0.3681 - loss: 1.7062[32m [repeated 74x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m537/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 63ms/step - accuracy: 0.1845 - loss: 2.5151[32m [repeated 77x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m25s[0m 60ms/step - accuracy: 0.2873 - loss: 2.0055
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m25s[0m 60ms/step - accuracy: 0.2873 - loss: 2.0055
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m25s[0m 60ms/step - accuracy: 0.2873 - loss: 2.0055
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m 38/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 50ms/step - accuracy: 0.2423 - loss: 2.2349
[1m 39/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 50ms/step - accuracy: 0.2421 - loss: 2.2357
[1m 40/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 50ms/step - accuracy: 0.2420 - loss: 2.2365
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m48s[0m 41ms/step - accuracy: 0.2309 - loss: 2.2460 - val_accuracy: 0.2518 - val_loss: 2.1308
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 33ms/step - accuracy: 0.2708 - loss: 2.0270 
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 79ms/step - accuracy: 0.3047 - loss: 1.7596  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 70ms/step - accuracy: 0.3108 - loss: 1.7251
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 32ms/step - accuracy: 0.1568 - loss: 2.5962[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m 64/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 35ms/step - accuracy: 0.1571 - loss: 2.6218[32m [repeated 198x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m 50/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 51ms/step - accuracy: 0.2404 - loss: 2.2447
[1m 51/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 52ms/step - accuracy: 0.2404 - loss: 2.2453[32m [repeated 105x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m42s[0m 71ms/step - accuracy: 0.3373 - loss: 1.7705 - val_accuracy: 0.2870 - val_loss: 2.0406[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m Epoch 7/26[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m17s[0m 41ms/step - accuracy: 0.1392 - loss: 2.8630
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m17s[0m 41ms/step - accuracy: 0.1392 - loss: 2.8630[32m [repeated 139x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m  30/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 41ms/step - accuracy: 0.2798 - loss: 2.0651[32m [repeated 193x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 32ms/step - accuracy: 0.1568 - loss: 2.5961
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 32ms/step - accuracy: 0.1568 - loss: 2.5961[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 113ms/step - accuracy: 0.2812 - loss: 1.8226[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m12s[0m 48ms/step - accuracy: 0.1623 - loss: 2.6073
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m11s[0m 48ms/step - accuracy: 0.1623 - loss: 2.6073
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m11s[0m 48ms/step - accuracy: 0.1623 - loss: 2.6073
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 131ms/step - accuracy: 0.3125 - loss: 2.1932
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 67ms/step - accuracy: 0.2969 - loss: 2.2099  
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m550/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 43ms/step - accuracy: 0.3690 - loss: 1.7020
[1m552/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 43ms/step - accuracy: 0.3690 - loss: 1.7020[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m554/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 43ms/step - accuracy: 0.3690 - loss: 1.7019[32m [repeated 91x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.1624 - loss: 2.6069 
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.1624 - loss: 2.6069
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 40ms/step - accuracy: 0.1763 - loss: 2.6300[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 88/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m30s[0m 62ms/step - accuracy: 0.3715 - loss: 1.6730[32m [repeated 168x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m146/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m22s[0m 52ms/step - accuracy: 0.2448 - loss: 2.2541
[1m148/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m22s[0m 52ms/step - accuracy: 0.2448 - loss: 2.2541[32m [repeated 170x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m42s[0m 71ms/step - accuracy: 0.1850 - loss: 2.5139 - val_accuracy: 0.2117 - val_loss: 2.3344
[36m(train_cnn_ray_tune pid=2857952)[0m Epoch 8/24
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 54ms/step - accuracy: 0.1797 - loss: 2.4833  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 64ms/step - accuracy: 0.1927 - loss: 2.4506
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m12s[0m 41ms/step - accuracy: 0.1385 - loss: 2.8654
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m12s[0m 41ms/step - accuracy: 0.1385 - loss: 2.8654[32m [repeated 130x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 257/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m38s[0m 42ms/step - accuracy: 0.1517 - loss: 2.6802[32m [repeated 195x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 48ms/step - accuracy: 0.1624 - loss: 2.6066
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 48ms/step - accuracy: 0.1624 - loss: 2.6066[32m [repeated 31x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:27[0m 151ms/step - accuracy: 0.1562 - loss: 2.4795
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m165/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m21s[0m 52ms/step - accuracy: 0.2444 - loss: 2.2541
[1m166/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m21s[0m 52ms/step - accuracy: 0.2444 - loss: 2.2540
[1m167/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m21s[0m 52ms/step - accuracy: 0.2444 - loss: 2.2540
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 48ms/step - accuracy: 0.1624 - loss: 2.6065
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 48ms/step - accuracy: 0.1624 - loss: 2.6065
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 48ms/step - accuracy: 0.1624 - loss: 2.6065
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m22s[0m 31ms/step - accuracy: 0.2121 - loss: 2.2783
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 31ms/step - accuracy: 0.2121 - loss: 2.2783
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 31ms/step - accuracy: 0.2121 - loss: 2.2782[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m43s[0m 37ms/step - accuracy: 0.1567 - loss: 2.5960 - val_accuracy: 0.1732 - val_loss: 2.3893
[36m(train_cnn_ray_tune pid=2857960)[0m Epoch 8/23
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 130ms/step - accuracy: 0.2500 - loss: 1.6094
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m318/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 33ms/step - accuracy: 0.2325 - loss: 2.2292
[1m320/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 33ms/step - accuracy: 0.2325 - loss: 2.2293[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m528/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 42ms/step - accuracy: 0.2023 - loss: 2.4185[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m376/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.1651 - loss: 2.5371 
[1m378/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.1652 - loss: 2.5371
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 40ms/step - accuracy: 0.1381 - loss: 2.8673[32m [repeated 73x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 75/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 60ms/step - accuracy: 0.1964 - loss: 2.5024[32m [repeated 185x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m240/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 53ms/step - accuracy: 0.2427 - loss: 2.2535
[1m242/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 53ms/step - accuracy: 0.2427 - loss: 2.2534[32m [repeated 169x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m29s[0m 49ms/step - accuracy: 0.3691 - loss: 1.7011 - val_accuracy: 0.2222 - val_loss: 2.2050
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 43ms/step - accuracy: 0.2679 - loss: 2.0784 - val_accuracy: 0.2429 - val_loss: 2.1321
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 89ms/step - accuracy: 0.3125 - loss: 2.0167
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 39ms/step - accuracy: 0.2812 - loss: 2.0383
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 30ms/step - accuracy: 0.2137 - loss: 2.2756
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 30ms/step - accuracy: 0.2138 - loss: 2.2756[32m [repeated 111x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 30ms/step - accuracy: 0.2138 - loss: 2.2756[32m [repeated 168x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 40ms/step - accuracy: 0.1380 - loss: 2.8676
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 40ms/step - accuracy: 0.1380 - loss: 2.8676[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m256/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m12s[0m 37ms/step - accuracy: 0.1584 - loss: 2.6071
[1m257/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m11s[0m 37ms/step - accuracy: 0.1584 - loss: 2.6070
[1m258/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m11s[0m 37ms/step - accuracy: 0.1584 - loss: 2.6070
[36m(train_cnn_ray_tune pid=2857954)[0m Epoch 13/28[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m410/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 36ms/step - accuracy: 0.1588 - loss: 2.6009
[1m412/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 36ms/step - accuracy: 0.1588 - loss: 2.6008[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m422/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 53ms/step - accuracy: 0.1655 - loss: 2.6667[32m [repeated 82x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 128ms/step - accuracy: 0.2500 - loss: 2.3684
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 52ms/step - accuracy: 0.2656 - loss: 2.2995  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 55ms/step - accuracy: 0.2569 - loss: 2.3016
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m395/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 53ms/step - accuracy: 0.3176 - loss: 1.8779 
[1m396/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 53ms/step - accuracy: 0.3176 - loss: 1.8779
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 40ms/step - accuracy: 0.1376 - loss: 2.8686[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m 46/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 41ms/step - accuracy: 0.2169 - loss: 2.3727[32m [repeated 157x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m336/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 53ms/step - accuracy: 0.2407 - loss: 2.2550
[1m338/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 53ms/step - accuracy: 0.2407 - loss: 2.2551[32m [repeated 145x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 48ms/step - accuracy: 0.2022 - loss: 2.4178 - val_accuracy: 0.2276 - val_loss: 2.2861
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m52s[0m 44ms/step - accuracy: 0.1761 - loss: 2.6294 - val_accuracy: 0.2152 - val_loss: 2.3507
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:02[0m 105ms/step - accuracy: 0.0625 - loss: 3.0176
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 31ms/step - accuracy: 0.1354 - loss: 2.8028  
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m424/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 53ms/step - accuracy: 0.3170 - loss: 1.8788
[1m425/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 53ms/step - accuracy: 0.3170 - loss: 1.8789
[1m426/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 53ms/step - accuracy: 0.3169 - loss: 1.8789
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m169/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m25s[0m 60ms/step - accuracy: 0.1960 - loss: 2.5004
[1m170/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m25s[0m 60ms/step - accuracy: 0.1960 - loss: 2.5003
[1m171/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 60ms/step - accuracy: 0.1960 - loss: 2.5002
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m29s[0m 43ms/step - accuracy: 0.1575 - loss: 2.6608
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m28s[0m 43ms/step - accuracy: 0.1575 - loss: 2.6607[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m21s[0m 51ms/step - accuracy: 0.1487 - loss: 2.8071[32m [repeated 145x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 40ms/step - accuracy: 0.1375 - loss: 2.8688
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 40ms/step - accuracy: 0.1375 - loss: 2.8688[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m Epoch 7/16[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m551/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 36ms/step - accuracy: 0.1589 - loss: 2.5966
[1m553/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 36ms/step - accuracy: 0.1589 - loss: 2.5965[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m549/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 36ms/step - accuracy: 0.1589 - loss: 2.5966[32m [repeated 130x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m396/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 53ms/step - accuracy: 0.2398 - loss: 2.2564 
[1m397/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 53ms/step - accuracy: 0.2398 - loss: 2.2564
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m22s[0m 37ms/step - accuracy: 0.2314 - loss: 2.2354 - val_accuracy: 0.2487 - val_loss: 2.1259
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 104ms/step - accuracy: 0.1562 - loss: 2.2840
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 30ms/step - accuracy: 0.2031 - loss: 2.1899  
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 29ms/step - accuracy: 0.2259 - loss: 2.1880
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m487/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 53ms/step - accuracy: 0.3155 - loss: 1.8807
[1m488/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 53ms/step - accuracy: 0.3155 - loss: 1.8807
[1m489/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 53ms/step - accuracy: 0.3155 - loss: 1.8807
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 60ms/step - accuracy: 0.2880 - loss: 1.9975[32m [repeated 74x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m298/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m12s[0m 42ms/step - accuracy: 0.3729 - loss: 1.6747[32m [repeated 139x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m167/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m17s[0m 41ms/step - accuracy: 0.2145 - loss: 2.3688
[1m169/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m17s[0m 41ms/step - accuracy: 0.2144 - loss: 2.3691[32m [repeated 140x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m63s[0m 54ms/step - accuracy: 0.1627 - loss: 2.6052 - val_accuracy: 0.1937 - val_loss: 2.3837
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m542/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 54ms/step - accuracy: 0.1647 - loss: 2.6684
[1m543/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 54ms/step - accuracy: 0.1646 - loss: 2.6684
[1m544/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 54ms/step - accuracy: 0.1646 - loss: 2.6684
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m52s[0m 45ms/step - accuracy: 0.1111 - loss: 2.9532  
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 53ms/step - accuracy: 0.1146 - loss: 2.9188
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m15s[0m 51ms/step - accuracy: 0.1502 - loss: 2.8037
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m15s[0m 51ms/step - accuracy: 0.1502 - loss: 2.8036[32m [repeated 80x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 141/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 37ms/step - accuracy: 0.1803 - loss: 2.6153[32m [repeated 127x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 60ms/step - accuracy: 0.2880 - loss: 1.9972
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 60ms/step - accuracy: 0.2880 - loss: 1.9972[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 55ms/step - accuracy: 0.1167 - loss: 2.8955
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 51ms/step - accuracy: 0.1286 - loss: 2.8575 
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 55ms/step - accuracy: 0.1403 - loss: 2.7943
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  12/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.1429 - loss: 2.7837
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  14/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.1496 - loss: 2.7624
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  16/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 53ms/step - accuracy: 0.1546 - loss: 2.7471
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  18/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.1571 - loss: 2.7358 
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 99ms/step - accuracy: 0.0312 - loss: 2.8387
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 27ms/step - accuracy: 0.0712 - loss: 2.6986
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.1632 - loss: 2.7080
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.1639 - loss: 2.7053
[36m(train_cnn_ray_tune pid=2857956)[0m Epoch 14/27[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.1646 - loss: 2.7027
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.1660 - loss: 2.6978
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  31/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.1670 - loss: 2.6938
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.1677 - loss: 2.6905
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.1680 - loss: 2.6888
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.1682 - loss: 2.6874
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.1683 - loss: 2.6861
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.1684 - loss: 2.6850
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m477/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 53ms/step - accuracy: 0.2390 - loss: 2.2575
[1m478/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 53ms/step - accuracy: 0.2390 - loss: 2.2575[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m479/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 53ms/step - accuracy: 0.2390 - loss: 2.2575[32m [repeated 91x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 53ms/step - accuracy: 0.1685 - loss: 2.6823 
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.1685 - loss: 2.6813
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 53ms/step - accuracy: 0.1684 - loss: 2.6795 
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m319/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.2735 - loss: 2.0552 
[1m321/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.2735 - loss: 2.0552
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m31s[0m 53ms/step - accuracy: 0.1678 - loss: 2.5364 - val_accuracy: 0.2017 - val_loss: 2.3334[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:46[0m 143ms/step - accuracy: 0.1250 - loss: 2.9999
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 60ms/step - accuracy: 0.2882 - loss: 1.9963[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m418/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 62ms/step - accuracy: 0.3662 - loss: 1.7045[32m [repeated 130x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m319/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m16s[0m 62ms/step - accuracy: 0.1982 - loss: 2.4892
[1m320/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m16s[0m 62ms/step - accuracy: 0.1982 - loss: 2.4892[32m [repeated 150x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m423/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 62ms/step - accuracy: 0.3662 - loss: 1.7046 
[1m424/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 62ms/step - accuracy: 0.3662 - loss: 1.7046
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m52s[0m 45ms/step - accuracy: 0.1374 - loss: 2.8690 - val_accuracy: 0.1488 - val_loss: 2.5576
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:23[0m 143ms/step - accuracy: 0.3125 - loss: 2.6360
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m429/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 62ms/step - accuracy: 0.3662 - loss: 1.7046
[1m430/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 62ms/step - accuracy: 0.3662 - loss: 1.7046
[1m431/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 62ms/step - accuracy: 0.3662 - loss: 1.7047
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m18s[0m 42ms/step - accuracy: 0.1580 - loss: 2.6570
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m18s[0m 42ms/step - accuracy: 0.1580 - loss: 2.6569[32m [repeated 105x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m  91/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 35ms/step - accuracy: 0.1375 - loss: 2.8083[32m [repeated 157x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 30ms/step - accuracy: 0.2170 - loss: 2.2677
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 30ms/step - accuracy: 0.2170 - loss: 2.2677[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:07[0m 109ms/step - accuracy: 0.1250 - loss: 2.3844
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 37ms/step - accuracy: 0.1076 - loss: 2.5577  [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m Epoch 10/24[32m [repeated 3x across cluster][0m
Trial status: 20 RUNNING
Current time: 2025-11-07 13:58:03. 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_a058a    RUNNING            3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21 │
│ trial_a058a    RUNNING            3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15 │
│ trial_a058a    RUNNING            2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26 │
│ trial_a058a    RUNNING            2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28 │
│ trial_a058a    RUNNING            2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22 │
│ trial_a058a    RUNNING            2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21 │
│ trial_a058a    RUNNING            3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24 │
│ trial_a058a    RUNNING            2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28 │
│ trial_a058a    RUNNING            2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25 │
│ trial_a058a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23 │
│ trial_a058a    RUNNING            3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23 │
│ trial_a058a    RUNNING            2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27 │
│ trial_a058a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000164705         24 │
│ trial_a058a    RUNNING            2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24 │
│ trial_a058a    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21 │
│ trial_a058a    RUNNING            3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m488/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 41ms/step - accuracy: 0.3780 - loss: 1.6676
[1m489/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 41ms/step - accuracy: 0.3780 - loss: 1.6676[32m [repeated 91x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m462/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 37ms/step - accuracy: 0.2732 - loss: 2.0550[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 65ms/step - accuracy: 0.2734 - loss: 1.8342  
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 52ms/step - accuracy: 0.2760 - loss: 1.8615
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 59ms/step - accuracy: 0.3139 - loss: 1.8827 - val_accuracy: 0.2677 - val_loss: 2.0219[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m39s[0m 33ms/step - accuracy: 0.2170 - loss: 2.2677 - val_accuracy: 0.2451 - val_loss: 2.1022
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 32ms/step - accuracy: 0.2743 - loss: 1.9887 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 30ms/step - accuracy: 0.2452 - loss: 2.0402
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m5s[0m 50ms/step - accuracy: 0.1520 - loss: 2.7991[32m [repeated 31x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m415/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 60ms/step - accuracy: 0.1992 - loss: 2.4825[32m [repeated 133x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m413/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 60ms/step - accuracy: 0.1992 - loss: 2.4826
[1m414/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 60ms/step - accuracy: 0.1992 - loss: 2.4825[32m [repeated 118x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:44[0m 89ms/step - accuracy: 0.3125 - loss: 1.9011[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 226/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m34s[0m 36ms/step - accuracy: 0.1446 - loss: 2.8231
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m34s[0m 36ms/step - accuracy: 0.1447 - loss: 2.8232[32m [repeated 110x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m12s[0m 42ms/step - accuracy: 0.1581 - loss: 2.6557[32m [repeated 162x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 50ms/step - accuracy: 0.1522 - loss: 2.7987
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 50ms/step - accuracy: 0.1522 - loss: 2.7987[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.2441 - loss: 2.1722 
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.2441 - loss: 2.1723
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m436/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 59ms/step - accuracy: 0.1994 - loss: 2.4813
[1m437/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 59ms/step - accuracy: 0.1994 - loss: 2.4812
[1m438/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 59ms/step - accuracy: 0.1994 - loss: 2.4812
[36m(train_cnn_ray_tune pid=2857951)[0m Epoch 10/21[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.3160 - loss: 1.8241 
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 59ms/step - accuracy: 0.3151 - loss: 1.8580
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.3125 - loss: 1.8960
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 60ms/step - accuracy: 0.3151 - loss: 1.9015
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m457/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 60ms/step - accuracy: 0.1995 - loss: 2.4803
[1m458/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 60ms/step - accuracy: 0.1995 - loss: 2.4802[32m [repeated 124x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m321/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 34ms/step - accuracy: 0.1643 - loss: 2.5598[32m [repeated 133x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 38ms/step - accuracy: 0.2101 - loss: 2.3089  
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 40ms/step - accuracy: 0.1995 - loss: 2.3109
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 36ms/step - accuracy: 0.2442 - loss: 2.1725
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 36ms/step - accuracy: 0.2442 - loss: 2.1725
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 36ms/step - accuracy: 0.2442 - loss: 2.1725
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 59ms/step - accuracy: 0.3167 - loss: 1.9071
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  10/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 60ms/step - accuracy: 0.3185 - loss: 1.9167
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 62ms/step - accuracy: 0.3174 - loss: 1.9190
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  12/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 62ms/step - accuracy: 0.3157 - loss: 1.9225
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 62ms/step - accuracy: 0.3132 - loss: 1.9262
[1m  14/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 62ms/step - accuracy: 0.3116 - loss: 1.9283
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  15/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 63ms/step - accuracy: 0.3097 - loss: 1.9295
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  16/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 64ms/step - accuracy: 0.3087 - loss: 1.9292
[1m  17/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 66ms/step - accuracy: 0.3072 - loss: 1.9292
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  18/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 67ms/step - accuracy: 0.3057 - loss: 1.9287
[1m  19/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 66ms/step - accuracy: 0.3043 - loss: 1.9289
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 60ms/step - accuracy: 0.2387 - loss: 2.2573 - val_accuracy: 0.2488 - val_loss: 2.1360
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  20/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 66ms/step - accuracy: 0.3032 - loss: 1.9301
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 67ms/step - accuracy: 0.3025 - loss: 1.9305
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 67ms/step - accuracy: 0.3018 - loss: 1.9311
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:17[0m 67ms/step - accuracy: 0.3010 - loss: 1.9318
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:17[0m 68ms/step - accuracy: 0.3000 - loss: 1.9326
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 67ms/step - accuracy: 0.2994 - loss: 1.9328
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 67ms/step - accuracy: 0.2989 - loss: 1.9331
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 65ms/step - accuracy: 0.2986 - loss: 1.9324
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 65ms/step - accuracy: 0.2986 - loss: 1.9317
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  30/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 65ms/step - accuracy: 0.2989 - loss: 1.9308
[1m  31/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 65ms/step - accuracy: 0.2991 - loss: 1.9300
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  32/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 64ms/step - accuracy: 0.2993 - loss: 1.9293
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.2995 - loss: 1.9287
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m79s[0m 67ms/step - accuracy: 0.2882 - loss: 1.9963 - val_accuracy: 0.2816 - val_loss: 2.0249
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.2997 - loss: 1.9281
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.2999 - loss: 1.9276
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.3001 - loss: 1.9273
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 41ms/step - accuracy: 0.2735 - loss: 2.0542 - val_accuracy: 0.2575 - val_loss: 2.1289
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 64ms/step - accuracy: 0.3004 - loss: 1.9268
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 64ms/step - accuracy: 0.3008 - loss: 1.9261
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 63ms/step - accuracy: 0.3007 - loss: 1.9259
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 64ms/step - accuracy: 0.3008 - loss: 1.9257
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 64ms/step - accuracy: 0.3008 - loss: 1.9256
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.3009 - loss: 1.9252
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  44/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 64ms/step - accuracy: 0.3008 - loss: 1.9250
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  45/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.3007 - loss: 1.9249
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 42ms/step - accuracy: 0.1582 - loss: 2.6550[32m [repeated 74x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 64ms/step - accuracy: 0.3003 - loss: 1.9248
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m 61/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 54ms/step - accuracy: 0.2270 - loss: 2.2224[32m [repeated 123x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m 17/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 32ms/step - accuracy: 0.2839 - loss: 1.9964
[1m 19/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 32ms/step - accuracy: 0.2841 - loss: 1.9953[32m [repeated 73x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 64ms/step - accuracy: 0.3000 - loss: 1.9248
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 64ms/step - accuracy: 0.2998 - loss: 1.9246
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 63ms/step - accuracy: 0.2994 - loss: 1.9243
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.2991 - loss: 1.9242
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 40ms/step - accuracy: 0.3819 - loss: 1.5364  
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 38ms/step - accuracy: 0.3792 - loss: 1.5344
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.2988 - loss: 1.9242
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 110ms/step - accuracy: 0.3750 - loss: 1.5941[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.2987 - loss: 1.9240
[1m  57/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.2986 - loss: 1.9238
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  58/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.2985 - loss: 1.9235
[1m  59/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.2985 - loss: 1.9233
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  61/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.2984 - loss: 1.9228
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  62/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.2983 - loss: 1.9228
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m38s[0m 47ms/step - accuracy: 0.1626 - loss: 2.6126
[1m 333/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m38s[0m 46ms/step - accuracy: 0.1627 - loss: 2.6124[32m [repeated 104x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m22s[0m 37ms/step - accuracy: 0.1802 - loss: 2.6006[32m [repeated 123x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 42ms/step - accuracy: 0.1582 - loss: 2.6549
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 42ms/step - accuracy: 0.1582 - loss: 2.6548[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  63/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.2982 - loss: 1.9227
[1m  64/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.2981 - loss: 1.9225
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  65/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.2980 - loss: 1.9223
[1m  66/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 61ms/step - accuracy: 0.2980 - loss: 1.9221
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  67/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 61ms/step - accuracy: 0.2980 - loss: 1.9219
[1m  68/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.2981 - loss: 1.9216
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m581/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 41ms/step - accuracy: 0.3793 - loss: 1.6647
[1m582/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 41ms/step - accuracy: 0.3793 - loss: 1.6647
[1m583/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 41ms/step - accuracy: 0.3793 - loss: 1.6647
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  69/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.2981 - loss: 1.9214
[1m  71/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.2981 - loss: 1.9211
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.2981 - loss: 1.9208
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.2981 - loss: 1.9207
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.2981 - loss: 1.9207
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.2981 - loss: 1.9208
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.2981 - loss: 1.9207
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.2980 - loss: 1.9208
[36m(train_cnn_ray_tune pid=2857959)[0m Epoch 12/25[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.2979 - loss: 1.9209
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 58ms/step - accuracy: 0.2978 - loss: 1.9211
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.2978 - loss: 1.9212
[1m  86/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 58ms/step - accuracy: 0.2977 - loss: 1.9214
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  88/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 58ms/step - accuracy: 0.2976 - loss: 1.9216
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  89/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 58ms/step - accuracy: 0.2975 - loss: 1.9217
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  91/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 58ms/step - accuracy: 0.2974 - loss: 1.9219
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  93/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 58ms/step - accuracy: 0.2974 - loss: 1.9221
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  94/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 58ms/step - accuracy: 0.2973 - loss: 1.9223
[1m  95/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 58ms/step - accuracy: 0.2973 - loss: 1.9225
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m546/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 59ms/step - accuracy: 0.2002 - loss: 2.4763
[1m547/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 59ms/step - accuracy: 0.2002 - loss: 2.4763[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m460/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 34ms/step - accuracy: 0.1633 - loss: 2.5619[32m [repeated 110x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  96/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 58ms/step - accuracy: 0.2973 - loss: 1.9227
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  98/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 58ms/step - accuracy: 0.2972 - loss: 1.9231
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 58ms/step - accuracy: 0.2972 - loss: 1.9233
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 58ms/step - accuracy: 0.2972 - loss: 1.9234
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 58ms/step - accuracy: 0.2972 - loss: 1.9236
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 57ms/step - accuracy: 0.2972 - loss: 1.9239
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.2972 - loss: 1.9242
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.2972 - loss: 1.9243
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.2972 - loss: 1.9245
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.2972 - loss: 1.9246
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.2972 - loss: 1.9247
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.2972 - loss: 1.9249
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.2972 - loss: 1.9250
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m564/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 59ms/step - accuracy: 0.2003 - loss: 2.4757
[1m565/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 59ms/step - accuracy: 0.2003 - loss: 2.4756
[1m566/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 59ms/step - accuracy: 0.2003 - loss: 2.4756
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 92ms/step - accuracy: 0.2188 - loss: 2.3547
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 37ms/step - accuracy: 0.2257 - loss: 2.3179
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.2972 - loss: 1.9251
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.2972 - loss: 1.9252
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 57ms/step - accuracy: 0.2972 - loss: 1.9254 
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m40s[0m 69ms/step - accuracy: 0.3663 - loss: 1.7051 - val_accuracy: 0.2735 - val_loss: 2.1671[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 41ms/step - accuracy: 0.1584 - loss: 2.6538[32m [repeated 58x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m252/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m16s[0m 50ms/step - accuracy: 0.3123 - loss: 1.8534[32m [repeated 155x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m165/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m20s[0m 49ms/step - accuracy: 0.2352 - loss: 2.2212
[1m167/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m20s[0m 49ms/step - accuracy: 0.2352 - loss: 2.2214[32m [repeated 120x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 28ms/step - accuracy: 0.2442 - loss: 2.1921
[1m 387/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 28ms/step - accuracy: 0.2441 - loss: 2.1922
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 28ms/step - accuracy: 0.2441 - loss: 2.1922
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:53[0m 195ms/step - accuracy: 0.5312 - loss: 1.5012[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m33s[0m 46ms/step - accuracy: 0.1639 - loss: 2.6036
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m33s[0m 46ms/step - accuracy: 0.1639 - loss: 2.6036[32m [repeated 98x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m23s[0m 36ms/step - accuracy: 0.1450 - loss: 2.8339[32m [repeated 118x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 41ms/step - accuracy: 0.1584 - loss: 2.6536
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 41ms/step - accuracy: 0.1584 - loss: 2.6536[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m Epoch 9/23[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m65s[0m 56ms/step - accuracy: 0.1529 - loss: 2.7969 - val_accuracy: 0.1950 - val_loss: 2.4484
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 39ms/step - accuracy: 0.2778 - loss: 2.6387  
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m19s[0m 28ms/step - accuracy: 0.2424 - loss: 2.1953
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m19s[0m 28ms/step - accuracy: 0.2424 - loss: 2.1954
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m19s[0m 28ms/step - accuracy: 0.2423 - loss: 2.1954
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m469/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 43ms/step - accuracy: 0.1786 - loss: 2.5213
[1m471/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 43ms/step - accuracy: 0.1786 - loss: 2.5212[32m [repeated 50x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m475/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 43ms/step - accuracy: 0.1786 - loss: 2.5211[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 51ms/step - accuracy: 0.2202 - loss: 2.6996 
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 125ms/step - accuracy: 0.1875 - loss: 2.6552
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 73ms/step - accuracy: 0.2188 - loss: 2.5496  
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 38ms/step - accuracy: 0.1823 - loss: 2.3677 
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 39ms/step - accuracy: 0.1719 - loss: 2.4258
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m39s[0m 66ms/step - accuracy: 0.2004 - loss: 2.4749 - val_accuracy: 0.2100 - val_loss: 2.3253[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 41ms/step - accuracy: 0.1585 - loss: 2.6532[32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 15/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 68ms/step - accuracy: 0.2019 - loss: 2.4592[32m [repeated 186x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 16/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 67ms/step - accuracy: 0.2010 - loss: 2.4591
[1m 17/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 67ms/step - accuracy: 0.2007 - loss: 2.4578[32m [repeated 196x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m52s[0m 55ms/step - accuracy: 0.2996 - loss: 1.9345
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m52s[0m 55ms/step - accuracy: 0.2996 - loss: 1.9346
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m52s[0m 55ms/step - accuracy: 0.2996 - loss: 1.9346
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 100ms/step - accuracy: 0.1562 - loss: 2.3832[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.1444 - loss: 2.8375
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.1444 - loss: 2.8375[32m [repeated 124x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m28s[0m 46ms/step - accuracy: 0.1649 - loss: 2.5968[32m [repeated 144x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 41ms/step - accuracy: 0.1585 - loss: 2.6531
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 41ms/step - accuracy: 0.1585 - loss: 2.6531[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 44ms/step - accuracy: 0.1806 - loss: 2.5294    
[36m(train_cnn_ray_tune pid=2857943)[0m Epoch 8/26[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m47s[0m 40ms/step - accuracy: 0.2443 - loss: 2.1731 - val_accuracy: 0.2505 - val_loss: 2.0996
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m443/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 50ms/step - accuracy: 0.1647 - loss: 2.6764
[1m445/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 50ms/step - accuracy: 0.1647 - loss: 2.6764[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m583/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 43ms/step - accuracy: 0.1791 - loss: 2.5186[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1799 - loss: 2.5951 
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1799 - loss: 2.5951
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m55s[0m 47ms/step - accuracy: 0.1585 - loss: 2.6531 - val_accuracy: 0.1900 - val_loss: 2.3990
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:43[0m 88ms/step - accuracy: 0.1875 - loss: 2.1935
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 32ms/step - accuracy: 0.1875 - loss: 2.2522 
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 40ms/step - accuracy: 0.1701 - loss: 2.8751  
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 46ms/step - accuracy: 0.1667 - loss: 2.8502
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.1709 - loss: 2.7837
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 59ms/step - accuracy: 0.1704 - loss: 2.7746
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m  10/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 59ms/step - accuracy: 0.1703 - loss: 2.7648
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m  12/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.1695 - loss: 2.7452
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m  14/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.1682 - loss: 2.7314
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m  16/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.1670 - loss: 2.7172 
[1m  18/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 51ms/step - accuracy: 0.1661 - loss: 2.7046
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 37ms/step - accuracy: 0.1799 - loss: 2.5942[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m289/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 40ms/step - accuracy: 0.2116 - loss: 2.3877[32m [repeated 174x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 90/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m33s[0m 68ms/step - accuracy: 0.2063 - loss: 2.4188
[1m 91/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m33s[0m 68ms/step - accuracy: 0.2064 - loss: 2.4187[32m [repeated 136x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3:17[0m 169ms/step - accuracy: 0.1875 - loss: 2.9244[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m48s[0m 58ms/step - accuracy: 0.3016 - loss: 1.9318
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m48s[0m 58ms/step - accuracy: 0.3017 - loss: 1.9318[32m [repeated 163x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m14s[0m 37ms/step - accuracy: 0.1439 - loss: 2.8399[32m [repeated 212x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 37ms/step - accuracy: 0.1800 - loss: 2.5937
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 37ms/step - accuracy: 0.1800 - loss: 2.5936[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m29s[0m 49ms/step - accuracy: 0.1791 - loss: 2.5185 - val_accuracy: 0.2139 - val_loss: 2.3305
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 49ms/step - accuracy: 0.1823 - loss: 2.4161  
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 50ms/step - accuracy: 0.1797 - loss: 2.4302
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 177/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m34s[0m 35ms/step - accuracy: 0.1589 - loss: 2.5638
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m34s[0m 35ms/step - accuracy: 0.1589 - loss: 2.5638
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m33s[0m 34ms/step - accuracy: 0.1588 - loss: 2.5638
[36m(train_cnn_ray_tune pid=2857964)[0m Epoch 12/26[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m392/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 52ms/step - accuracy: 0.2369 - loss: 2.2231 
[1m394/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 52ms/step - accuracy: 0.2370 - loss: 2.2231
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m400/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 52ms/step - accuracy: 0.2370 - loss: 2.2231
[1m401/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 52ms/step - accuracy: 0.2370 - loss: 2.2231[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m417/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 42ms/step - accuracy: 0.3896 - loss: 1.6203[32m [repeated 146x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2388 - loss: 2.1999 
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2388 - loss: 2.1999
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m408/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 52ms/step - accuracy: 0.2371 - loss: 2.2231
[1m409/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 52ms/step - accuracy: 0.2371 - loss: 2.2231
[1m410/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 52ms/step - accuracy: 0.2371 - loss: 2.2230
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m146/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m28s[0m 66ms/step - accuracy: 0.2099 - loss: 2.4141
[1m147/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m28s[0m 66ms/step - accuracy: 0.2099 - loss: 2.4142
[1m148/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m28s[0m 66ms/step - accuracy: 0.2099 - loss: 2.4142
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 29ms/step - accuracy: 0.2384 - loss: 2.2002
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 29ms/step - accuracy: 0.2384 - loss: 2.2002
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 29ms/step - accuracy: 0.2384 - loss: 2.2003
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 37ms/step - accuracy: 0.1802 - loss: 2.5911[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m171/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m27s[0m 65ms/step - accuracy: 0.2105 - loss: 2.4135[32m [repeated 105x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m254/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m20s[0m 62ms/step - accuracy: 0.3836 - loss: 1.6693
[1m255/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m20s[0m 62ms/step - accuracy: 0.3836 - loss: 1.6694[32m [repeated 106x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:37[0m 167ms/step - accuracy: 0.1562 - loss: 2.4254
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m19s[0m 47ms/step - accuracy: 0.1664 - loss: 2.5880
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m19s[0m 47ms/step - accuracy: 0.1664 - loss: 2.5879[32m [repeated 146x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m10s[0m 38ms/step - accuracy: 0.1436 - loss: 2.8408[32m [repeated 224x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 37ms/step - accuracy: 0.1803 - loss: 2.5906
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 37ms/step - accuracy: 0.1803 - loss: 2.5906[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m473/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 53ms/step - accuracy: 0.2375 - loss: 2.2226
[1m474/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 53ms/step - accuracy: 0.2375 - loss: 2.2226
[1m475/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 53ms/step - accuracy: 0.2375 - loss: 2.2226
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m35s[0m 36ms/step - accuracy: 0.2398 - loss: 2.1693
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m35s[0m 36ms/step - accuracy: 0.2398 - loss: 2.1692
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m35s[0m 36ms/step - accuracy: 0.2399 - loss: 2.1692
Trial status: 20 RUNNING
Current time: 2025-11-07 13:58:33. 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_a058a    RUNNING            3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21 │
│ trial_a058a    RUNNING            3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15 │
│ trial_a058a    RUNNING            2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26 │
│ trial_a058a    RUNNING            2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28 │
│ trial_a058a    RUNNING            2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22 │
│ trial_a058a    RUNNING            2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21 │
│ trial_a058a    RUNNING            3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26 │
│ trial_a058a    RUNNING            3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24 │
│ trial_a058a    RUNNING            2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28 │
│ trial_a058a    RUNNING            2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25 │
│ trial_a058a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23 │
│ trial_a058a    RUNNING            3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23 │
│ trial_a058a    RUNNING            2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27 │
│ trial_a058a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000164705         24 │
│ trial_a058a    RUNNING            2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24 │
│ trial_a058a    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21 │
│ trial_a058a    RUNNING            3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m18s[0m 47ms/step - accuracy: 0.1666 - loss: 2.5872
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m18s[0m 47ms/step - accuracy: 0.1666 - loss: 2.5872
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m18s[0m 47ms/step - accuracy: 0.1666 - loss: 2.5872
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m463/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 41ms/step - accuracy: 0.2118 - loss: 2.3842
[1m464/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 41ms/step - accuracy: 0.2118 - loss: 2.3842[32m [repeated 106x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m489/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 53ms/step - accuracy: 0.2376 - loss: 2.2224[32m [repeated 219x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 42ms/step - accuracy: 0.2779 - loss: 2.0254 - val_accuracy: 0.2418 - val_loss: 2.1054
[36m(train_cnn_ray_tune pid=2857954)[0m Epoch 15/28
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 109ms/step - accuracy: 0.4375 - loss: 1.7979
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 30ms/step - accuracy: 0.2374 - loss: 2.2015[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m248/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m22s[0m 66ms/step - accuracy: 0.2111 - loss: 2.4133[32m [repeated 109x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m332/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 62ms/step - accuracy: 0.3814 - loss: 1.6710
[1m333/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 62ms/step - accuracy: 0.3814 - loss: 1.6711[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m334/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 62ms/step - accuracy: 0.3814 - loss: 1.6711
[1m335/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 62ms/step - accuracy: 0.3814 - loss: 1.6711
[1m336/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 62ms/step - accuracy: 0.3813 - loss: 1.6711
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m14s[0m 47ms/step - accuracy: 0.1670 - loss: 2.5850
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m14s[0m 47ms/step - accuracy: 0.1670 - loss: 2.5849[32m [repeated 124x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 255/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m42s[0m 46ms/step - accuracy: 0.1729 - loss: 2.5868[32m [repeated 179x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 38ms/step - accuracy: 0.1434 - loss: 2.8410
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 38ms/step - accuracy: 0.1434 - loss: 2.8410[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 77ms/step - accuracy: 0.3672 - loss: 1.7580  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 69ms/step - accuracy: 0.3455 - loss: 1.7721
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m500/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 37ms/step - accuracy: 0.1652 - loss: 2.5433
[1m503/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 37ms/step - accuracy: 0.1652 - loss: 2.5434[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 53ms/step - accuracy: 0.2384 - loss: 2.2204[32m [repeated 98x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m34s[0m 59ms/step - accuracy: 0.3132 - loss: 1.8557 - val_accuracy: 0.2413 - val_loss: 2.0604[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m Epoch 11/15[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 109ms/step - accuracy: 0.4062 - loss: 1.7527[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 343ms/step
[36m(train_cnn_ray_tune pid=2857959)[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=2857959)[0m 
[1m 9/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 24ms/step
[1m12/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m14/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 23ms/step
[1m18/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m49s[0m 42ms/step - accuracy: 0.1805 - loss: 2.5890 - val_accuracy: 0.2252 - val_loss: 2.3213
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m20/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 21ms/step
[1m23/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m26/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 63ms/step - accuracy: 0.1406 - loss: 2.7318 
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m29/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 53ms/step - accuracy: 0.1419 - loss: 2.7410
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m31/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 48ms/step - accuracy: 0.1401 - loss: 2.7454 
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m33/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m36/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 24ms/step
[1m39/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 24ms/step
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 38ms/step - accuracy: 0.1432 - loss: 2.8409[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m42/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 23ms/step
[1m46/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m49/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m330/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 65ms/step - accuracy: 0.2113 - loss: 2.4126[32m [repeated 156x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m328/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 65ms/step - accuracy: 0.2113 - loss: 2.4127
[1m329/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 65ms/step - accuracy: 0.2113 - loss: 2.4127[32m [repeated 142x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m319/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m17s[0m 65ms/step - accuracy: 0.2113 - loss: 2.4128
[1m320/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m17s[0m 65ms/step - accuracy: 0.2113 - loss: 2.4128
[1m321/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m17s[0m 65ms/step - accuracy: 0.2113 - loss: 2.4127[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m57/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m60/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 21ms/step
[1m63/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 47ms/step - accuracy: 0.1675 - loss: 2.5824 
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 47ms/step - accuracy: 0.1675 - loss: 2.5823
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 77ms/step - accuracy: 0.1250 - loss: 2.3662
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 30ms/step - accuracy: 0.1753 - loss: 2.3964
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m68/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 20ms/step
[1m72/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 20ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m75/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 20ms/step
[1m78/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 20ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m81/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 20ms/step
[1m84/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 20ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m36s[0m 60ms/step - accuracy: 0.3028 - loss: 1.9297
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m35s[0m 60ms/step - accuracy: 0.3028 - loss: 1.9297[32m [repeated 131x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m19s[0m 34ms/step - accuracy: 0.1596 - loss: 2.5551[32m [repeated 170x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.1432 - loss: 2.8409
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.1432 - loss: 2.8409[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 23ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 76ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m  4/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 24ms/step 
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m  7/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m 12/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 15/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 57ms/step - accuracy: 0.2266 - loss: 2.0865  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 63ms/step - accuracy: 0.2135 - loss: 2.1202
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m18s[0m 34ms/step - accuracy: 0.1595 - loss: 2.5553
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m18s[0m 34ms/step - accuracy: 0.1595 - loss: 2.5553
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m18s[0m 34ms/step - accuracy: 0.1595 - loss: 2.5553
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m 18/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 18ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m 21/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 18ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m 24/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 18ms/step
[1m 27/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 18ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m 29/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 19ms/step
[1m 32/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m 35/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[1m 38/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m 42/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 19ms/step
[1m 44/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m2s[0m 19ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m 47/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[1m 49/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m 51/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m2s[0m 21ms/step
[1m 53/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m2s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m 56/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m2s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m 59/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m2s[0m 21ms/step
[1m 61/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m458/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 62ms/step - accuracy: 0.3794 - loss: 1.6731
[1m460/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 62ms/step - accuracy: 0.3794 - loss: 1.6731[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m454/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 62ms/step - accuracy: 0.3795 - loss: 1.6731[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m 63/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 21ms/step
[1m 66/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m 69/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m2s[0m 21ms/step
[1m 72/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m2s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m 75/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 21ms/step
[1m 78/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m 81/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 21ms/step
[1m 85/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m 88/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 21ms/step
[1m 92/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 20ms/step
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 29ms/step - accuracy: 0.3160 - loss: 2.0279 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.3019 - loss: 2.0442
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m 96/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 20ms/step
[1m 99/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 20ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m102/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 20ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m105/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 20ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m108/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 20ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m111/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m1s[0m 20ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m114/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m1s[0m 20ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 42ms/step - accuracy: 0.1649 - loss: 2.5441 - val_accuracy: 0.1833 - val_loss: 2.3785[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m Epoch 16/27[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 62ms/step - accuracy: 0.1094 - loss: 2.7146 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 57ms/step - accuracy: 0.1181 - loss: 2.7041
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m116/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m1s[0m 20ms/step
[1m119/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m1s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 102ms/step - accuracy: 0.0938 - loss: 2.6788[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m122/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 21ms/step
[1m125/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m127/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 21ms/step
[1m129/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m132/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 21ms/step
[1m135/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m138/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 21ms/step
[1m141/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m377/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.1846 - loss: 2.4890 
[1m379/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.1846 - loss: 2.4890
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m143/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 21ms/step
[1m145/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m148/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m39s[0m 33ms/step - accuracy: 0.2365 - loss: 2.2028 - val_accuracy: 0.2575 - val_loss: 2.0808
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m151/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857959)[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=2857959)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=2857957)[0m 2025-11-07 13:52:36.476086: 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=2857957)[0m 2025-11-07 13:52:36.498690: 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=2857957)[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=2857957)[0m E0000 00:00:1762519956.528394 2859231 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=2857957)[0m E0000 00:00:1762519956.536970 2859231 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=2857957)[0m W0000 00:00:1762519956.557554 2859231 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=2857957)[0m 2025-11-07 13:52:36.563684: 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=2857957)[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=2857951)[0m 2025-11-07 13:52:39.754251: 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=2857951)[0m 2025-11-07 13:52:39.754342: 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=2857951)[0m 2025-11-07 13:52:39.754354: 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=2857951)[0m 2025-11-07 13:52:39.754360: 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=2857951)[0m 2025-11-07 13:52:39.754367: 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=2857951)[0m 2025-11-07 13:52:39.754371: 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=2857951)[0m 2025-11-07 13:52:39.754850: 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=2857951)[0m 2025-11-07 13:52:39.754900: 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=2857951)[0m 2025-11-07 13:52:39.754905: 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=2857959)[0m 
[1m155/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m157/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 21ms/step
[1m161/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m163/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 21ms/step
[1m165/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857959)[0m 
[1m168/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 21ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m4s[0m 21ms/step

Trial trial_a058a finished iteration 1 at 2025-11-07 13:58:46. Total running time: 6min 13s
╭──────────────────────────────────────╮
│ Trial trial_a058a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             370.735 │
│ time_total_s                 370.735 │
│ training_iteration                 1 │
│ val_accuracy                 0.27253 │
╰──────────────────────────────────────╯

Trial trial_a058a completed after 1 iterations at 2025-11-07 13:58:46. Total running time: 6min 13s
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m5s[0m 47ms/step - accuracy: 0.1679 - loss: 2.5800[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m412/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m11s[0m 64ms/step - accuracy: 0.2115 - loss: 2.4121[32m [repeated 187x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m157/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 55ms/step - accuracy: 0.3093 - loss: 1.8578
[1m158/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 55ms/step - accuracy: 0.3093 - loss: 1.8577[32m [repeated 186x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m31s[0m 60ms/step - accuracy: 0.3030 - loss: 1.9283
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m31s[0m 60ms/step - accuracy: 0.3030 - loss: 1.9283[32m [repeated 134x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m30s[0m 51ms/step - accuracy: 0.1844 - loss: 2.7151[32m [repeated 196x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 47ms/step - accuracy: 0.1680 - loss: 2.5797
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 47ms/step - accuracy: 0.1680 - loss: 2.5796[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m31s[0m 60ms/step - accuracy: 0.3030 - loss: 1.9283
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m31s[0m 60ms/step - accuracy: 0.3030 - loss: 1.9283
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m31s[0m 60ms/step - accuracy: 0.3030 - loss: 1.9283
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m451/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 64ms/step - accuracy: 0.2115 - loss: 2.4121
[1m452/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 64ms/step - accuracy: 0.2115 - loss: 2.4121[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m542/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 62ms/step - accuracy: 0.3787 - loss: 1.6737[32m [repeated 73x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m51s[0m 43ms/step - accuracy: 0.1431 - loss: 2.8410 - val_accuracy: 0.1539 - val_loss: 2.5392
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 39ms/step - accuracy: 0.1354 - loss: 2.7264  
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 38ms/step - accuracy: 0.1256 - loss: 2.7372
[36m(train_cnn_ray_tune pid=2857942)[0m Epoch 8/21
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:24[0m 124ms/step - accuracy: 0.1250 - loss: 2.9426
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m28s[0m 60ms/step - accuracy: 0.3029 - loss: 1.9276
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m28s[0m 60ms/step - accuracy: 0.3029 - loss: 1.9276
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m28s[0m 60ms/step - accuracy: 0.3029 - loss: 1.9275
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 47ms/step - accuracy: 0.1683 - loss: 2.5782
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 47ms/step - accuracy: 0.1683 - loss: 2.5782
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 47ms/step - accuracy: 0.1683 - loss: 2.5781
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m315/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.2939 - loss: 1.9840 
[1m317/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.2938 - loss: 1.9842
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.1585 - loss: 2.5577 
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.1585 - loss: 2.5577
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.1584 - loss: 2.5579[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m257/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 54ms/step - accuracy: 0.3118 - loss: 1.8539[32m [repeated 137x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m167/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m22s[0m 54ms/step - accuracy: 0.2531 - loss: 2.1786
[1m168/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m22s[0m 54ms/step - accuracy: 0.2531 - loss: 2.1786[32m [repeated 118x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 38ms/step - accuracy: 0.1242 - loss: 2.8548
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 38ms/step - accuracy: 0.1240 - loss: 2.8556[32m [repeated 141x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m26s[0m 29ms/step - accuracy: 0.2508 - loss: 2.1828[32m [repeated 228x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 33ms/step - accuracy: 0.1584 - loss: 2.5581
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 33ms/step - accuracy: 0.1583 - loss: 2.5581[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m236/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m12s[0m 36ms/step - accuracy: 0.1668 - loss: 2.5340
[1m238/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m12s[0m 36ms/step - accuracy: 0.1668 - loss: 2.5339
[1m240/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m12s[0m 36ms/step - accuracy: 0.1668 - loss: 2.5338
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m539/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 63ms/step - accuracy: 0.2115 - loss: 2.4128
[1m540/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 63ms/step - accuracy: 0.2115 - loss: 2.4128[32m [repeated 107x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m537/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 63ms/step - accuracy: 0.2115 - loss: 2.4127[32m [repeated 114x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 29ms/step - accuracy: 0.2494 - loss: 2.1840
[1m 301/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 29ms/step - accuracy: 0.2493 - loss: 2.1841
[1m 304/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 28ms/step - accuracy: 0.2492 - loss: 2.1842[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.2459 - loss: 2.1480 
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.2459 - loss: 2.1479
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m390/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.1663 - loss: 2.6414 
[1m392/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.1663 - loss: 2.6413
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m41s[0m 70ms/step - accuracy: 0.3785 - loss: 1.6737 - val_accuracy: 0.2764 - val_loss: 2.0657
[36m(train_cnn_ray_tune pid=2857953)[0m Epoch 10/23
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 131ms/step - accuracy: 0.3125 - loss: 1.7497
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 56ms/step - accuracy: 0.3359 - loss: 1.6604  
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 32ms/step - accuracy: 0.1581 - loss: 2.5588[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 57ms/step - accuracy: 0.3602 - loss: 1.6586[32m [repeated 128x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m282/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 50ms/step - accuracy: 0.2519 - loss: 2.1812
[1m284/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 50ms/step - accuracy: 0.2518 - loss: 2.1812[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 224/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m33s[0m 36ms/step - accuracy: 0.1240 - loss: 2.8633
[1m 225/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m33s[0m 36ms/step - accuracy: 0.1240 - loss: 2.8632[32m [repeated 144x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m19s[0m 27ms/step - accuracy: 0.2446 - loss: 2.1885[32m [repeated 174x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 32ms/step - accuracy: 0.1581 - loss: 2.5589
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 32ms/step - accuracy: 0.1581 - loss: 2.5589[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 96ms/step - accuracy: 0.1250 - loss: 2.4766
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m459/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 51ms/step - accuracy: 0.1667 - loss: 2.6403
[1m461/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 51ms/step - accuracy: 0.1667 - loss: 2.6403[32m [repeated 103x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m418/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 34ms/step - accuracy: 0.1667 - loss: 2.5312[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m16s[0m 27ms/step - accuracy: 0.2426 - loss: 2.1892
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m16s[0m 27ms/step - accuracy: 0.2426 - loss: 2.1892
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m16s[0m 27ms/step - accuracy: 0.2426 - loss: 2.1892
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m380/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 49ms/step - accuracy: 0.2509 - loss: 2.1818 
[1m381/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 49ms/step - accuracy: 0.2509 - loss: 2.1818
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m41s[0m 70ms/step - accuracy: 0.2115 - loss: 2.4132 - val_accuracy: 0.2191 - val_loss: 2.3156[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m Epoch 10/24[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 122ms/step - accuracy: 0.2188 - loss: 2.6759
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 86ms/step - accuracy: 0.1953 - loss: 2.6871  
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 35ms/step - accuracy: 0.2467 - loss: 2.1458[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m 83/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 33ms/step - accuracy: 0.2829 - loss: 1.9774[32m [repeated 111x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 13/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 63ms/step - accuracy: 0.2017 - loss: 2.5205
[1m 14/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 62ms/step - accuracy: 0.2015 - loss: 2.5186[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m66s[0m 56ms/step - accuracy: 0.1684 - loss: 2.5776 - val_accuracy: 0.2020 - val_loss: 2.3563
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 56ms/step - accuracy: 0.0625 - loss: 2.7196 
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.0938 - loss: 2.6935
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m21s[0m 36ms/step - accuracy: 0.1907 - loss: 2.5171
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m21s[0m 36ms/step - accuracy: 0.1907 - loss: 2.5171[32m [repeated 135x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m14s[0m 49ms/step - accuracy: 0.1797 - loss: 2.7168[32m [repeated 161x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 35ms/step - accuracy: 0.2468 - loss: 2.1457
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 35ms/step - accuracy: 0.2468 - loss: 2.1457[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 46ms/step - accuracy: 0.1059 - loss: 2.6735 
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:31[0m 130ms/step - accuracy: 0.0625 - loss: 2.7195[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m504/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 50ms/step - accuracy: 0.3144 - loss: 1.8490
[1m505/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 50ms/step - accuracy: 0.3144 - loss: 1.8489
[1m506/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 50ms/step - accuracy: 0.3144 - loss: 1.8489

Trial status: 19 RUNNING | 1 TERMINATED
Current time: 2025-11-07 13:59:03. Total running time: 6min 30s
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_a058a    RUNNING              3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21                                              │
│ trial_a058a    RUNNING              3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26                                              │
│ trial_a058a    RUNNING              2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21                                              │
│ trial_a058a    RUNNING              3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24                                              │
│ trial_a058a    RUNNING              2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23                                              │
│ trial_a058a    RUNNING              3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27                                              │
│ trial_a058a    RUNNING              3   adam            relu                                   16                 64                  3                 1          0.000164705         24                                              │
│ trial_a058a    RUNNING              2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24                                              │
│ trial_a058a    RUNNING              3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21                                              │
│ trial_a058a    RUNNING              3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24                                              │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25        1            370.735         0.272525 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.2148 - loss: 2.4105  
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.2016 - loss: 2.4474
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  44/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 46ms/step - accuracy: 0.1429 - loss: 2.6276
[1m  45/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 46ms/step - accuracy: 0.1433 - loss: 2.6266
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 46ms/step - accuracy: 0.1436 - loss: 2.6258
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 54/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 60ms/step - accuracy: 0.2100 - loss: 2.4544
[1m 55/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 60ms/step - accuracy: 0.2100 - loss: 2.4537
[1m 56/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 60ms/step - accuracy: 0.2100 - loss: 2.4530
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m566/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 34ms/step - accuracy: 0.1661 - loss: 2.5309
[1m568/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 34ms/step - accuracy: 0.1661 - loss: 2.5309[32m [repeated 98x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m446/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 49ms/step - accuracy: 0.2506 - loss: 2.1821[32m [repeated 122x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1703 - loss: 2.6033 
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1703 - loss: 2.6033
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 65/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 60ms/step - accuracy: 0.2099 - loss: 2.4472
[1m 66/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 59ms/step - accuracy: 0.2099 - loss: 2.4465
[1m 67/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 59ms/step - accuracy: 0.2099 - loss: 2.4459
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  86/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 45ms/step - accuracy: 0.1500 - loss: 2.5982
[1m  87/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 46ms/step - accuracy: 0.1501 - loss: 2.5979
[1m  88/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 46ms/step - accuracy: 0.1501 - loss: 2.5975
[36m(train_cnn_ray_tune pid=2857960)[0m Epoch 9/23[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 27ms/step - accuracy: 0.2405 - loss: 2.1893[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m185/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 56ms/step - accuracy: 0.3842 - loss: 1.6513[32m [repeated 122x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m102/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m28s[0m 58ms/step - accuracy: 0.2086 - loss: 2.4370
[1m103/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m27s[0m 58ms/step - accuracy: 0.2085 - loss: 2.4369[32m [repeated 117x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m81s[0m 36ms/step - accuracy: 0.1581 - loss: 2.5590 - val_accuracy: 0.1776 - val_loss: 2.3790
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m26s[0m 44ms/step - accuracy: 0.2156 - loss: 2.3489 - val_accuracy: 0.2333 - val_loss: 2.2665
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m270/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.2416 - loss: 2.1640 
[1m272/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.2417 - loss: 2.1640
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 88ms/step - accuracy: 0.1562 - loss: 2.5342
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 31ms/step - accuracy: 0.1478 - loss: 2.4862
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m23s[0m 36ms/step - accuracy: 0.1295 - loss: 2.8458
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m23s[0m 36ms/step - accuracy: 0.1295 - loss: 2.8457[32m [repeated 135x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m23s[0m 36ms/step - accuracy: 0.1295 - loss: 2.8459[32m [repeated 185x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.2404 - loss: 2.1892
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.2404 - loss: 2.1892[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:33[0m 132ms/step - accuracy: 0.2500 - loss: 2.3440
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m577/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 50ms/step - accuracy: 0.3154 - loss: 1.8471
[1m578/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 50ms/step - accuracy: 0.3154 - loss: 1.8471
[1m579/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 50ms/step - accuracy: 0.3154 - loss: 1.8471[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m47s[0m 40ms/step - accuracy: 0.2468 - loss: 2.1455 - val_accuracy: 0.2849 - val_loss: 2.0537
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:52[0m 97ms/step - accuracy: 0.1875 - loss: 2.3074
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 30ms/step - accuracy: 0.1944 - loss: 2.3538 
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m10s[0m 59ms/step - accuracy: 0.3024 - loss: 1.9239
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m10s[0m 59ms/step - accuracy: 0.3024 - loss: 1.9239
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m10s[0m 59ms/step - accuracy: 0.3024 - loss: 1.9239
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m155/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 56ms/step - accuracy: 0.3830 - loss: 1.6527
[1m156/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 56ms/step - accuracy: 0.3830 - loss: 1.6526
[1m157/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 56ms/step - accuracy: 0.3830 - loss: 1.6526
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m553/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 48ms/step - accuracy: 0.2502 - loss: 2.1821
[1m554/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 48ms/step - accuracy: 0.2502 - loss: 2.1821[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m321/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.2429 - loss: 2.1622[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 43ms/step - accuracy: 0.2170 - loss: 2.4241  
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 46ms/step - accuracy: 0.2057 - loss: 2.4761
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 59ms/step - accuracy: 0.3024 - loss: 1.9238 
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 59ms/step - accuracy: 0.3023 - loss: 1.9238[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m Epoch 12/15[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 42ms/step - accuracy: 0.1702 - loss: 2.6044[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m269/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m18s[0m 58ms/step - accuracy: 0.3872 - loss: 1.6477[32m [repeated 139x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m189/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 58ms/step - accuracy: 0.2069 - loss: 2.4309
[1m190/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 58ms/step - accuracy: 0.2069 - loss: 2.4309[32m [repeated 146x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 56ms/step - accuracy: 0.3154 - loss: 1.8470 - val_accuracy: 0.2679 - val_loss: 2.0021[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 103ms/step - accuracy: 0.1250 - loss: 2.5795
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 27ms/step - accuracy: 0.1684 - loss: 2.5228 
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 225/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m43s[0m 46ms/step - accuracy: 0.1576 - loss: 2.5757
[1m 227/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m42s[0m 46ms/step - accuracy: 0.1577 - loss: 2.5756[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m11s[0m 36ms/step - accuracy: 0.1910 - loss: 2.5177[32m [repeated 145x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 58ms/step - accuracy: 0.3022 - loss: 1.9229
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 58ms/step - accuracy: 0.3022 - loss: 1.9229[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 110ms/step - accuracy: 0.2188 - loss: 2.2962
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m428/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 35ms/step - accuracy: 0.2849 - loss: 1.9715
[1m429/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 36ms/step - accuracy: 0.2849 - loss: 1.9715[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m383/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 43ms/step - accuracy: 0.1974 - loss: 2.4527[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 116ms/step - accuracy: 0.2188 - loss: 2.3150
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 35ms/step - accuracy: 0.2500 - loss: 2.2626  
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 40ms/step - accuracy: 0.2578 - loss: 2.2408
[36m(train_cnn_ray_tune pid=2857951)[0m Epoch 12/21
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 36ms/step - accuracy: 0.1912 - loss: 2.5173[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m286/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 34ms/step - accuracy: 0.1566 - loss: 2.5453[32m [repeated 144x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m257/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m12s[0m 38ms/step - accuracy: 0.2131 - loss: 2.3505
[1m259/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m12s[0m 38ms/step - accuracy: 0.2131 - loss: 2.3504[32m [repeated 123x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 56ms/step - accuracy: 0.2501 - loss: 2.1820 - val_accuracy: 0.2535 - val_loss: 2.0957
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m13s[0m 36ms/step - accuracy: 0.1327 - loss: 2.8360
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m13s[0m 36ms/step - accuracy: 0.1327 - loss: 2.8359[32m [repeated 93x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m37s[0m 45ms/step - accuracy: 0.1612 - loss: 2.5659[32m [repeated 118x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 36ms/step - accuracy: 0.1912 - loss: 2.5173
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 36ms/step - accuracy: 0.1912 - loss: 2.5173[32m [repeated 74x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m406/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 56ms/step - accuracy: 0.3891 - loss: 1.6446 
[1m407/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 56ms/step - accuracy: 0.3891 - loss: 1.6446
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m367/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.1577 - loss: 2.5410
[1m369/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.1577 - loss: 2.5409[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m410/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 56ms/step - accuracy: 0.3892 - loss: 1.6445[32m [repeated 87x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m21s[0m 35ms/step - accuracy: 0.2448 - loss: 2.1585 - val_accuracy: 0.2522 - val_loss: 2.0646
[36m(train_cnn_ray_tune pid=2857957)[0m Epoch 19/24
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m55s[0m 47ms/step - accuracy: 0.1701 - loss: 2.6049 - val_accuracy: 0.2009 - val_loss: 2.3821
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 43ms/step - accuracy: 0.0799 - loss: 2.6133     
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 40ms/step - accuracy: 0.1148 - loss: 2.5296
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:51[0m 96ms/step - accuracy: 0.0000e+00 - loss: 2.8002[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 58ms/step - accuracy: 0.1719 - loss: 1.9976  
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 50ms/step - accuracy: 0.2064 - loss: 1.9978
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 35ms/step - accuracy: 0.1337 - loss: 2.8327[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m 74/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 44ms/step - accuracy: 0.3249 - loss: 1.8121[32m [repeated 164x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m152/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m19s[0m 44ms/step - accuracy: 0.2510 - loss: 2.1499
[1m153/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m19s[0m 44ms/step - accuracy: 0.2510 - loss: 2.1499[32m [repeated 89x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 30ms/step - accuracy: 0.3142 - loss: 1.9377 
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 33ms/step - accuracy: 0.3082 - loss: 1.9775
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:28[0m 127ms/step - accuracy: 0.3125 - loss: 2.6343
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 40ms/step - accuracy: 0.2639 - loss: 2.7405  
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 28ms/step - accuracy: 0.1628 - loss: 2.5452
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 28ms/step - accuracy: 0.1628 - loss: 2.5452[32m [repeated 94x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 28ms/step - accuracy: 0.1628 - loss: 2.5452[32m [repeated 119x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 35ms/step - accuracy: 0.1337 - loss: 2.8324
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 35ms/step - accuracy: 0.1338 - loss: 2.8324[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:53[0m 97ms/step - accuracy: 0.2500 - loss: 1.9356 
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m421/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 56ms/step - accuracy: 0.2090 - loss: 2.4203
[1m422/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 56ms/step - accuracy: 0.2090 - loss: 2.4202[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m507/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 55ms/step - accuracy: 0.3899 - loss: 1.6428[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m23s[0m 39ms/step - accuracy: 0.2850 - loss: 1.9714 - val_accuracy: 0.2524 - val_loss: 2.0652
[36m(train_cnn_ray_tune pid=2857963)[0m Epoch 6/24[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:29[0m 77ms/step - accuracy: 0.2708 - loss: 1.9157
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 63ms/step - accuracy: 0.2881 - loss: 1.8923
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.2921 - loss: 1.8999
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.2927 - loss: 1.9088
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.2941 - loss: 1.9165
[1m  10/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.2966 - loss: 1.9216
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m76s[0m 65ms/step - accuracy: 0.3021 - loss: 1.9221 - val_accuracy: 0.2549 - val_loss: 1.9991[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.2980 - loss: 1.9271
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 53ms/step - accuracy: 0.2984 - loss: 1.9430
[1m  14/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 53ms/step - accuracy: 0.2981 - loss: 1.9476
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m432/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 56ms/step - accuracy: 0.2091 - loss: 2.4199
[1m433/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 56ms/step - accuracy: 0.2091 - loss: 2.4199
[1m434/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 56ms/step - accuracy: 0.2091 - loss: 2.4198
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  15/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.2985 - loss: 1.9493
[1m  17/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.2988 - loss: 1.9499
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 47ms/step - accuracy: 0.1956 - loss: 2.4538 - val_accuracy: 0.2179 - val_loss: 2.3117
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  18/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.2990 - loss: 1.9494
[1m  19/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.2985 - loss: 1.9507
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:25[0m 124ms/step - accuracy: 0.2500 - loss: 1.8337[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  20/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.2981 - loss: 1.9516
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.2979 - loss: 1.9522
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.2977 - loss: 1.9522
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.2979 - loss: 1.9518
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.2980 - loss: 1.9509
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.2983 - loss: 1.9504
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.2983 - loss: 1.9499
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.2985 - loss: 1.9487
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.2987 - loss: 1.9483
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.2988 - loss: 1.9479
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  30/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.2988 - loss: 1.9476
[1m  31/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 61ms/step - accuracy: 0.2988 - loss: 1.9478
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  32/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 61ms/step - accuracy: 0.2986 - loss: 1.9483
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.2983 - loss: 1.9484
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.2982 - loss: 1.9485
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.2980 - loss: 1.9489
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.2979 - loss: 1.9489
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.2981 - loss: 1.9486
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.2982 - loss: 1.9482
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.2983 - loss: 1.9477
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.2985 - loss: 1.9470
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 61ms/step - accuracy: 0.2986 - loss: 1.9459
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 61ms/step - accuracy: 0.2986 - loss: 1.9455
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  44/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.2986 - loss: 1.9453
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 35ms/step - accuracy: 0.1344 - loss: 2.8299[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 61ms/step - accuracy: 0.2988 - loss: 1.9445
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 61ms/step - accuracy: 0.2990 - loss: 1.9441
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 42/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 45ms/step - accuracy: 0.1925 - loss: 2.4612[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m250/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m15s[0m 47ms/step - accuracy: 0.2504 - loss: 2.1551
[1m251/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m15s[0m 47ms/step - accuracy: 0.2504 - loss: 2.1551[32m [repeated 136x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.2991 - loss: 1.9438
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.2991 - loss: 1.9437
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:42[0m 87ms/step - accuracy: 0.1250 - loss: 2.6276
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.2018 - loss: 2.5173 
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 61ms/step - accuracy: 0.2992 - loss: 1.9433
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 61ms/step - accuracy: 0.2992 - loss: 1.9430
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 29ms/step - accuracy: 0.1620 - loss: 2.5459
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 29ms/step - accuracy: 0.1620 - loss: 2.5459[32m [repeated 131x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m38s[0m 39ms/step - accuracy: 0.1596 - loss: 2.6154[32m [repeated 160x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 35ms/step - accuracy: 0.1345 - loss: 2.8297
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 35ms/step - accuracy: 0.1345 - loss: 2.8296[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 61ms/step - accuracy: 0.2993 - loss: 1.9425
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 61ms/step - accuracy: 0.2994 - loss: 1.9421
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.2995 - loss: 1.9418
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.2996 - loss: 1.9414
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  57/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.2997 - loss: 1.9409
[1m  58/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.2999 - loss: 1.9404
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m267/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2338 - loss: 2.1650 
[1m269/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2339 - loss: 2.1649
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  59/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.3000 - loss: 1.9398
[1m  60/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.3001 - loss: 1.9393
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.1619 - loss: 2.5460 
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.1619 - loss: 2.5460
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  61/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.3002 - loss: 1.9387
[1m  62/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.3003 - loss: 1.9383
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  63/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.3004 - loss: 1.9378
[1m  64/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.3005 - loss: 1.9373
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  65/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.3006 - loss: 1.9369
[1m  66/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.3007 - loss: 1.9364
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  68/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.3010 - loss: 1.9354
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  69/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.3011 - loss: 1.9349
[1m  70/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.3012 - loss: 1.9345
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  71/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.3013 - loss: 1.9341
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 61ms/step - accuracy: 0.3014 - loss: 1.9337
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 61ms/step - accuracy: 0.3015 - loss: 1.9332
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 61ms/step - accuracy: 0.3016 - loss: 1.9328
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 61ms/step - accuracy: 0.3018 - loss: 1.9324
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 61ms/step - accuracy: 0.3018 - loss: 1.9320
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 61ms/step - accuracy: 0.3019 - loss: 1.9316
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 61ms/step - accuracy: 0.3021 - loss: 1.9308
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 61ms/step - accuracy: 0.3022 - loss: 1.9304
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m27s[0m 29ms/step - accuracy: 0.2397 - loss: 2.1844
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m27s[0m 29ms/step - accuracy: 0.2397 - loss: 2.1843
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m27s[0m 29ms/step - accuracy: 0.2397 - loss: 2.1841
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.3024 - loss: 1.9296
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.3025 - loss: 1.9293
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.3026 - loss: 1.9290
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 34ms/step - accuracy: 0.1510 - loss: 2.5448 
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 32ms/step - accuracy: 0.1478 - loss: 2.5322
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.3027 - loss: 1.9286
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m509/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 56ms/step - accuracy: 0.2096 - loss: 2.4176
[1m510/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 56ms/step - accuracy: 0.2096 - loss: 2.4175[32m [repeated 92x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m316/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2354 - loss: 2.1631[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m Epoch 18/27[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  87/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.3030 - loss: 1.9279
[1m  88/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.3031 - loss: 1.9275
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  90/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.3034 - loss: 1.9268
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  92/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.3036 - loss: 1.9261
[1m  93/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.3037 - loss: 1.9258
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m47s[0m 40ms/step - accuracy: 0.1914 - loss: 2.5170 - val_accuracy: 0.2165 - val_loss: 2.2857
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  95/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.3038 - loss: 1.9251
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  97/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.3040 - loss: 1.9244
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m538/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 55ms/step - accuracy: 0.3901 - loss: 1.6423
[1m539/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 55ms/step - accuracy: 0.3901 - loss: 1.6423
[1m540/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 55ms/step - accuracy: 0.3901 - loss: 1.6423
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3042 - loss: 1.9237
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 58ms/step - accuracy: 0.3043 - loss: 1.9229
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m22s[0m 37ms/step - accuracy: 0.1592 - loss: 2.5344 - val_accuracy: 0.1804 - val_loss: 2.3751
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 58ms/step - accuracy: 0.3044 - loss: 1.9222
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 58ms/step - accuracy: 0.3046 - loss: 1.9216
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 102ms/step - accuracy: 0.1875 - loss: 2.5170[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.3047 - loss: 1.9211
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.3048 - loss: 1.9205
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.3048 - loss: 1.9202
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.3048 - loss: 1.9200
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.3050 - loss: 1.9195
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 57ms/step - accuracy: 0.3051 - loss: 1.9190 
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 42ms/step - accuracy: 0.2190 - loss: 2.3364 - val_accuracy: 0.2292 - val_loss: 2.2584
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 30ms/step - accuracy: 0.2465 - loss: 2.2300 [32m [repeated 42x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m295/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.2878 - loss: 1.9796 [32m [repeated 111x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m287/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m13s[0m 46ms/step - accuracy: 0.3330 - loss: 1.8009
[1m288/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m13s[0m 46ms/step - accuracy: 0.3331 - loss: 1.8009[32m [repeated 109x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 28ms/step - accuracy: 0.2402 - loss: 2.1781
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 28ms/step - accuracy: 0.2402 - loss: 2.1781
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 28ms/step - accuracy: 0.2402 - loss: 2.1780
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 148/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 55ms/step - accuracy: 0.3057 - loss: 1.9159
[1m 150/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 55ms/step - accuracy: 0.3057 - loss: 1.9158[32m [repeated 117x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m42s[0m 45ms/step - accuracy: 0.1858 - loss: 2.6851[32m [repeated 150x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 29ms/step - accuracy: 0.1612 - loss: 2.5463
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 29ms/step - accuracy: 0.1612 - loss: 2.5463[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m575/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 55ms/step - accuracy: 0.2101 - loss: 2.4155
[1m576/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 55ms/step - accuracy: 0.2101 - loss: 2.4155
[1m577/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 55ms/step - accuracy: 0.2101 - loss: 2.4154
Trial status: 19 RUNNING | 1 TERMINATED
Current time: 2025-11-07 13:59:33. Total running time: 7min 0s
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_a058a    RUNNING              3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21                                              │
│ trial_a058a    RUNNING              3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26                                              │
│ trial_a058a    RUNNING              2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21                                              │
│ trial_a058a    RUNNING              3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24                                              │
│ trial_a058a    RUNNING              2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23                                              │
│ trial_a058a    RUNNING              3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27                                              │
│ trial_a058a    RUNNING              3   adam            relu                                   16                 64                  3                 1          0.000164705         24                                              │
│ trial_a058a    RUNNING              2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24                                              │
│ trial_a058a    RUNNING              3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21                                              │
│ trial_a058a    RUNNING              3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24                                              │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25        1            370.735         0.272525 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m369/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 34ms/step - accuracy: 0.2881 - loss: 1.9757
[1m371/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 34ms/step - accuracy: 0.2881 - loss: 1.9757[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m535/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 47ms/step - accuracy: 0.1683 - loss: 2.6434[32m [repeated 93x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m Epoch 11/23[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m350/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m10s[0m 46ms/step - accuracy: 0.3337 - loss: 1.8016
[1m351/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 46ms/step - accuracy: 0.3337 - loss: 1.8017
[1m352/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 46ms/step - accuracy: 0.3337 - loss: 1.8017
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 114ms/step - accuracy: 0.3750 - loss: 1.8120[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m46s[0m 40ms/step - accuracy: 0.1349 - loss: 2.8281 - val_accuracy: 0.1532 - val_loss: 2.5326
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 31ms/step - accuracy: 0.1701 - loss: 2.7863  
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m37s[0m 63ms/step - accuracy: 0.3903 - loss: 1.6418 - val_accuracy: 0.2429 - val_loss: 2.2711
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.2588 - loss: 2.0997[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m256/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m10s[0m 31ms/step - accuracy: 0.1620 - loss: 2.5081[32m [repeated 136x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 68/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 53ms/step - accuracy: 0.3865 - loss: 1.6573
[1m 69/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 53ms/step - accuracy: 0.3866 - loss: 1.6567[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m36s[0m 45ms/step - accuracy: 0.1846 - loss: 2.6814
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m36s[0m 45ms/step - accuracy: 0.1845 - loss: 2.6814
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m36s[0m 44ms/step - accuracy: 0.1845 - loss: 2.6814
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m37s[0m 63ms/step - accuracy: 0.2101 - loss: 2.4152 - val_accuracy: 0.2189 - val_loss: 2.2980
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m48s[0m 52ms/step - accuracy: 0.3057 - loss: 1.9144
[1m 253/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m48s[0m 52ms/step - accuracy: 0.3057 - loss: 1.9144[32m [repeated 123x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 35ms/step - accuracy: 0.1748 - loss: 2.7710[32m [repeated 182x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 29ms/step - accuracy: 0.1606 - loss: 2.5459
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 29ms/step - accuracy: 0.1606 - loss: 2.5459[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m356/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 40ms/step - accuracy: 0.1910 - loss: 2.4498
[1m358/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 40ms/step - accuracy: 0.1910 - loss: 2.4498[32m [repeated 105x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m455/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 46ms/step - accuracy: 0.3340 - loss: 1.8036[32m [repeated 106x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m Epoch 20/24[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m52s[0m 90ms/step - accuracy: 0.1875 - loss: 2.3912[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1690 - loss: 2.5465 
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1690 - loss: 2.5465
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m38s[0m 32ms/step - accuracy: 0.1606 - loss: 2.5459 - val_accuracy: 0.1717 - val_loss: 2.3832
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m294/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.2252 - loss: 2.3021 
[1m296/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.2252 - loss: 2.3021
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 30ms/step - accuracy: 0.1007 - loss: 2.7036  
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 28ms/step - accuracy: 0.1304 - loss: 2.6502
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1691 - loss: 2.5463[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 63ms/step - accuracy: 0.3047 - loss: 2.2889[32m [repeated 79x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m172/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m21s[0m 51ms/step - accuracy: 0.3932 - loss: 1.6277
[1m173/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m21s[0m 51ms/step - accuracy: 0.3932 - loss: 1.6275[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m31s[0m 54ms/step - accuracy: 0.1685 - loss: 2.6410 - val_accuracy: 0.2107 - val_loss: 2.3857[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m32s[0m 34ms/step - accuracy: 0.1643 - loss: 2.7711
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m32s[0m 34ms/step - accuracy: 0.1642 - loss: 2.7712[32m [repeated 151x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m32s[0m 34ms/step - accuracy: 0.1644 - loss: 2.7711[32m [repeated 128x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 32ms/step - accuracy: 0.2590 - loss: 2.0988
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 32ms/step - accuracy: 0.2590 - loss: 2.0988[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m431/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 31ms/step - accuracy: 0.1637 - loss: 2.5090
[1m432/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 31ms/step - accuracy: 0.1637 - loss: 2.5090
[1m434/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 31ms/step - accuracy: 0.1637 - loss: 2.5090
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m567/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 45ms/step - accuracy: 0.3339 - loss: 1.8054
[1m569/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 45ms/step - accuracy: 0.3339 - loss: 1.8054[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m488/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 31ms/step - accuracy: 0.1640 - loss: 2.5095[32m [repeated 122x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m Epoch 18/28[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m229/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 52ms/step - accuracy: 0.3952 - loss: 1.6219
[1m230/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 52ms/step - accuracy: 0.3953 - loss: 1.6218
[1m231/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 52ms/step - accuracy: 0.3953 - loss: 1.6217
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 42ms/step - accuracy: 0.1697 - loss: 2.5448
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 42ms/step - accuracy: 0.1697 - loss: 2.5448
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 42ms/step - accuracy: 0.1697 - loss: 2.5448
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 111ms/step - accuracy: 0.3125 - loss: 1.8640[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m235/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 52ms/step - accuracy: 0.3954 - loss: 1.6215
[1m236/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 52ms/step - accuracy: 0.3955 - loss: 1.6215
[1m237/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 52ms/step - accuracy: 0.3955 - loss: 1.6214
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 27ms/step - accuracy: 0.2388 - loss: 2.1686[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m 17/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 50ms/step - accuracy: 0.2573 - loss: 2.0515[32m [repeated 117x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 90/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m29s[0m 59ms/step - accuracy: 0.2371 - loss: 2.3439
[1m 91/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m29s[0m 59ms/step - accuracy: 0.2369 - loss: 2.3444[32m [repeated 113x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m31s[0m 53ms/step - accuracy: 0.2512 - loss: 2.1519 - val_accuracy: 0.2718 - val_loss: 2.0749[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m38s[0m 53ms/step - accuracy: 0.3055 - loss: 1.9096
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m38s[0m 53ms/step - accuracy: 0.3055 - loss: 1.9096[32m [repeated 106x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m28s[0m 35ms/step - accuracy: 0.1586 - loss: 2.7775[32m [repeated 161x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 43ms/step - accuracy: 0.1701 - loss: 2.5440
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 43ms/step - accuracy: 0.1701 - loss: 2.5440[32m [repeated 58x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m541/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 45ms/step - accuracy: 0.3339 - loss: 1.8050
[1m542/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 45ms/step - accuracy: 0.3339 - loss: 1.8050
[1m543/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 45ms/step - accuracy: 0.3339 - loss: 1.8050
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 56ms/step - accuracy: 0.2656 - loss: 1.7889  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 54ms/step - accuracy: 0.2951 - loss: 1.7629
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m337/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 30ms/step - accuracy: 0.2485 - loss: 2.1352
[1m340/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 30ms/step - accuracy: 0.2485 - loss: 2.1350[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m503/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 35ms/step - accuracy: 0.2251 - loss: 2.3008[32m [repeated 103x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m Epoch 13/15[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 43ms/step - accuracy: 0.1705 - loss: 2.5431
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 43ms/step - accuracy: 0.1705 - loss: 2.5431
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 43ms/step - accuracy: 0.1706 - loss: 2.5431
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 119ms/step - accuracy: 0.2500 - loss: 1.7704[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:17[0m 134ms/step - accuracy: 0.0938 - loss: 2.7753
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 46ms/step - accuracy: 0.1233 - loss: 2.6354  
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m327/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 53ms/step - accuracy: 0.3973 - loss: 1.6190
[1m328/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 53ms/step - accuracy: 0.3973 - loss: 1.6190
[1m329/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 53ms/step - accuracy: 0.3973 - loss: 1.6190
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m43s[0m 37ms/step - accuracy: 0.2591 - loss: 2.0981 - val_accuracy: 0.2842 - val_loss: 2.0127
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 41ms/step - accuracy: 0.2057 - loss: 2.1544 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 37ms/step - accuracy: 0.2111 - loss: 2.1693
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 43ms/step - accuracy: 0.1708 - loss: 2.5425[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m177/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m23s[0m 59ms/step - accuracy: 0.2287 - loss: 2.3602[32m [repeated 163x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m 48/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 33ms/step - accuracy: 0.1601 - loss: 2.5356
[1m 50/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 33ms/step - accuracy: 0.1599 - loss: 2.5355[32m [repeated 124x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m21s[0m 36ms/step - accuracy: 0.1641 - loss: 2.5106 - val_accuracy: 0.1900 - val_loss: 2.3701[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m24s[0m 30ms/step - accuracy: 0.1655 - loss: 2.5347
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m24s[0m 30ms/step - accuracy: 0.1655 - loss: 2.5347[32m [repeated 108x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m23s[0m 35ms/step - accuracy: 0.1557 - loss: 2.7818[32m [repeated 151x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 27ms/step - accuracy: 0.2385 - loss: 2.1669
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 27ms/step - accuracy: 0.2385 - loss: 2.1669[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m509/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 30ms/step - accuracy: 0.2484 - loss: 2.1300
[1m511/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 30ms/step - accuracy: 0.2484 - loss: 2.1300[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m300/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.2928 - loss: 1.9265[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m Epoch 15/26[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m31s[0m 53ms/step - accuracy: 0.3057 - loss: 1.9051
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m31s[0m 53ms/step - accuracy: 0.3057 - loss: 1.9050
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m31s[0m 53ms/step - accuracy: 0.3057 - loss: 1.9050
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:43[0m 177ms/step - accuracy: 0.1562 - loss: 2.5594
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:51[0m 96ms/step - accuracy: 0.1875 - loss: 2.2041
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 58ms/step - accuracy: 0.1875 - loss: 2.1604
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m196/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 59ms/step - accuracy: 0.2278 - loss: 2.3614
[1m197/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 59ms/step - accuracy: 0.2278 - loss: 2.3615
[1m198/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 59ms/step - accuracy: 0.2278 - loss: 2.3616
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 84ms/step - accuracy: 0.1562 - loss: 2.5663
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m242/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m19s[0m 58ms/step - accuracy: 0.2258 - loss: 2.3649
[1m243/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m19s[0m 58ms/step - accuracy: 0.2258 - loss: 2.3649
[1m244/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m19s[0m 58ms/step - accuracy: 0.2258 - loss: 2.3650
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.1606 - loss: 2.6002[32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m219/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 50ms/step - accuracy: 0.2633 - loss: 2.1015[32m [repeated 181x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m263/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m18s[0m 59ms/step - accuracy: 0.2250 - loss: 2.3662
[1m264/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m18s[0m 59ms/step - accuracy: 0.2249 - loss: 2.3662[32m [repeated 155x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 41ms/step - accuracy: 0.2251 - loss: 2.3009 - val_accuracy: 0.2431 - val_loss: 2.2419[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m18s[0m 35ms/step - accuracy: 0.1538 - loss: 2.7829
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m18s[0m 35ms/step - accuracy: 0.1538 - loss: 2.7829[32m [repeated 128x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m28s[0m 53ms/step - accuracy: 0.3059 - loss: 1.9029[32m [repeated 142x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.1606 - loss: 2.6001
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.1606 - loss: 2.6001[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m28s[0m 53ms/step - accuracy: 0.3059 - loss: 1.9027
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m28s[0m 53ms/step - accuracy: 0.3059 - loss: 1.9027
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m28s[0m 53ms/step - accuracy: 0.3059 - loss: 1.9027
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m36s[0m 31ms/step - accuracy: 0.2384 - loss: 2.1664 - val_accuracy: 0.2751 - val_loss: 2.0337
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m374/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 47ms/step - accuracy: 0.1785 - loss: 2.5898 
[1m375/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 47ms/step - accuracy: 0.1785 - loss: 2.5898
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:59[0m 102ms/step - accuracy: 0.1875 - loss: 1.8683
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 25ms/step - accuracy: 0.2326 - loss: 1.9813  
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 48ms/step - accuracy: 0.1836 - loss: 2.4881 
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m484/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 54ms/step - accuracy: 0.3987 - loss: 1.6150
[1m485/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 54ms/step - accuracy: 0.3987 - loss: 1.6150[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m444/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 35ms/step - accuracy: 0.2936 - loss: 1.9241[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m Epoch 21/24[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 94ms/step - accuracy: 0.2188 - loss: 2.1851
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 39ms/step - accuracy: 0.1610 - loss: 2.5987[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m 90/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m14s[0m 30ms/step - accuracy: 0.2448 - loss: 2.1003[32m [repeated 181x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m349/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 59ms/step - accuracy: 0.2228 - loss: 2.3691
[1m350/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 59ms/step - accuracy: 0.2227 - loss: 2.3691[32m [repeated 129x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m20s[0m 35ms/step - accuracy: 0.2482 - loss: 2.1293 - val_accuracy: 0.2544 - val_loss: 2.0538
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11:25:24[0m 35s/step - accuracy: 0.3125 - loss: 2.5164
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 36ms/step - accuracy: 0.2778 - loss: 2.5881    
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  92/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 46ms/step - accuracy: 0.2063 - loss: 2.4681
[1m  93/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 46ms/step - accuracy: 0.2061 - loss: 2.4685[32m [repeated 137x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m14s[0m 35ms/step - accuracy: 0.1526 - loss: 2.7839[32m [repeated 206x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 39ms/step - accuracy: 0.1610 - loss: 2.5986
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 39ms/step - accuracy: 0.1610 - loss: 2.5986[32m [repeated 17x across cluster][0m
Trial status: 19 RUNNING | 1 TERMINATED
Current time: 2025-11-07 14:00:03. Total running time: 7min 30s
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_a058a    RUNNING              3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21                                              │
│ trial_a058a    RUNNING              3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26                                              │
│ trial_a058a    RUNNING              2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21                                              │
│ trial_a058a    RUNNING              3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24                                              │
│ trial_a058a    RUNNING              2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23                                              │
│ trial_a058a    RUNNING              3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27                                              │
│ trial_a058a    RUNNING              3   adam            relu                                   16                 64                  3                 1          0.000164705         24                                              │
│ trial_a058a    RUNNING              2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24                                              │
│ trial_a058a    RUNNING              3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21                                              │
│ trial_a058a    RUNNING              3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24                                              │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25        1            370.735         0.272525 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m57s[0m 48ms/step - accuracy: 0.1708 - loss: 2.5424 - val_accuracy: 0.2142 - val_loss: 2.3538
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m288/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.1652 - loss: 2.5156 
[1m289/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.1652 - loss: 2.5155
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:56[0m 100ms/step - accuracy: 0.1875 - loss: 2.5728
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 57ms/step - accuracy: 0.1719 - loss: 2.5454 
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m568/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 55ms/step - accuracy: 0.3995 - loss: 1.6129
[1m569/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 55ms/step - accuracy: 0.3995 - loss: 1.6129[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m419/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 34ms/step - accuracy: 0.1654 - loss: 2.5117[32m [repeated 102x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 46ms/step - accuracy: 0.2025 - loss: 2.4816
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 46ms/step - accuracy: 0.2024 - loss: 2.4818
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 47ms/step - accuracy: 0.2023 - loss: 2.4820
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m415/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 59ms/step - accuracy: 0.2219 - loss: 2.3698 
[1m416/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 59ms/step - accuracy: 0.2218 - loss: 2.3698
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.1627 - loss: 2.5302 
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.1627 - loss: 2.5302
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m23s[0m 40ms/step - accuracy: 0.2940 - loss: 1.9223 - val_accuracy: 0.2653 - val_loss: 2.0342
[36m(train_cnn_ray_tune pid=2857954)[0m Epoch 19/28
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 100ms/step - accuracy: 0.3438 - loss: 1.6366
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 31ms/step - accuracy: 0.3021 - loss: 1.8268 
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1518 - loss: 2.7847[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m333/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 44ms/step - accuracy: 0.1980 - loss: 2.4315[32m [repeated 138x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m249/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m10s[0m 31ms/step - accuracy: 0.2448 - loss: 2.1126
[1m252/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m10s[0m 31ms/step - accuracy: 0.2448 - loss: 2.1127[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m446/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 58ms/step - accuracy: 0.2216 - loss: 2.3699
[1m447/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 58ms/step - accuracy: 0.2216 - loss: 2.3699
[1m448/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 58ms/step - accuracy: 0.2216 - loss: 2.3699
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m43s[0m 45ms/step - accuracy: 0.1960 - loss: 2.4951
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m43s[0m 45ms/step - accuracy: 0.1958 - loss: 2.4954[32m [repeated 143x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m19s[0m 54ms/step - accuracy: 0.3071 - loss: 1.8974[32m [repeated 224x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.1625 - loss: 2.5301
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.1625 - loss: 2.5301[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 114ms/step - accuracy: 0.3750 - loss: 1.6396
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m467/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 50ms/step - accuracy: 0.2615 - loss: 2.1062
[1m468/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 50ms/step - accuracy: 0.2615 - loss: 2.1063[32m [repeated 97x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m478/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 58ms/step - accuracy: 0.2214 - loss: 2.3698[32m [repeated 116x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 45ms/step - accuracy: 0.3490 - loss: 1.6792  
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 48ms/step - accuracy: 0.3500 - loss: 1.6460
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m51s[0m 44ms/step - accuracy: 0.1613 - loss: 2.5977 - val_accuracy: 0.1917 - val_loss: 2.3749
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m385/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.3296 - loss: 1.7943 
[1m387/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.3296 - loss: 1.7944
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 38ms/step - accuracy: 0.1354 - loss: 2.6496  
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m39s[0m 45ms/step - accuracy: 0.1924 - loss: 2.5017
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m39s[0m 45ms/step - accuracy: 0.1923 - loss: 2.5018
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m39s[0m 45ms/step - accuracy: 0.1923 - loss: 2.5018
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m36s[0m 62ms/step - accuracy: 0.3996 - loss: 1.6126 - val_accuracy: 0.2468 - val_loss: 2.3007
[36m(train_cnn_ray_tune pid=2857961)[0m Epoch 9/22[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 36ms/step - accuracy: 0.1510 - loss: 2.7855[32m [repeated 102x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m156/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m13s[0m 33ms/step - accuracy: 0.3087 - loss: 1.8935[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 50/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 56ms/step - accuracy: 0.3916 - loss: 1.6114
[1m 51/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 57ms/step - accuracy: 0.3919 - loss: 1.6113[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m158/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m13s[0m 33ms/step - accuracy: 0.3087 - loss: 1.8937
[1m160/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m13s[0m 32ms/step - accuracy: 0.3086 - loss: 1.8938
[1m161/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m13s[0m 33ms/step - accuracy: 0.3086 - loss: 1.8939
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m22s[0m 38ms/step - accuracy: 0.1654 - loss: 2.5085 - val_accuracy: 0.1787 - val_loss: 2.3659
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m519/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 50ms/step - accuracy: 0.2615 - loss: 2.1065
[1m520/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 50ms/step - accuracy: 0.2615 - loss: 2.1065
[1m521/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 50ms/step - accuracy: 0.2615 - loss: 2.1065
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m14s[0m 54ms/step - accuracy: 0.3077 - loss: 1.8947
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m14s[0m 54ms/step - accuracy: 0.3077 - loss: 1.8946[32m [repeated 120x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m38s[0m 45ms/step - accuracy: 0.1916 - loss: 2.5033[32m [repeated 140x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 36ms/step - accuracy: 0.1509 - loss: 2.7856
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 36ms/step - accuracy: 0.1509 - loss: 2.7856[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m545/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 59ms/step - accuracy: 0.2212 - loss: 2.3693
[1m546/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 59ms/step - accuracy: 0.2212 - loss: 2.3692
[1m547/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 59ms/step - accuracy: 0.2212 - loss: 2.3692
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:25[0m 147ms/step - accuracy: 0.1250 - loss: 2.7330[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m567/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 50ms/step - accuracy: 0.2615 - loss: 2.1069
[1m569/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 50ms/step - accuracy: 0.2614 - loss: 2.1069[32m [repeated 130x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m486/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 39ms/step - accuracy: 0.2320 - loss: 2.2959[32m [repeated 165x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 53ms/step - accuracy: 0.1328 - loss: 2.6264  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 56ms/step - accuracy: 0.1337 - loss: 2.5683
[36m(train_cnn_ray_tune pid=2857955)[0m Epoch 14/24[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 36ms/step - accuracy: 0.1504 - loss: 2.7861[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m136/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 35ms/step - accuracy: 0.1659 - loss: 2.5010[32m [repeated 108x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m129/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 35ms/step - accuracy: 0.1656 - loss: 2.5013
[1m131/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 35ms/step - accuracy: 0.1657 - loss: 2.5013[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 58/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 57ms/step - accuracy: 0.3943 - loss: 1.6108
[1m 59/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 57ms/step - accuracy: 0.3947 - loss: 1.6106
[1m 60/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 57ms/step - accuracy: 0.3950 - loss: 1.6104
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 55ms/step - accuracy: 0.1772 - loss: 2.5940 - val_accuracy: 0.2091 - val_loss: 2.3855
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m32s[0m 45ms/step - accuracy: 0.1901 - loss: 2.5051
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m32s[0m 45ms/step - accuracy: 0.1901 - loss: 2.5051[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m25s[0m 35ms/step - accuracy: 0.2047 - loss: 2.4915[32m [repeated 192x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 54ms/step - accuracy: 0.3080 - loss: 1.8924
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 54ms/step - accuracy: 0.3081 - loss: 1.8924[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 57ms/step - accuracy: 0.2614 - loss: 2.1071 - val_accuracy: 0.2642 - val_loss: 2.0738
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 111ms/step - accuracy: 0.3438 - loss: 2.0335
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 52ms/step - accuracy: 0.3125 - loss: 2.1034  
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m374/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 33ms/step - accuracy: 0.3079 - loss: 1.8981
[1m376/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 33ms/step - accuracy: 0.3078 - loss: 1.8981[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m356/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 33ms/step - accuracy: 0.3079 - loss: 1.8981[32m [repeated 84x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 96ms/step - accuracy: 0.2812 - loss: 1.9859
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2637 - loss: 2.0834 
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2637 - loss: 2.0834
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m39s[0m 34ms/step - accuracy: 0.1617 - loss: 2.5290 - val_accuracy: 0.1778 - val_loss: 2.3729
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m276/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1655 - loss: 2.5040 
[1m278/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1655 - loss: 2.5040
[36m(train_cnn_ray_tune pid=2857958)[0m Epoch 14/15[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 28ms/step - accuracy: 0.2358 - loss: 2.1358[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 39/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 44ms/step - accuracy: 0.1904 - loss: 2.4301[32m [repeated 109x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 38/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 61ms/step - accuracy: 0.2348 - loss: 2.3195
[1m 39/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 61ms/step - accuracy: 0.2346 - loss: 2.3203[32m [repeated 122x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 28ms/step - accuracy: 0.2358 - loss: 2.1359
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 28ms/step - accuracy: 0.2358 - loss: 2.1359
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 28ms/step - accuracy: 0.2358 - loss: 2.1359
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 33ms/step - accuracy: 0.1507 - loss: 2.5280
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 32ms/step - accuracy: 0.1511 - loss: 2.5272[32m [repeated 97x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 38ms/step - accuracy: 0.2160 - loss: 2.5776[32m [repeated 156x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 28ms/step - accuracy: 0.2358 - loss: 2.1361
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 28ms/step - accuracy: 0.2358 - loss: 2.1361[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 58/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 62ms/step - accuracy: 0.2311 - loss: 2.3303
[1m 59/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 62ms/step - accuracy: 0.2308 - loss: 2.3309
[1m 60/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 62ms/step - accuracy: 0.2306 - loss: 2.3315
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 56ms/step - accuracy: 0.3310 - loss: 1.7929 - val_accuracy: 0.2553 - val_loss: 2.0877[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:29[0m 76ms/step - accuracy: 0.1875 - loss: 2.4811
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 36ms/step - accuracy: 0.2257 - loss: 2.5044 [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m361/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 33ms/step - accuracy: 0.1658 - loss: 2.5032
[1m363/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 33ms/step - accuracy: 0.1658 - loss: 2.5032[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m514/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 34ms/step - accuracy: 0.3072 - loss: 1.8984[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 126ms/step - accuracy: 0.1875 - loss: 2.2328[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.2360 - loss: 2.1350 
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.2360 - loss: 2.1351
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m24s[0m 44ms/step - accuracy: 0.1888 - loss: 2.5046
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m24s[0m 44ms/step - accuracy: 0.1888 - loss: 2.5046
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m24s[0m 44ms/step - accuracy: 0.1888 - loss: 2.5046
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m47s[0m 40ms/step - accuracy: 0.1503 - loss: 2.7861 - val_accuracy: 0.1623 - val_loss: 2.5175[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m Epoch 10/21
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 33ms/step - accuracy: 0.2639 - loss: 2.0797[32m [repeated 87x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m121/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m28s[0m 61ms/step - accuracy: 0.2259 - loss: 2.3459[32m [repeated 196x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m110/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m24s[0m 52ms/step - accuracy: 0.3308 - loss: 1.7706
[1m111/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m24s[0m 52ms/step - accuracy: 0.3309 - loss: 1.7706[32m [repeated 185x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 54ms/step - accuracy: 0.3085 - loss: 1.8899
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 54ms/step - accuracy: 0.3085 - loss: 1.8898
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 54ms/step - accuracy: 0.3085 - loss: 1.8898
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 39ms/step - accuracy: 0.1577 - loss: 2.7657
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 39ms/step - accuracy: 0.1575 - loss: 2.7657[32m [repeated 116x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 50ms/step - accuracy: 0.1907 - loss: 2.5641[32m [repeated 177x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 29ms/step - accuracy: 0.2357 - loss: 2.1371
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 29ms/step - accuracy: 0.2357 - loss: 2.1371[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m 89/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m24s[0m 50ms/step - accuracy: 0.2636 - loss: 2.1106
[1m 90/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m24s[0m 50ms/step - accuracy: 0.2636 - loss: 2.1105
[1m 91/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m24s[0m 50ms/step - accuracy: 0.2635 - loss: 2.1104
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m199/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m19s[0m 50ms/step - accuracy: 0.2616 - loss: 2.1078
[1m200/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m19s[0m 50ms/step - accuracy: 0.2616 - loss: 2.1078
[1m201/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m19s[0m 50ms/step - accuracy: 0.2616 - loss: 2.1078
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m506/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 34ms/step - accuracy: 0.1659 - loss: 2.5032
[1m508/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 34ms/step - accuracy: 0.1659 - loss: 2.5032[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m308/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.2418 - loss: 2.1311[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m23s[0m 40ms/step - accuracy: 0.3068 - loss: 1.8989 - val_accuracy: 0.2605 - val_loss: 2.0212
[36m(train_cnn_ray_tune pid=2857954)[0m Epoch 20/28
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 110ms/step - accuracy: 0.4062 - loss: 1.8953
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 29ms/step - accuracy: 0.2357 - loss: 2.1373[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m212/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 59ms/step - accuracy: 0.2227 - loss: 2.3536[32m [repeated 199x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m266/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 49ms/step - accuracy: 0.2606 - loss: 2.1072
[1m267/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 50ms/step - accuracy: 0.2606 - loss: 2.1072[32m [repeated 149x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m23s[0m 30ms/step - accuracy: 0.1598 - loss: 2.5137
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m23s[0m 30ms/step - accuracy: 0.1598 - loss: 2.5137[32m [repeated 126x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m34s[0m 38ms/step - accuracy: 0.1512 - loss: 2.7620[32m [repeated 176x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 29ms/step - accuracy: 0.2357 - loss: 2.1373
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 29ms/step - accuracy: 0.2357 - loss: 2.1373[32m [repeated 36x across cluster][0m
Trial status: 19 RUNNING | 1 TERMINATED
Current time: 2025-11-07 14:00:33. Total running time: 8min 0s
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_a058a    RUNNING              3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21                                              │
│ trial_a058a    RUNNING              3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26                                              │
│ trial_a058a    RUNNING              2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21                                              │
│ trial_a058a    RUNNING              3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24                                              │
│ trial_a058a    RUNNING              2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23                                              │
│ trial_a058a    RUNNING              3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27                                              │
│ trial_a058a    RUNNING              3   adam            relu                                   16                 64                  3                 1          0.000164705         24                                              │
│ trial_a058a    RUNNING              2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24                                              │
│ trial_a058a    RUNNING              3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21                                              │
│ trial_a058a    RUNNING              3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24                                              │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25        1            370.735         0.272525 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m326/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2301 - loss: 2.2716 
[1m328/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2302 - loss: 2.2715
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m232/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m20s[0m 59ms/step - accuracy: 0.2222 - loss: 2.3543
[1m233/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m20s[0m 59ms/step - accuracy: 0.2222 - loss: 2.3543
[1m234/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m20s[0m 59ms/step - accuracy: 0.2221 - loss: 2.3543[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m445/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 57ms/step - accuracy: 0.4140 - loss: 1.5727
[1m446/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 57ms/step - accuracy: 0.4140 - loss: 1.5726[32m [repeated 77x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m462/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 48ms/step - accuracy: 0.1695 - loss: 2.5843[32m [repeated 58x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 89ms/step - accuracy: 0.2500 - loss: 2.2797
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 31ms/step - accuracy: 0.2587 - loss: 2.3067
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m447/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 57ms/step - accuracy: 0.4140 - loss: 1.5726
[1m448/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 57ms/step - accuracy: 0.4140 - loss: 1.5726
[1m449/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 57ms/step - accuracy: 0.4140 - loss: 1.5725
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m44s[0m 38ms/step - accuracy: 0.2640 - loss: 2.0784 - val_accuracy: 0.2698 - val_loss: 2.0040
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m22s[0m 38ms/step - accuracy: 0.1660 - loss: 2.5029 - val_accuracy: 0.1846 - val_loss: 2.3585
[36m(train_cnn_ray_tune pid=2857943)[0m Epoch 11/26[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:59[0m 102ms/step - accuracy: 0.1250 - loss: 2.5912
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 30ms/step - accuracy: 0.2044 - loss: 2.2884  
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m464/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 57ms/step - accuracy: 0.4141 - loss: 1.5721
[1m465/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 57ms/step - accuracy: 0.4142 - loss: 1.5721
[1m466/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 57ms/step - accuracy: 0.4142 - loss: 1.5720
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 63ms/step - accuracy: 0.1875 - loss: 2.0012
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 59ms/step - accuracy: 0.1953 - loss: 1.9858
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.2083 - loss: 2.2837  
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 37ms/step - accuracy: 0.1992 - loss: 2.3038
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 61ms/step - accuracy: 0.2013 - loss: 1.9769
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 60ms/step - accuracy: 0.2024 - loss: 1.9680
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 58ms/step - accuracy: 0.2101 - loss: 1.9565
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 60ms/step - accuracy: 0.2138 - loss: 1.9552
[1m  10/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 59ms/step - accuracy: 0.2168 - loss: 1.9567
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m13s[0m 44ms/step - accuracy: 0.1878 - loss: 2.5026
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m13s[0m 44ms/step - accuracy: 0.1878 - loss: 2.5026
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m13s[0m 44ms/step - accuracy: 0.1878 - loss: 2.5026
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  12/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.2219 - loss: 1.9527
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.2236 - loss: 1.9506
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  14/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.2258 - loss: 1.9477
[1m  15/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.2288 - loss: 1.9433
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  17/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.2342 - loss: 1.9370
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  18/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.2365 - loss: 1.9348
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  19/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.2386 - loss: 1.9321
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  20/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.2404 - loss: 1.9298
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.2440 - loss: 1.9261
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.2452 - loss: 1.9262
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 61ms/step - accuracy: 0.2462 - loss: 1.9262
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.2471 - loss: 1.9267
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.2494 - loss: 1.9267
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.2504 - loss: 1.9265
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 35ms/step - accuracy: 0.2005 - loss: 2.4879[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m 79/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 35ms/step - accuracy: 0.1685 - loss: 2.5143[32m [repeated 133x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m204/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 35ms/step - accuracy: 0.3037 - loss: 1.8931
[1m206/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 35ms/step - accuracy: 0.3037 - loss: 1.8931[32m [repeated 128x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  30/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.2522 - loss: 1.9259
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  32/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 60ms/step - accuracy: 0.2542 - loss: 1.9247
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.2552 - loss: 1.9243
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.2564 - loss: 1.9235
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.2576 - loss: 1.9226
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.2587 - loss: 1.9218
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 61ms/step - accuracy: 0.2599 - loss: 1.9211
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m11s[0m 44ms/step - accuracy: 0.1877 - loss: 2.5025
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m11s[0m 44ms/step - accuracy: 0.1877 - loss: 2.5025[32m [repeated 126x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m28s[0m 38ms/step - accuracy: 0.1474 - loss: 2.7652[32m [repeated 177x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 35ms/step - accuracy: 0.2004 - loss: 2.4878
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 35ms/step - accuracy: 0.2004 - loss: 2.4878[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 61ms/step - accuracy: 0.2611 - loss: 1.9203
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.2623 - loss: 1.9196
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 60ms/step - accuracy: 0.2635 - loss: 1.9189
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.2656 - loss: 1.9178
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  44/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.2674 - loss: 1.9167
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  45/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.2682 - loss: 1.9162
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.2690 - loss: 1.9156
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.2697 - loss: 1.9153
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.2704 - loss: 1.9149
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.2711 - loss: 1.9144
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.2726 - loss: 1.9131
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.2734 - loss: 1.9125
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.2741 - loss: 1.9122
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.2749 - loss: 1.9117
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.2757 - loss: 1.9113
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.2764 - loss: 1.9108
[1m  57/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.2772 - loss: 1.9104
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  58/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.2780 - loss: 1.9098
[1m  59/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.2788 - loss: 1.9091
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m233/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m12s[0m 35ms/step - accuracy: 0.3036 - loss: 1.8933
[1m235/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m12s[0m 35ms/step - accuracy: 0.3036 - loss: 1.8934
[1m237/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m12s[0m 35ms/step - accuracy: 0.3036 - loss: 1.8934[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  60/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.2796 - loss: 1.9085
[1m  61/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.2803 - loss: 1.9078
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  62/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.2810 - loss: 1.9071
[1m  63/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.2817 - loss: 1.9063
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  64/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.2824 - loss: 1.9057
[1m  65/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.2830 - loss: 1.9050
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  66/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.2835 - loss: 1.9045
[1m  67/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.2841 - loss: 1.9039
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m418/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 49ms/step - accuracy: 0.2591 - loss: 2.1054
[1m419/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 49ms/step - accuracy: 0.2591 - loss: 2.1053[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m428/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 45ms/step - accuracy: 0.1956 - loss: 2.4087[32m [repeated 124x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  68/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.2846 - loss: 1.9034
[1m  69/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.2852 - loss: 1.9028
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  71/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.2862 - loss: 1.9020
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m21s[0m 35ms/step - accuracy: 0.2445 - loss: 2.1236 - val_accuracy: 0.2783 - val_loss: 2.0204
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.2867 - loss: 1.9016
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.2872 - loss: 1.9011
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.2877 - loss: 1.9006
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.2882 - loss: 1.9002
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.2887 - loss: 1.8997
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m38s[0m 32ms/step - accuracy: 0.2357 - loss: 2.1373 - val_accuracy: 0.2766 - val_loss: 2.0189[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 44ms/step - accuracy: 0.2812 - loss: 1.9430  
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 41ms/step - accuracy: 0.2781 - loss: 2.0062
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.2892 - loss: 1.8992
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.2896 - loss: 1.8988
[36m(train_cnn_ray_tune pid=2857957)[0m Epoch 23/24[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 104ms/step - accuracy: 0.2500 - loss: 1.9360[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.2901 - loss: 1.8984
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.2905 - loss: 1.8979
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:20[0m 69ms/step - accuracy: 0.1875 - loss: 2.0252 
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.2909 - loss: 1.8974
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.2914 - loss: 1.8969
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.2918 - loss: 1.8964
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.2921 - loss: 1.8959
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m384/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.3371 - loss: 1.7705 
[1m385/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.3372 - loss: 1.7705
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.2925 - loss: 1.8954
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  86/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2929 - loss: 1.8949
[1m  87/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2933 - loss: 1.8945
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  88/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2936 - loss: 1.8939
[1m  89/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2940 - loss: 1.8934
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  90/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2944 - loss: 1.8928
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  91/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2947 - loss: 1.8923
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  92/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2951 - loss: 1.8918
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  93/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2954 - loss: 1.8913
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  94/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2957 - loss: 1.8908
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  95/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 61ms/step - accuracy: 0.2960 - loss: 1.8903
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  96/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2964 - loss: 1.8898
[1m  97/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2967 - loss: 1.8893
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  98/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 61ms/step - accuracy: 0.2970 - loss: 1.8890
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 61ms/step - accuracy: 0.2973 - loss: 1.8886
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 61ms/step - accuracy: 0.2975 - loss: 1.8883
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 61ms/step - accuracy: 0.2977 - loss: 1.8880
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 61ms/step - accuracy: 0.2980 - loss: 1.8877
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 61ms/step - accuracy: 0.2982 - loss: 1.8873
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 61ms/step - accuracy: 0.2984 - loss: 1.8869
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m30s[0m 32ms/step - accuracy: 0.2280 - loss: 2.1554
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m30s[0m 31ms/step - accuracy: 0.2281 - loss: 2.1551
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m30s[0m 31ms/step - accuracy: 0.2282 - loss: 2.1548
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2989 - loss: 1.8862
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2991 - loss: 1.8858
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2994 - loss: 1.8854
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 60ms/step - accuracy: 0.2996 - loss: 1.8851
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 60ms/step - accuracy: 0.2998 - loss: 1.8847
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 60ms/step - accuracy: 0.3002 - loss: 1.8840
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 60ms/step - accuracy: 0.3004 - loss: 1.8836
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 60ms/step - accuracy: 0.3006 - loss: 1.8832
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 44ms/step - accuracy: 0.1874 - loss: 2.5019[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m378/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m12s[0m 60ms/step - accuracy: 0.2226 - loss: 2.3506[32m [repeated 87x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m379/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m12s[0m 60ms/step - accuracy: 0.2226 - loss: 2.3506
[1m380/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m12s[0m 60ms/step - accuracy: 0.2226 - loss: 2.3506[32m [repeated 92x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 60ms/step - accuracy: 0.3008 - loss: 1.8829
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 60ms/step - accuracy: 0.3009 - loss: 1.8826
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 61ms/step - accuracy: 0.3011 - loss: 1.8822
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 61ms/step - accuracy: 0.3013 - loss: 1.8819
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 61ms/step - accuracy: 0.3015 - loss: 1.8816
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 61ms/step - accuracy: 0.3016 - loss: 1.8812
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 220/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m32s[0m 35ms/step - accuracy: 0.2742 - loss: 2.0481
[1m 222/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m32s[0m 35ms/step - accuracy: 0.2742 - loss: 2.0481[32m [repeated 122x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m15s[0m 40ms/step - accuracy: 0.1737 - loss: 2.5541[32m [repeated 200x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 36ms/step - accuracy: 0.1998 - loss: 2.4871
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 36ms/step - accuracy: 0.1998 - loss: 2.4871[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 61ms/step - accuracy: 0.3018 - loss: 1.8809
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 61ms/step - accuracy: 0.3020 - loss: 1.8805
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 61ms/step - accuracy: 0.3024 - loss: 1.8798
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 61ms/step - accuracy: 0.3026 - loss: 1.8795
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 61ms/step - accuracy: 0.3029 - loss: 1.8789
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 60ms/step - accuracy: 0.3031 - loss: 1.8784
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 60ms/step - accuracy: 0.3032 - loss: 1.8781
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 60ms/step - accuracy: 0.3035 - loss: 1.8775
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 60ms/step - accuracy: 0.3037 - loss: 1.8772
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 60ms/step - accuracy: 0.3038 - loss: 1.8769
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 60ms/step - accuracy: 0.3039 - loss: 1.8766
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 60ms/step - accuracy: 0.3041 - loss: 1.8763
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 60ms/step - accuracy: 0.3042 - loss: 1.8760
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 139/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.3045 - loss: 1.8753
[1m 141/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.3047 - loss: 1.8747
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 143/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.3050 - loss: 1.8741
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 145/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.3053 - loss: 1.8735
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m410/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 59ms/step - accuracy: 0.2227 - loss: 2.3503
[1m411/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 59ms/step - accuracy: 0.2227 - loss: 2.3503
[1m412/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 59ms/step - accuracy: 0.2227 - loss: 2.3503
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 147/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.3055 - loss: 1.8728
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 148/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.3057 - loss: 1.8725
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 149/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.3058 - loss: 1.8722
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 150/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.3059 - loss: 1.8719
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 59ms/step - accuracy: 0.3062 - loss: 1.8712 
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 59ms/step - accuracy: 0.3063 - loss: 1.8709
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m472/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 49ms/step - accuracy: 0.3386 - loss: 1.7706
[1m473/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 49ms/step - accuracy: 0.3386 - loss: 1.7706[32m [repeated 106x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m421/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 59ms/step - accuracy: 0.2227 - loss: 2.3503[32m [repeated 163x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 55ms/step - accuracy: 0.1701 - loss: 2.5850 - val_accuracy: 0.2094 - val_loss: 2.3736
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m25s[0m 29ms/step - accuracy: 0.2350 - loss: 2.1417
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 29ms/step - accuracy: 0.2352 - loss: 2.1415
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 29ms/step - accuracy: 0.2353 - loss: 2.1414
[36m(train_cnn_ray_tune pid=2857955)[0m Epoch 15/24
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:35[0m 164ms/step - accuracy: 0.1250 - loss: 2.6740
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m299/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.1676 - loss: 2.5006 
[1m301/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.1676 - loss: 2.5005[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m444/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 59ms/step - accuracy: 0.2227 - loss: 2.3503
[1m445/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 59ms/step - accuracy: 0.2227 - loss: 2.3503
[1m446/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 59ms/step - accuracy: 0.2227 - loss: 2.3503
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 858/1168[0m [32m━
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m26s[0m 44ms/step - accuracy: 0.2318 - loss: 2.2662 - val_accuracy: 0.2340 - val_loss: 2.2095
[36m(train_cnn_ray_tune pid=2857966)[0m Epoch 19/28
[36m(train_cnn_ray_tune pid=2857960)[0m ━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.1588 - loss: 2.5166
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 44ms/step - accuracy: 0.1871 - loss: 2.5010[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m244/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m10s[0m 30ms/step - accuracy: 0.2620 - loss: 2.0792[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m 17/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 35ms/step - accuracy: 0.2452 - loss: 2.2723
[1m 19/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 35ms/step - accuracy: 0.2441 - loss: 2.2722[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 451ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 4/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 23ms/step  
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 6/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 26ms/step
[1m 9/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 26ms/step
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m17s[0m 37ms/step - accuracy: 0.1464 - loss: 2.7626
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m17s[0m 37ms/step - accuracy: 0.1464 - loss: 2.7626[32m [repeated 134x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m54s[0m 57ms/step - accuracy: 0.3116 - loss: 1.8574[32m [repeated 184x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 44ms/step - accuracy: 0.1871 - loss: 2.5010
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 44ms/step - accuracy: 0.1871 - loss: 2.5009[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m12/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 25ms/step
[1m15/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m17/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 24ms/step
[1m20/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m24/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 22ms/step
[1m27/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m29/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 23ms/step
[1m32/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m35/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m38/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m41/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m44/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m46/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 23ms/step
[1m49/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m82s[0m 40ms/step - accuracy: 0.1997 - loss: 2.4868 - val_accuracy: 0.2355 - val_loss: 2.2489
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m52/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 23ms/step
[1m54/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:27[0m 126ms/step - accuracy: 0.3750 - loss: 2.0305
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 32ms/step - accuracy: 0.3125 - loss: 2.1997  
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m56/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 23ms/step
[1m58/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m60/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 23ms/step
[1m64/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m66/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 24ms/step
[1m69/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m71/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 24ms/step
[1m74/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m77/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 23ms/step
[1m79/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 24ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 53ms/step - accuracy: 0.2344 - loss: 2.3326  
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 45ms/step - accuracy: 0.2266 - loss: 2.3742
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m82/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 23ms/step
[1m84/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m577/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 49ms/step - accuracy: 0.3402 - loss: 1.7698
[1m578/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 49ms/step - accuracy: 0.3402 - loss: 1.7697[32m [repeated 113x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m453/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 33ms/step - accuracy: 0.1676 - loss: 2.4965[32m [repeated 137x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 28ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 28ms/step
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 30ms/step - accuracy: 0.1590 - loss: 2.5163
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 30ms/step - accuracy: 0.1590 - loss: 2.5163
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 30ms/step - accuracy: 0.1590 - loss: 2.5163
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 57ms/step
[1m  4/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m  6/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 25ms/step
[1m 10/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 13/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step
[1m 16/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 19/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[1m 22/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 25/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[1m 28/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 31/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[1m 34/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m505/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 58ms/step - accuracy: 0.2228 - loss: 2.3501
[1m506/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 58ms/step - accuracy: 0.2228 - loss: 2.3501
[1m507/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 58ms/step - accuracy: 0.2228 - loss: 2.3501[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 36/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 21ms/step
[1m 38/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 40/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 22ms/step
[1m 43/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m2s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 47/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m2s[0m 21ms/step
[1m 50/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[1m 53/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 55/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[1m 57/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m2s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 60/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 21ms/step
[1m 62/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 55ms/step - accuracy: 0.2589 - loss: 2.1030 - val_accuracy: 0.2677 - val_loss: 2.0359[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m Epoch 15/21[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 115ms/step - accuracy: 0.2500 - loss: 1.9295[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 65/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 21ms/step
[1m 68/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m2s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 71/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m2s[0m 21ms/step
[1m 73/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m2s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 76/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 21ms/step
[1m 79/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 82/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 21ms/step
[1m 85/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 87/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 90/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 22ms/step
[1m 92/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m 95/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 22ms/step
[1m 99/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 40ms/step - accuracy: 0.1738 - loss: 2.5535[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m159/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.2412 - loss: 2.2541[32m [repeated 106x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m 23/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 43ms/step - accuracy: 0.2683 - loss: 2.0572
[1m 25/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 42ms/step - accuracy: 0.2691 - loss: 2.0553[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m102/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 22ms/step
[1m105/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m109/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 22ms/step
[1m112/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m1s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m114/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m1s[0m 22ms/step
[1m116/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m1s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m118/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m1s[0m 22ms/step
[1m121/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m1s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m12s[0m 37ms/step - accuracy: 0.1466 - loss: 2.7614
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m12s[0m 37ms/step - accuracy: 0.1466 - loss: 2.7614[32m [repeated 141x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 31ms/step - accuracy: 0.2202 - loss: 2.4288[32m [repeated 148x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 29ms/step - accuracy: 0.1591 - loss: 2.5161
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 29ms/step - accuracy: 0.1592 - loss: 2.5161[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m124/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 22ms/step
[1m127/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m130/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 22ms/step
[1m132/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m135/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 22ms/step
[1m138/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m141/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 22ms/step
[1m144/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m147/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 22ms/step
[1m149/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m152/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 22ms/step
[1m154/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m157/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 22ms/step
[1m159/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857953)[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=2857953)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m162/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m165/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 121ms/step - accuracy: 0.3750 - loss: 1.9841
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 32ms/step - accuracy: 0.3403 - loss: 1.9141  
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m168/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857953)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m4s[0m 22ms/step

Trial trial_a058a finished iteration 1 at 2025-11-07 14:00:54. Total running time: 8min 21s
╭──────────────────────────────────────╮
│ Trial trial_a058a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             498.889 │
│ time_total_s                 498.889 │
│ training_iteration                 1 │
│ val_accuracy                 0.26401 │
╰──────────────────────────────────────╯

Trial trial_a058a completed after 1 iterations at 2025-11-07 14:00:54. Total running time: 8min 21s
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 43ms/step - accuracy: 0.2448 - loss: 2.0030  
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 40ms/step - accuracy: 0.2506 - loss: 2.0380
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m513/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 28ms/step - accuracy: 0.2597 - loss: 2.0815
[1m516/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 28ms/step - accuracy: 0.2597 - loss: 2.0815[32m [repeated 77x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m504/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 28ms/step - accuracy: 0.2598 - loss: 2.0814[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m57s[0m 49ms/step - accuracy: 0.1871 - loss: 2.5006 - val_accuracy: 0.2120 - val_loss: 2.3388
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:57[0m 101ms/step - accuracy: 0.0625 - loss: 2.7710
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.0781 - loss: 2.7321 
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1466 - loss: 2.7610 
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1466 - loss: 2.7610
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 53ms/step - accuracy: 0.0799 - loss: 2.6997
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 46ms/step - accuracy: 0.0923 - loss: 2.6406 
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m21s[0m 36ms/step - accuracy: 0.1679 - loss: 2.4934 - val_accuracy: 0.1784 - val_loss: 2.3656[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m Epoch 22/27[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 81ms/step - accuracy: 0.0938 - loss: 2.6661[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 51ms/step - accuracy: 0.2109 - loss: 2.4763  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 54ms/step - accuracy: 0.2101 - loss: 2.4494
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 36ms/step - accuracy: 0.1466 - loss: 2.7606[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m297/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m12s[0m 43ms/step - accuracy: 0.1784 - loss: 2.5646[32m [repeated 156x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m 97/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m19s[0m 40ms/step - accuracy: 0.3450 - loss: 1.7567
[1m 99/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m19s[0m 40ms/step - accuracy: 0.3451 - loss: 1.7565[32m [repeated 132x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 302/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m26s[0m 30ms/step - accuracy: 0.2134 - loss: 2.4313
[1m 304/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m25s[0m 30ms/step - accuracy: 0.2134 - loss: 2.4313[32m [repeated 138x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m38s[0m 52ms/step - accuracy: 0.3190 - loss: 1.8378[32m [repeated 147x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 35ms/step - accuracy: 0.1466 - loss: 2.7604
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 35ms/step - accuracy: 0.1466 - loss: 2.7604[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m168/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m17s[0m 43ms/step - accuracy: 0.2747 - loss: 2.0434
[1m170/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m17s[0m 43ms/step - accuracy: 0.2746 - loss: 2.0434
[1m171/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m17s[0m 43ms/step - accuracy: 0.2746 - loss: 2.0434
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.1562 - loss: 2.7089 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.1594 - loss: 2.6638
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m373/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 33ms/step - accuracy: 0.2436 - loss: 2.2422
[1m375/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 33ms/step - accuracy: 0.2436 - loss: 2.2421[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m388/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 33ms/step - accuracy: 0.2437 - loss: 2.2418[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m38s[0m 32ms/step - accuracy: 0.1593 - loss: 2.5159 - val_accuracy: 0.1887 - val_loss: 2.3688
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 86ms/step - accuracy: 0.1250 - loss: 2.3331
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 29ms/step - accuracy: 0.1667 - loss: 2.1665
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m313/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.2052 - loss: 2.3920 
[1m315/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.2052 - loss: 2.3920
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m51s[0m 43ms/step - accuracy: 0.1740 - loss: 2.5532 - val_accuracy: 0.1859 - val_loss: 2.3716
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m18s[0m 31ms/step - accuracy: 0.2593 - loss: 2.0823 - val_accuracy: 0.2821 - val_loss: 2.0098[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m Epoch 10/22[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:29[0m 77ms/step - accuracy: 0.2500 - loss: 2.3576[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 38ms/step - accuracy: 0.2222 - loss: 2.4299 
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.1901 - loss: 2.5869 
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.1901 - loss: 2.5870
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 35ms/step - accuracy: 0.1467 - loss: 2.7597[32m [repeated 65x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m257/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m14s[0m 43ms/step - accuracy: 0.2736 - loss: 2.0443[32m [repeated 156x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m108/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m22s[0m 48ms/step - accuracy: 0.2223 - loss: 2.3365
[1m109/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m22s[0m 48ms/step - accuracy: 0.2224 - loss: 2.3365[32m [repeated 155x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 25ms/step - accuracy: 0.2444 - loss: 2.1236
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 25ms/step - accuracy: 0.2444 - loss: 2.1236
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 25ms/step - accuracy: 0.2445 - loss: 2.1235
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 31ms/step - accuracy: 0.2112 - loss: 2.4322
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 31ms/step - accuracy: 0.2112 - loss: 2.4323[32m [repeated 133x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 180/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m24s[0m 25ms/step - accuracy: 0.1787 - loss: 2.4950[32m [repeated 145x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 35ms/step - accuracy: 0.1467 - loss: 2.7597
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 35ms/step - accuracy: 0.1467 - loss: 2.7597[32m [repeated 61x across cluster][0m

Trial status: 18 RUNNING | 2 TERMINATED
Current time: 2025-11-07 14:01:03. Total running time: 8min 30s
Logical resource usage: 18.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status         N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_a058a    RUNNING              3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21                                              │
│ trial_a058a    RUNNING              3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26                                              │
│ trial_a058a    RUNNING              2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21                                              │
│ trial_a058a    RUNNING              3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24                                              │
│ trial_a058a    RUNNING              2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27                                              │
│ trial_a058a    RUNNING              3   adam            relu                                   16                 64                  3                 1          0.000164705         24                                              │
│ trial_a058a    RUNNING              2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24                                              │
│ trial_a058a    RUNNING              3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21                                              │
│ trial_a058a    RUNNING              3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24                                              │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25        1            370.735         0.272525 │
│ trial_a058a    TERMINATED           3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23        1            498.889         0.264015 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m307/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m7s[0m 29ms/step - accuracy: 0.1603 - loss: 2.5089
[1m309/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m7s[0m 29ms/step - accuracy: 0.1604 - loss: 2.5088[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m239/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 27ms/step - accuracy: 0.2396 - loss: 2.1028[32m [repeated 109x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m165/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m20s[0m 49ms/step - accuracy: 0.2239 - loss: 2.3321
[1m166/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m20s[0m 49ms/step - accuracy: 0.2239 - loss: 2.3320
[1m167/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m20s[0m 49ms/step - accuracy: 0.2239 - loss: 2.3319
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m232/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.1582 - loss: 2.5128 
[1m235/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.1583 - loss: 2.5126
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 43ms/step - accuracy: 0.1894 - loss: 2.5894[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m211/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 49ms/step - accuracy: 0.2242 - loss: 2.3300[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m339/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m10s[0m 41ms/step - accuracy: 0.3497 - loss: 1.7478
[1m341/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m10s[0m 41ms/step - accuracy: 0.3497 - loss: 1.7478[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m20s[0m 26ms/step - accuracy: 0.1737 - loss: 2.4942
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m20s[0m 26ms/step - accuracy: 0.1737 - loss: 2.4941[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m31s[0m 39ms/step - accuracy: 0.1828 - loss: 2.4683[32m [repeated 114x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 30ms/step - accuracy: 0.2704 - loss: 2.0450
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 30ms/step - accuracy: 0.2704 - loss: 2.0450[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m46s[0m 39ms/step - accuracy: 0.1467 - loss: 2.7597 - val_accuracy: 0.1654 - val_loss: 2.5047
[36m(train_cnn_ray_tune pid=2857942)[0m Epoch 11/21
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:38[0m 84ms/step - accuracy: 0.1250 - loss: 2.6852
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 30ms/step - accuracy: 0.1250 - loss: 2.6971 
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:36[0m 83ms/step - accuracy: 0.2500 - loss: 1.8197
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 35ms/step - accuracy: 0.2882 - loss: 1.9454 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 31ms/step - accuracy: 0.2754 - loss: 2.0346
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m23s[0m 38ms/step - accuracy: 0.2444 - loss: 2.2388 - val_accuracy: 0.2416 - val_loss: 2.2038
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 34ms/step - accuracy: 0.2613 - loss: 2.0893
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 32ms/step - accuracy: 0.2561 - loss: 2.1019
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 31ms/step - accuracy: 0.2490 - loss: 2.1153
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m416/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 44ms/step - accuracy: 0.2719 - loss: 2.0493
[1m418/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 44ms/step - accuracy: 0.2719 - loss: 2.0494[32m [repeated 162x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m390/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 41ms/step - accuracy: 0.3499 - loss: 1.7482[32m [repeated 135x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 28ms/step - accuracy: 0.2317 - loss: 2.1370
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 27ms/step - accuracy: 0.2306 - loss: 2.1383
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 27ms/step - accuracy: 0.2303 - loss: 2.1387
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m426/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 44ms/step - accuracy: 0.2718 - loss: 2.0496
[1m427/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 44ms/step - accuracy: 0.2718 - loss: 2.0497
[1m428/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 44ms/step - accuracy: 0.2718 - loss: 2.0497
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 43ms/step - accuracy: 0.1890 - loss: 2.5906[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m313/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m13s[0m 49ms/step - accuracy: 0.2247 - loss: 2.3276[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m315/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m13s[0m 49ms/step - accuracy: 0.2247 - loss: 2.3275
[1m317/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m13s[0m 49ms/step - accuracy: 0.2247 - loss: 2.3274[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 175/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 23ms/step - accuracy: 0.2412 - loss: 2.1135
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m23s[0m 23ms/step - accuracy: 0.2414 - loss: 2.1132[32m [repeated 168x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m26s[0m 39ms/step - accuracy: 0.1858 - loss: 2.4636[32m [repeated 166x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 43ms/step - accuracy: 0.1890 - loss: 2.5907
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 43ms/step - accuracy: 0.1890 - loss: 2.5907[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 28ms/step - accuracy: 0.2449 - loss: 2.1223 - val_accuracy: 0.2764 - val_loss: 1.9752
[36m(train_cnn_ray_tune pid=2857954)[0m Epoch 22/28[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 103ms/step - accuracy: 0.1250 - loss: 2.4631
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 29ms/step - accuracy: 0.1962 - loss: 2.3677  
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 87ms/step - accuracy: 0.1875 - loss: 2.4608[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 42ms/step - accuracy: 0.2052 - loss: 2.3922 - val_accuracy: 0.2105 - val_loss: 2.2911[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m532/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 44ms/step - accuracy: 0.2712 - loss: 2.0527
[1m534/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 44ms/step - accuracy: 0.2712 - loss: 2.0527[32m [repeated 82x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m538/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 44ms/step - accuracy: 0.2712 - loss: 2.0528[32m [repeated 117x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m40s[0m 34ms/step - accuracy: 0.2705 - loss: 2.0441 - val_accuracy: 0.2790 - val_loss: 1.9744
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 35ms/step - accuracy: 0.2118 - loss: 2.2121  
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m533/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 42ms/step - accuracy: 0.3509 - loss: 1.7481
[1m534/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 42ms/step - accuracy: 0.3509 - loss: 1.7481
[1m535/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 42ms/step - accuracy: 0.3509 - loss: 1.7481
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 329ms/step
[1m 6/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step  
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m11/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m16/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m20/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m24/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[1m28/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m32/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[1m37/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 35ms/step - accuracy: 0.0486 - loss: 2.7561     
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m42/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m48/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 12ms/step
[1m54/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m60/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m65/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m69/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 12ms/step
[1m74/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m 85/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 28ms/step - accuracy: 0.1665 - loss: 2.5060
[1m 87/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 28ms/step - accuracy: 0.1666 - loss: 2.5058
[1m 89/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m13s[0m 28ms/step - accuracy: 0.1666 - loss: 2.5055
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m80/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m16s[0m 50ms/step - accuracy: 0.3263 - loss: 1.8242
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m16s[0m 50ms/step - accuracy: 0.3264 - loss: 1.8242
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m16s[0m 50ms/step - accuracy: 0.3264 - loss: 1.8242
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 50ms/step
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m  8/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 7ms/step 
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.2064 - loss: 2.4324[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m114/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 27ms/step - accuracy: 0.1673 - loss: 2.5029[32m [repeated 114x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m109/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m13s[0m 27ms/step - accuracy: 0.1671 - loss: 2.5035
[1m112/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 27ms/step - accuracy: 0.1672 - loss: 2.5031[32m [repeated 110x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m 15/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 7ms/step
[1m 20/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m 25/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[1m 30/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m 36/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[1m 41/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m 47/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step 
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m26s[0m 31ms/step - accuracy: 0.1500 - loss: 2.7268
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m26s[0m 31ms/step - accuracy: 0.1500 - loss: 2.7269[32m [repeated 179x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 26ms/step - accuracy: 0.1694 - loss: 2.4972[32m [repeated 171x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.2063 - loss: 2.4323
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.2063 - loss: 2.4323[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[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=2857957)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m 53/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[1m 60/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m 66/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m 71/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m 75/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m 82/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 9ms/step 
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.1693 - loss: 2.4973 
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.1693 - loss: 2.4973
[36m(train_cnn_ray_tune pid=2857950)[0m Epoch 9/15[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m 86/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m 91/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m 95/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m101/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m108/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 10ms/step
[1m112/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m116/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 88ms/step - accuracy: 0.2500 - loss: 2.4146
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 27ms/step - accuracy: 0.2014 - loss: 2.4860
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m121/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 10ms/step
[1m125/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m131/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 10ms/step
[1m136/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m142/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:35[0m 82ms/step - accuracy: 0.0000e+00 - loss: 2.8283[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m149/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 10ms/step
[1m155/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m18s[0m 30ms/step - accuracy: 0.2469 - loss: 2.0935 - val_accuracy: 0.2722 - val_loss: 2.0123[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m160/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 10ms/step
[1m167/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857957)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 10ms/step

Trial trial_a058a finished iteration 1 at 2025-11-07 14:01:19. Total running time: 8min 47s
╭──────────────────────────────────────╮
│ Trial trial_a058a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             524.007 │
│ time_total_s                 524.007 │
│ training_iteration                 1 │
│ val_accuracy                 0.27216 │
╰──────────────────────────────────────╯

Trial trial_a058a completed after 1 iterations at 2025-11-07 14:01:19. Total running time: 8min 47s
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m318/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 33ms/step - accuracy: 0.2394 - loss: 2.2367
[1m320/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.2394 - loss: 2.2367[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m467/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 48ms/step - accuracy: 0.2253 - loss: 2.3251[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m56s[0m 48ms/step - accuracy: 0.1890 - loss: 2.5908 - val_accuracy: 0.2080 - val_loss: 2.3464
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m215/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 27ms/step - accuracy: 0.1705 - loss: 2.4927 
[1m218/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 27ms/step - accuracy: 0.1706 - loss: 2.4926
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m469/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 48ms/step - accuracy: 0.2253 - loss: 2.3251
[1m470/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 48ms/step - accuracy: 0.2253 - loss: 2.3251
[1m471/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 48ms/step - accuracy: 0.2253 - loss: 2.3251[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 479ms/step
[1m 4/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 20ms/step  
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m 8/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m11/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m15/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m18/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m21/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 18ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m25/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m29/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m33/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m36/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m40/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 17ms/step
[1m43/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m47/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 17ms/step
[1m50/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 17ms/step
[1m57/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m59/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 17ms/step
[1m62/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m66/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 17ms/step
[1m70/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m73/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m75/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 17ms/step
[1m78/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 30ms/step - accuracy: 0.2058 - loss: 2.4315[32m [repeated 50x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m229/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m14s[0m 41ms/step - accuracy: 0.1851 - loss: 2.5485[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m 69/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 40ms/step - accuracy: 0.2767 - loss: 2.0257
[1m 71/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 40ms/step - accuracy: 0.2767 - loss: 2.0269[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m82/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m85/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 18ms/step
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m35s[0m 36ms/step - accuracy: 0.1832 - loss: 2.5956
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m35s[0m 36ms/step - accuracy: 0.1833 - loss: 2.5955[32m [repeated 166x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m21s[0m 31ms/step - accuracy: 0.1499 - loss: 2.7347[32m [repeated 192x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 25ms/step - accuracy: 0.1685 - loss: 2.4975
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 25ms/step - accuracy: 0.1685 - loss: 2.4975[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 22ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 49ms/step - accuracy: 0.3277 - loss: 1.8216 
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 49ms/step - accuracy: 0.3277 - loss: 1.8216
[36m(train_cnn_ray_tune pid=2857951)[0m Epoch 16/21
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 49ms/step
[1m  5/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m  9/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 14ms/step
[1m 12/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m 15/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 19/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m 22/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m 26/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 30/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m 33/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m 37/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m 41/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m 45/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 91ms/step - accuracy: 0.2188 - loss: 1.9709
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m 49/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m 53/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 47ms/step - accuracy: 0.3514 - loss: 1.7479 - val_accuracy: 0.2490 - val_loss: 2.0201[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m 56/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m 60/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m 64/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m 68/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m 72/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m 76/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m 81/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 84/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 87/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m580/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 47ms/step - accuracy: 0.2259 - loss: 2.3232
[1m581/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 48ms/step - accuracy: 0.2259 - loss: 2.3231[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m489/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 32ms/step - accuracy: 0.2400 - loss: 2.2348[32m [repeated 77x across cluster][0m
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m 91/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m 95/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 99/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m103/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 15ms/step
[1m108/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857958)[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=2857958)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m112/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 22ms/step - accuracy: 0.2460 - loss: 2.0989 
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 22ms/step - accuracy: 0.2460 - loss: 2.0989
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m116/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 15ms/step
[1m122/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m126/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 15ms/step
[1m129/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m133/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 15ms/step
[1m139/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m143/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 15ms/step
[1m147/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m152/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 15ms/step
[1m156/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m159/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 15ms/step
[1m162/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857958)[0m 
[1m165/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 15ms/step
[1m168/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 15ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 15ms/step

Trial trial_a058a finished iteration 1 at 2025-11-07 14:01:26. Total running time: 8min 53s
╭──────────────────────────────────────╮
│ Trial trial_a058a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             530.858 │
│ time_total_s                 530.858 │
│ training_iteration                 1 │
│ val_accuracy                 0.24903 │
╰──────────────────────────────────────╯

Trial trial_a058a completed after 1 iterations at 2025-11-07 14:01:26. Total running time: 8min 53s
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.2463 - loss: 2.0984[32m [repeated 60x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m198/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m14s[0m 39ms/step - accuracy: 0.2726 - loss: 2.0485[32m [repeated 42x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m204/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m14s[0m 38ms/step - accuracy: 0.2726 - loss: 2.0484
[1m206/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m14s[0m 38ms/step - accuracy: 0.2726 - loss: 2.0484[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m11s[0m 32ms/step - accuracy: 0.1770 - loss: 2.5360
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 32ms/step - accuracy: 0.1770 - loss: 2.5360[32m [repeated 153x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 29ms/step - accuracy: 0.1499 - loss: 2.7388[32m [repeated 118x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.1880 - loss: 2.4599
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.1880 - loss: 2.4599[32m [repeated 74x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m39s[0m 34ms/step - accuracy: 0.2057 - loss: 2.4312 - val_accuracy: 0.2218 - val_loss: 2.2292
[36m(train_cnn_ray_tune pid=2857944)[0m Epoch 11/16
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:47[0m 92ms/step - accuracy: 0.0625 - loss: 2.6145
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1302 - loss: 2.4972 
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m31s[0m 53ms/step - accuracy: 0.2259 - loss: 2.3231 - val_accuracy: 0.2211 - val_loss: 2.2595
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m426/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 39ms/step - accuracy: 0.1843 - loss: 2.5532
[1m428/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 39ms/step - accuracy: 0.1843 - loss: 2.5532[32m [repeated 113x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 26ms/step - accuracy: 0.1719 - loss: 2.4812[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m21s[0m 36ms/step - accuracy: 0.2403 - loss: 2.2333 - val_accuracy: 0.2426 - val_loss: 2.1934
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 80ms/step - accuracy: 0.1562 - loss: 2.3077
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 32ms/step - accuracy: 0.2083 - loss: 2.2699
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 36ms/step - accuracy: 0.1880 - loss: 2.4598
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 36ms/step - accuracy: 0.1880 - loss: 2.4598
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 36ms/step - accuracy: 0.1880 - loss: 2.4598
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m316/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.2713 - loss: 2.0497 
[1m318/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.2713 - loss: 2.0497
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m 23/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 27ms/step - accuracy: 0.1668 - loss: 2.4736
[1m 25/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 27ms/step - accuracy: 0.1666 - loss: 2.4760
[1m 27/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 27ms/step - accuracy: 0.1663 - loss: 2.4776
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 31ms/step - accuracy: 0.1771 - loss: 2.5357[32m [repeated 82x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m112/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m18s[0m 39ms/step - accuracy: 0.2313 - loss: 2.2927[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m114/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m18s[0m 39ms/step - accuracy: 0.2314 - loss: 2.2925
[1m116/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m18s[0m 39ms/step - accuracy: 0.2314 - loss: 2.2922[32m [repeated 69x across cluster][0m

Trial status: 16 RUNNING | 4 TERMINATED
Current time: 2025-11-07 14:01:33. Total running time: 9min 1s
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_a058a    RUNNING              3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21                                              │
│ trial_a058a    RUNNING              3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26                                              │
│ trial_a058a    RUNNING              2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21                                              │
│ trial_a058a    RUNNING              3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24                                              │
│ trial_a058a    RUNNING              2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27                                              │
│ trial_a058a    RUNNING              3   adam            relu                                   16                 64                  3                 1          0.000164705         24                                              │
│ trial_a058a    RUNNING              3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21                                              │
│ trial_a058a    RUNNING              3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24                                              │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25        1            370.735         0.272525 │
│ trial_a058a    TERMINATED           3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15        1            530.858         0.249029 │
│ trial_a058a    TERMINATED           3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23        1            498.889         0.264015 │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24        1            524.007         0.272155 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 21ms/step - accuracy: 0.1634 - loss: 2.5023
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 21ms/step - accuracy: 0.1635 - loss: 2.5022[32m [repeated 130x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m12s[0m 26ms/step - accuracy: 0.2742 - loss: 2.0391[32m [repeated 93x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 31ms/step - accuracy: 0.1771 - loss: 2.5356
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 31ms/step - accuracy: 0.1772 - loss: 2.5356[32m [repeated 102x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 28ms/step - accuracy: 0.1681 - loss: 2.4976 - val_accuracy: 0.1841 - val_loss: 2.3645
[36m(train_cnn_ray_tune pid=2857956)[0m Epoch 24/27[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 100ms/step - accuracy: 0.3125 - loss: 2.1503
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m569/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.1840 - loss: 2.5527
[1m571/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.1840 - loss: 2.5527[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m408/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 37ms/step - accuracy: 0.2714 - loss: 2.0498[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m17s[0m 29ms/step - accuracy: 0.1719 - loss: 2.4812 - val_accuracy: 0.1804 - val_loss: 2.3600[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 78ms/step - accuracy: 0.1250 - loss: 2.5448
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 20ms/step - accuracy: 0.1406 - loss: 2.5028[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 83ms/step - accuracy: 0.1562 - loss: 2.5855
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 24ms/step - accuracy: 0.2470 - loss: 2.0970 - val_accuracy: 0.2725 - val_loss: 1.9773
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m181/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 25ms/step - accuracy: 0.3214 - loss: 1.8620 
[1m183/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 25ms/step - accuracy: 0.3214 - loss: 1.8619[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 16ms/step - accuracy: 0.3017 - loss: 1.9449 
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 24/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 28ms/step - accuracy: 0.1925 - loss: 2.4061
[1m 26/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 28ms/step - accuracy: 0.1921 - loss: 2.4073
[1m 28/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 28ms/step - accuracy: 0.1918 - loss: 2.4081[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 25ms/step - accuracy: 0.2749 - loss: 2.0328[32m [repeated 58x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m254/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m12s[0m 37ms/step - accuracy: 0.2316 - loss: 2.2874[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 80/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 28ms/step - accuracy: 0.1956 - loss: 2.4008
[1m 82/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 28ms/step - accuracy: 0.1958 - loss: 2.4005[32m [repeated 92x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 37ms/step - accuracy: 0.3420 - loss: 1.7359
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 37ms/step - accuracy: 0.3420 - loss: 1.7367[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 33ms/step - accuracy: 0.1876 - loss: 2.5876[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 28ms/step - accuracy: 0.1495 - loss: 2.7411
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 28ms/step - accuracy: 0.1495 - loss: 2.7411[32m [repeated 99x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m Epoch 17/24[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m350/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 23ms/step - accuracy: 0.1714 - loss: 2.4746
[1m352/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 23ms/step - accuracy: 0.1714 - loss: 2.4746[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m556/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 36ms/step - accuracy: 0.2720 - loss: 2.0489[32m [repeated 84x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 42ms/step - accuracy: 0.1839 - loss: 2.5526 - val_accuracy: 0.2061 - val_loss: 2.3689[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m17s[0m 26ms/step - accuracy: 0.2110 - loss: 2.3788
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m17s[0m 26ms/step - accuracy: 0.2110 - loss: 2.3790
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 26ms/step - accuracy: 0.2110 - loss: 2.3791
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 91ms/step - accuracy: 0.2500 - loss: 2.1686[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 29ms/step - accuracy: 0.1944 - loss: 2.4996 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 34ms/step - accuracy: 0.2054 - loss: 2.5245
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m46s[0m 40ms/step - accuracy: 0.1881 - loss: 2.4592 - val_accuracy: 0.2081 - val_loss: 2.3284[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 39ms/step - accuracy: 0.3403 - loss: 1.8125 
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 25ms/step - accuracy: 0.2754 - loss: 2.0281[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m247/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2020 - loss: 2.3861 [32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m132/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 35ms/step - accuracy: 0.1851 - loss: 2.5294
[1m134/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 35ms/step - accuracy: 0.1850 - loss: 2.5296[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m11s[0m 20ms/step - accuracy: 0.1670 - loss: 2.4940
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m11s[0m 20ms/step - accuracy: 0.1670 - loss: 2.4940[32m [repeated 142x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 33ms/step - accuracy: 0.1881 - loss: 2.5853[32m [repeated 140x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 25ms/step - accuracy: 0.2754 - loss: 2.0280
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 25ms/step - accuracy: 0.2754 - loss: 2.0279[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m Epoch 11/22[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m312/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2031 - loss: 2.3817
[1m314/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2031 - loss: 2.3816[32m [repeated 124x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m535/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 25ms/step - accuracy: 0.3211 - loss: 1.8563[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 41ms/step - accuracy: 0.2722 - loss: 2.0487 - val_accuracy: 0.2609 - val_loss: 2.0256
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m12s[0m 20ms/step - accuracy: 0.1670 - loss: 2.4941
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 20ms/step - accuracy: 0.1670 - loss: 2.4941
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m11s[0m 20ms/step - accuracy: 0.1670 - loss: 2.4941
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:27[0m 75ms/step - accuracy: 0.0625 - loss: 2.9477[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.1389 - loss: 2.7413 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.1446 - loss: 2.7448[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m36s[0m 31ms/step - accuracy: 0.1495 - loss: 2.7410 - val_accuracy: 0.1669 - val_loss: 2.4963[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m16s[0m 27ms/step - accuracy: 0.1702 - loss: 2.4731 - val_accuracy: 0.1802 - val_loss: 2.3590
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 77ms/step - accuracy: 0.0938 - loss: 2.6010
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 19ms/step - accuracy: 0.1484 - loss: 2.5431
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 33ms/step - accuracy: 0.1883 - loss: 2.5839[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m108/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 36ms/step - accuracy: 0.2693 - loss: 2.0724[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m  6/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 23ms/step - accuracy: 0.1562 - loss: 2.5367
[1m  8/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 24ms/step - accuracy: 0.1615 - loss: 2.5266[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 26ms/step - accuracy: 0.1628 - loss: 2.6862
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 26ms/step - accuracy: 0.1627 - loss: 2.6865[32m [repeated 178x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 225/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m29s[0m 31ms/step - accuracy: 0.1905 - loss: 2.4605[32m [repeated 140x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 21ms/step - accuracy: 0.1673 - loss: 2.4928
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 21ms/step - accuracy: 0.1673 - loss: 2.4928[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m Epoch 25/27[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m306/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1844 - loss: 2.5325 
[1m308/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1844 - loss: 2.5324
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m330/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1845 - loss: 2.5323
[1m332/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1845 - loss: 2.5323[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m560/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 39ms/step - accuracy: 0.2306 - loss: 2.2920[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 63ms/step - accuracy: 0.1875 - loss: 1.9733
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 20ms/step - accuracy: 0.2507 - loss: 2.0923
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 20ms/step - accuracy: 0.2507 - loss: 2.0922
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 20ms/step - accuracy: 0.2507 - loss: 2.0922
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 28ms/step - accuracy: 0.2755 - loss: 2.0271 - val_accuracy: 0.2812 - val_loss: 1.9797
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m17s[0m 29ms/step - accuracy: 0.3210 - loss: 1.8557 - val_accuracy: 0.2681 - val_loss: 1.9903[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 72ms/step - accuracy: 0.2812 - loss: 2.1119
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 34ms/step - accuracy: 0.2899 - loss: 2.0941[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m237/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m12s[0m 37ms/step - accuracy: 0.2715 - loss: 2.0534
[1m239/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m12s[0m 37ms/step - accuracy: 0.2715 - loss: 2.0532
[1m241/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m12s[0m 37ms/step - accuracy: 0.2716 - loss: 2.0529
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.2510 - loss: 2.0910[32m [repeated 113x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m243/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m12s[0m 37ms/step - accuracy: 0.2716 - loss: 2.0527[32m [repeated 77x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m156/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 29ms/step - accuracy: 0.2481 - loss: 2.1860
[1m159/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 29ms/step - accuracy: 0.2480 - loss: 2.1863[32m [repeated 109x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m23s[0m 29ms/step - accuracy: 0.1898 - loss: 2.5122
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m23s[0m 29ms/step - accuracy: 0.1898 - loss: 2.5122
[1m 378/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m23s[0m 29ms/step - accuracy: 0.1898 - loss: 2.5121
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m22s[0m 26ms/step - accuracy: 0.1565 - loss: 2.7075
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m22s[0m 26ms/step - accuracy: 0.1564 - loss: 2.7077[32m [repeated 147x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m28s[0m 38ms/step - accuracy: 0.3550 - loss: 1.7572[32m [repeated 119x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.2511 - loss: 2.0909
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.2511 - loss: 2.0908[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m Epoch 24/28[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m209/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 27ms/step - accuracy: 0.3226 - loss: 1.8291 
[1m212/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 27ms/step - accuracy: 0.3227 - loss: 1.8290
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m246/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.3233 - loss: 1.8282
[1m249/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.3233 - loss: 1.8282[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m301/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 24ms/step - accuracy: 0.1799 - loss: 2.4533[32m [repeated 50x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m311/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.2726 - loss: 2.0463 
[1m313/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.2726 - loss: 2.0461
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 88ms/step - accuracy: 0.3125 - loss: 2.3565
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m20s[0m 35ms/step - accuracy: 0.2065 - loss: 2.3729 - val_accuracy: 0.2133 - val_loss: 2.2726[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 85ms/step - accuracy: 0.0938 - loss: 2.6378
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 39ms/step - accuracy: 0.1597 - loss: 2.4220
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 26ms/step - accuracy: 0.2086 - loss: 2.3943[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 87/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 39ms/step - accuracy: 0.2356 - loss: 2.2483[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 67/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 30ms/step - accuracy: 0.2132 - loss: 2.3621
[1m 70/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 30ms/step - accuracy: 0.2132 - loss: 2.3614[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m19s[0m 31ms/step - accuracy: 0.1982 - loss: 2.4360
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m19s[0m 31ms/step - accuracy: 0.1982 - loss: 2.4359[32m [repeated 147x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 24ms/step - accuracy: 0.2928 - loss: 1.9680[32m [repeated 99x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 26ms/step - accuracy: 0.2086 - loss: 2.3943
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 26ms/step - accuracy: 0.2086 - loss: 2.3943[32m [repeated 80x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m Epoch 20/26[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 24ms/step - accuracy: 0.1674 - loss: 2.4910 - val_accuracy: 0.1785 - val_loss: 2.3666
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1484 - loss: 2.4005 
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m509/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 24ms/step - accuracy: 0.1790 - loss: 2.4549
[1m512/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 24ms/step - accuracy: 0.1790 - loss: 2.4549[32m [repeated 148x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m447/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 36ms/step - accuracy: 0.2733 - loss: 2.0404[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:17[0m 66ms/step - accuracy: 0.0625 - loss: 2.4632
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 86ms/step - accuracy: 0.1250 - loss: 2.5616
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 35ms/step - accuracy: 0.1493 - loss: 2.5617
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:35[0m 82ms/step - accuracy: 0.1875 - loss: 2.2918
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 30ms/step - accuracy: 0.2326 - loss: 2.2475 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 30ms/step - accuracy: 0.2427 - loss: 2.2349
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 41ms/step - accuracy: 0.1846 - loss: 2.5337 - val_accuracy: 0.2063 - val_loss: 2.3685
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 20ms/step - accuracy: 0.2515 - loss: 2.0888[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 29/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 33ms/step - accuracy: 0.1568 - loss: 2.6080[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m225/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 38ms/step - accuracy: 0.2377 - loss: 2.2555
[1m227/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 38ms/step - accuracy: 0.2377 - loss: 2.2557[32m [repeated 57x across cluster][0m
Trial status: 16 RUNNING | 4 TERMINATED
Current time: 2025-11-07 14:02:03. Total running time: 9min 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_a058a    RUNNING              3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21                                              │
│ trial_a058a    RUNNING              3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26                                              │
│ trial_a058a    RUNNING              2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21                                              │
│ trial_a058a    RUNNING              3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24                                              │
│ trial_a058a    RUNNING              2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27                                              │
│ trial_a058a    RUNNING              3   adam            relu                                   16                 64                  3                 1          0.000164705         24                                              │
│ trial_a058a    RUNNING              3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21                                              │
│ trial_a058a    RUNNING              3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24                                              │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25        1            370.735         0.272525 │
│ trial_a058a    TERMINATED           3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15        1            530.858         0.249029 │
│ trial_a058a    TERMINATED           3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23        1            498.889         0.264015 │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24        1            524.007         0.272155 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 26ms/step - accuracy: 0.1520 - loss: 2.7248
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 26ms/step - accuracy: 0.1520 - loss: 2.7248[32m [repeated 174x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m12s[0m 29ms/step - accuracy: 0.1899 - loss: 2.5110[32m [repeated 120x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 20ms/step - accuracy: 0.2516 - loss: 2.0886
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 20ms/step - accuracy: 0.2516 - loss: 2.0886[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m Epoch 16/25[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m249/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2157 - loss: 2.3451 
[1m251/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2157 - loss: 2.3451
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m16s[0m 28ms/step - accuracy: 0.1788 - loss: 2.4551 - val_accuracy: 0.1795 - val_loss: 2.3581
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m26s[0m 22ms/step - accuracy: 0.2516 - loss: 2.0886 - val_accuracy: 0.2768 - val_loss: 1.9584[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 19ms/step - accuracy: 0.3606 - loss: 1.8946 
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.1519 - loss: 2.7260 
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.1519 - loss: 2.7261
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m303/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2165 - loss: 2.3427
[1m305/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2165 - loss: 2.3426[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m307/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2165 - loss: 2.3425[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m17s[0m 20ms/step - accuracy: 0.1708 - loss: 2.4686
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m17s[0m 20ms/step - accuracy: 0.1708 - loss: 2.4686
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m16s[0m 20ms/step - accuracy: 0.1708 - loss: 2.4687
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 66ms/step - accuracy: 0.0625 - loss: 2.4126
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 30ms/step - accuracy: 0.1476 - loss: 2.2766
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 74ms/step - accuracy: 0.3750 - loss: 1.9208[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 28ms/step - accuracy: 0.1892 - loss: 2.5122[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m177/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 33ms/step - accuracy: 0.1748 - loss: 2.5614[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m  9/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 36ms/step - accuracy: 0.2174 - loss: 2.0873
[1m 11/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 36ms/step - accuracy: 0.2216 - loss: 2.0781[32m [repeated 83x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m12s[0m 37ms/step - accuracy: 0.3560 - loss: 1.7569
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m12s[0m 37ms/step - accuracy: 0.3560 - loss: 1.7569[32m [repeated 176x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m14s[0m 20ms/step - accuracy: 0.1712 - loss: 2.4673[32m [repeated 121x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.1993 - loss: 2.4311
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.1993 - loss: 2.4311[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m Epoch 18/21[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 41ms/step - accuracy: 0.2734 - loss: 2.0371 - val_accuracy: 0.2735 - val_loss: 2.0089[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1993 - loss: 2.4314 
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.1993 - loss: 2.4314
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m480/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 30ms/step - accuracy: 0.2170 - loss: 2.3410
[1m482/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 30ms/step - accuracy: 0.2170 - loss: 2.3410[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m277/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.1810 - loss: 2.4364[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.3561 - loss: 1.7569 
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.3561 - loss: 1.7569
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m294/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.1796 - loss: 2.5478 
[1m296/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.1796 - loss: 2.5477
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m52s[0m 90ms/step - accuracy: 0.1562 - loss: 2.3505
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 37ms/step - accuracy: 0.3561 - loss: 1.7570[32m [repeated 111x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m148/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.2635 - loss: 2.0311[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m150/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m15s[0m 35ms/step - accuracy: 0.2636 - loss: 2.0311
[1m152/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m15s[0m 35ms/step - accuracy: 0.2636 - loss: 2.0311[32m [repeated 84x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m12s[0m 19ms/step - accuracy: 0.2602 - loss: 2.0570
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 19ms/step - accuracy: 0.2602 - loss: 2.0571[32m [repeated 97x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 25ms/step - accuracy: 0.2126 - loss: 2.3580[32m [repeated 79x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 31ms/step - accuracy: 0.1996 - loss: 2.4299
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 31ms/step - accuracy: 0.1996 - loss: 2.4299[32m [repeated 126x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m548/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 38ms/step - accuracy: 0.2388 - loss: 2.2595
[1m550/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 38ms/step - accuracy: 0.2388 - loss: 2.2595[32m [repeated 130x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m382/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 34ms/step - accuracy: 0.1811 - loss: 2.5444[32m [repeated 91x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 20ms/step - accuracy: 0.1724 - loss: 2.4657
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 20ms/step - accuracy: 0.1724 - loss: 2.4657
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 20ms/step - accuracy: 0.1724 - loss: 2.4657
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m20s[0m 34ms/step - accuracy: 0.2167 - loss: 2.3412 - val_accuracy: 0.2037 - val_loss: 2.2851
[36m(train_cnn_ray_tune pid=2857964)[0m Epoch 21/26
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 78ms/step - accuracy: 0.1875 - loss: 2.2858
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 28ms/step - accuracy: 0.2253 - loss: 2.2967
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m218/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 27ms/step - accuracy: 0.2434 - loss: 2.1664 
[1m220/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 27ms/step - accuracy: 0.2435 - loss: 2.1664
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m286/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2671 - loss: 2.0301 
[1m288/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.2671 - loss: 2.0300
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 29ms/step - accuracy: 0.1508 - loss: 2.7320 - val_accuracy: 0.1674 - val_loss: 2.4885
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 37ms/step - accuracy: 0.3564 - loss: 1.7563[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 81/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 25ms/step - accuracy: 0.2119 - loss: 2.3619[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 84/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 25ms/step - accuracy: 0.2120 - loss: 2.3615
[1m 87/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 25ms/step - accuracy: 0.2120 - loss: 2.3611[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 66ms/step - accuracy: 0.1250 - loss: 2.8335
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1263 - loss: 2.8215 
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m12s[0m 24ms/step - accuracy: 0.2109 - loss: 2.3626
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m12s[0m 24ms/step - accuracy: 0.2109 - loss: 2.3627[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1254 - loss: 2.8595[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 19ms/step - accuracy: 0.2589 - loss: 2.0598
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 19ms/step - accuracy: 0.2589 - loss: 2.0598[32m [repeated 119x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m343/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 33ms/step - accuracy: 0.2677 - loss: 2.0282
[1m345/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 33ms/step - accuracy: 0.2678 - loss: 2.0281
[1m347/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.2678 - loss: 2.0280
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1185 - loss: 2.4462 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1645 - loss: 2.3535
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m525/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 25ms/step - accuracy: 0.2510 - loss: 2.1616
[1m528/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 25ms/step - accuracy: 0.2510 - loss: 2.1615[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m385/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 33ms/step - accuracy: 0.2682 - loss: 2.0267[32m [repeated 79x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 20ms/step - accuracy: 0.1725 - loss: 2.4658
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 20ms/step - accuracy: 0.1725 - loss: 2.4658
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 20ms/step - accuracy: 0.1725 - loss: 2.4658[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 42ms/step - accuracy: 0.2389 - loss: 2.2593 - val_accuracy: 0.2407 - val_loss: 2.2370[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m Epoch 16/24[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 82ms/step - accuracy: 0.1875 - loss: 2.3695
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 16ms/step - accuracy: 0.1768 - loss: 2.3838 
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m193/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.2161 - loss: 2.3461 
[1m195/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.2161 - loss: 2.3460
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m40s[0m 34ms/step - accuracy: 0.1998 - loss: 2.4290 - val_accuracy: 0.2152 - val_loss: 2.3297[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 18ms/step - accuracy: 0.2581 - loss: 2.0609[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m 60/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.3232 - loss: 1.8127[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m119/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 33ms/step - accuracy: 0.2413 - loss: 2.2549
[1m121/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 33ms/step - accuracy: 0.2413 - loss: 2.2549[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 78ms/step - accuracy: 0.3125 - loss: 1.8846[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 30ms/step - accuracy: 0.3056 - loss: 1.9860 
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m19s[0m 21ms/step - accuracy: 0.1527 - loss: 2.7177
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m19s[0m 21ms/step - accuracy: 0.1527 - loss: 2.7176[32m [repeated 124x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  91/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 25ms/step - accuracy: 0.2084 - loss: 2.4200[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 18ms/step - accuracy: 0.2581 - loss: 2.0609
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 18ms/step - accuracy: 0.2581 - loss: 2.0609[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m243/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.2170 - loss: 2.3426
[1m245/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.2170 - loss: 2.3425
[1m247/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.2170 - loss: 2.3424[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 82ms/step - accuracy: 0.2188 - loss: 2.4404
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 32ms/step - accuracy: 0.2587 - loss: 2.3464
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m115/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.3249 - loss: 1.8099 
[1m117/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.3248 - loss: 1.8100
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2174 - loss: 2.3725 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.2057 - loss: 2.4051
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m551/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 32ms/step - accuracy: 0.2699 - loss: 2.0223
[1m553/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 32ms/step - accuracy: 0.2699 - loss: 2.0223[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m165/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m8s[0m 21ms/step - accuracy: 0.3232 - loss: 1.8111[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 18ms/step - accuracy: 0.1732 - loss: 2.4455 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 18ms/step - accuracy: 0.1808 - loss: 2.4326
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m21s[0m 24ms/step - accuracy: 0.2033 - loss: 2.4282
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m21s[0m 24ms/step - accuracy: 0.2032 - loss: 2.4286
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m21s[0m 24ms/step - accuracy: 0.2032 - loss: 2.4290
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m22s[0m 37ms/step - accuracy: 0.1823 - loss: 2.5426 - val_accuracy: 0.2072 - val_loss: 2.3547[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m Epoch 9/24[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 20ms/step - accuracy: 0.2580 - loss: 2.0609 - val_accuracy: 0.2720 - val_loss: 1.9564[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 23ms/step - accuracy: 0.2108 - loss: 2.3639[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m131/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m14s[0m 33ms/step - accuracy: 0.1951 - loss: 2.4948[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m261/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m11s[0m 34ms/step - accuracy: 0.2397 - loss: 2.2507
[1m263/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 34ms/step - accuracy: 0.2397 - loss: 2.2507[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:28[0m 76ms/step - accuracy: 0.1875 - loss: 1.9887[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 20ms/step - accuracy: 0.1777 - loss: 2.4469
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 20ms/step - accuracy: 0.1776 - loss: 2.4470[32m [repeated 178x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  89/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 36ms/step - accuracy: 0.3817 - loss: 1.6941[32m [repeated 82x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 23ms/step - accuracy: 0.2109 - loss: 2.3638
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 23ms/step - accuracy: 0.2109 - loss: 2.3638[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m328/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m6s[0m 26ms/step - accuracy: 0.2181 - loss: 2.3391
[1m330/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m6s[0m 26ms/step - accuracy: 0.2181 - loss: 2.3390
[1m332/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m6s[0m 26ms/step - accuracy: 0.2181 - loss: 2.3390
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:42[0m 88ms/step - accuracy: 0.5625 - loss: 1.3505
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 32ms/step - accuracy: 0.4306 - loss: 1.5131 
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m197/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.2514 - loss: 2.1619 
[1m200/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.2514 - loss: 2.1618
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m321/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.2397 - loss: 2.2504
[1m323/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.2397 - loss: 2.2504[32m [repeated 107x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m537/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 27ms/step - accuracy: 0.2192 - loss: 2.3362[32m [repeated 82x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 20ms/step - accuracy: 0.2109 - loss: 1.9888 
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 19ms/step - accuracy: 0.2374 - loss: 1.9683
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m  58/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 20ms/step - accuracy: 0.1780 - loss: 2.4446
[1m  61/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 20ms/step - accuracy: 0.1780 - loss: 2.4449
[1m  63/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 20ms/step - accuracy: 0.1780 - loss: 2.4450
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m22s[0m 37ms/step - accuracy: 0.2702 - loss: 2.0216 - val_accuracy: 0.2775 - val_loss: 2.0063
[36m(train_cnn_ray_tune pid=2857951)[0m Epoch 19/21[32m [repeated 2x across cluster][0m
Trial status: 16 RUNNING | 4 TERMINATED
Current time: 2025-11-07 14:02:33. Total running time: 10min 1s
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_a058a    RUNNING              3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21                                              │
│ trial_a058a    RUNNING              3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26                                              │
│ trial_a058a    RUNNING              2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21                                              │
│ trial_a058a    RUNNING              3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24                                              │
│ trial_a058a    RUNNING              2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27                                              │
│ trial_a058a    RUNNING              3   adam            relu                                   16                 64                  3                 1          0.000164705         24                                              │
│ trial_a058a    RUNNING              3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21                                              │
│ trial_a058a    RUNNING              3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24                                              │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25        1            370.735         0.272525 │
│ trial_a058a    TERMINATED           3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15        1            530.858         0.249029 │
│ trial_a058a    TERMINATED           3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23        1            498.889         0.264015 │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24        1            524.007         0.272155 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 24ms/step - accuracy: 0.2110 - loss: 2.3636[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m275/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 34ms/step - accuracy: 0.1919 - loss: 2.5044[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m115/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m15s[0m 34ms/step - accuracy: 0.2809 - loss: 1.9632
[1m117/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 34ms/step - accuracy: 0.2808 - loss: 1.9637[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m498/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 23ms/step - accuracy: 0.3240 - loss: 1.8082
[1m500/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 23ms/step - accuracy: 0.3240 - loss: 1.8083
[1m502/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 23ms/step - accuracy: 0.3240 - loss: 1.8083
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 111ms/step - accuracy: 0.2500 - loss: 2.0478
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 23ms/step - accuracy: 0.1541 - loss: 2.7129
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 23ms/step - accuracy: 0.1541 - loss: 2.7129[32m [repeated 217x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m33s[0m 36ms/step - accuracy: 0.3683 - loss: 1.7048[32m [repeated 129x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 24ms/step - accuracy: 0.2110 - loss: 2.3637
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 24ms/step - accuracy: 0.2110 - loss: 2.3636[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m15s[0m 25ms/step - accuracy: 0.1823 - loss: 2.4287 - val_accuracy: 0.1833 - val_loss: 2.3505
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m291/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.1916 - loss: 2.5053 
[1m293/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.1916 - loss: 2.5054
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 420ms/step
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 27ms/step - accuracy: 0.2110 - loss: 2.3636 - val_accuracy: 0.2331 - val_loss: 2.2018
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:32[0m 79ms/step - accuracy: 0.1250 - loss: 2.2513
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m 7/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step   
[1m11/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1523 - loss: 2.3523 
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m16/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m21/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m26/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m31/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m36/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m41/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m46/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m50/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m55/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 22ms/step - accuracy: 0.2824 - loss: 1.9810 
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 22ms/step - accuracy: 0.2824 - loss: 1.9809
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m60/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 11ms/step
[1m65/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m72/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 11ms/step
[1m77/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m80/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 11ms/step
[1m85/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m459/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 35ms/step - accuracy: 0.2405 - loss: 2.2472
[1m461/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 35ms/step - accuracy: 0.2406 - loss: 2.2472[32m [repeated 102x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m457/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 35ms/step - accuracy: 0.2405 - loss: 2.2473[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 42ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m  8/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step 
[1m 15/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m 21/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[1m 27/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m 33/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[1m 39/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m 44/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[1m 49/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m 54/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m Epoch 22/26[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m 59/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m 64/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m 70/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m 75/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m 80/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m 84/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m 89/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m 94/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m100/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m103/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 10ms/step
[1m109/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m114/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 10ms/step
[1m119/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m124/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 10ms/step
[1m129/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m134/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 10ms/step
[1m139/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m12s[0m 26ms/step - accuracy: 0.1948 - loss: 2.4652
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m12s[0m 26ms/step - accuracy: 0.1948 - loss: 2.4653
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m12s[0m 26ms/step - accuracy: 0.1948 - loss: 2.4654
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m145/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 10ms/step
[1m150/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m155/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m162/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m167/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857956)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 11ms/step

Trial trial_a058a finished iteration 1 at 2025-11-07 14:02:38. Total running time: 10min 5s
[36m(train_cnn_ray_tune pid=2857956)[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=2857956)[0m   _log_deprecation_warning(
╭──────────────────────────────────────╮
│ Trial trial_a058a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             602.129 │
│ time_total_s                 602.129 │
│ training_iteration                 1 │
│ val_accuracy                 0.18335 │
╰──────────────────────────────────────╯

Trial trial_a058a completed after 1 iterations at 2025-11-07 14:02:38. Total running time: 10min 5s
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 24ms/step - accuracy: 0.1546 - loss: 2.7121[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m127/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m13s[0m 30ms/step - accuracy: 0.2318 - loss: 2.2793[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m258/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m11s[0m 34ms/step - accuracy: 0.2765 - loss: 1.9825
[1m260/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m11s[0m 34ms/step - accuracy: 0.2765 - loss: 1.9826[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m444/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 26ms/step - accuracy: 0.2530 - loss: 2.1535
[1m446/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 26ms/step - accuracy: 0.2530 - loss: 2.1535
[1m448/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 26ms/step - accuracy: 0.2531 - loss: 2.1534
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 34ms/step - accuracy: 0.2396 - loss: 2.3482    
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 174/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 25ms/step - accuracy: 0.2116 - loss: 2.3643
[1m 177/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m24s[0m 25ms/step - accuracy: 0.2116 - loss: 2.3645[32m [repeated 191x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m16s[0m 29ms/step - accuracy: 0.2069 - loss: 2.4121[32m [repeated 124x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.1546 - loss: 2.7121
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.1546 - loss: 2.7121[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m16s[0m 28ms/step - accuracy: 0.3241 - loss: 1.8089 - val_accuracy: 0.2696 - val_loss: 1.9936[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 19ms/step - accuracy: 0.2654 - loss: 2.0498
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 19ms/step - accuracy: 0.2654 - loss: 2.0498
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 19ms/step - accuracy: 0.2653 - loss: 2.0498
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:35:01[0m 39s/step - accuracy: 0.3125 - loss: 2.1723[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 18ms/step - accuracy: 0.2655 - loss: 2.0498 
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 18ms/step - accuracy: 0.2655 - loss: 2.0498
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m316/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.2759 - loss: 1.9864
[1m318/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.2759 - loss: 1.9865[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m320/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.2759 - loss: 1.9866[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m Epoch 27/28
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m252/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2282 - loss: 2.2885 
[1m254/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2282 - loss: 2.2886
[36m(train_cnn_ray_tune pid=2857966)[0m Epoch 25/28
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 20ms/step - accuracy: 0.1733 - loss: 2.4514
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 20ms/step - accuracy: 0.1733 - loss: 2.4514
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 20ms/step - accuracy: 0.1733 - loss: 2.4514
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 25ms/step - accuracy: 0.2734 - loss: 2.0039
[1m  6/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 26ms/step - accuracy: 0.2724 - loss: 2.0244
[1m  8/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.2688 - loss: 2.0457
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m12s[0m 29ms/step - accuracy: 0.2065 - loss: 2.4110
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m12s[0m 29ms/step - accuracy: 0.2065 - loss: 2.4110
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m12s[0m 29ms/step - accuracy: 0.2064 - loss: 2.4110
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 24ms/step - accuracy: 0.1548 - loss: 2.7115[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m 10/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.2661 - loss: 2.0601[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m 49/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.2595 - loss: 2.0821
[1m 52/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.2591 - loss: 2.0837[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 29ms/step - accuracy: 0.2064 - loss: 2.4109
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 29ms/step - accuracy: 0.2064 - loss: 2.4109[32m [repeated 131x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 30ms/step - accuracy: 0.1826 - loss: 2.5638[32m [repeated 82x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 18ms/step - accuracy: 0.2633 - loss: 2.0484
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 18ms/step - accuracy: 0.2633 - loss: 2.0484[32m [repeated 145x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 42ms/step - accuracy: 0.2414 - loss: 2.2438 - val_accuracy: 0.2285 - val_loss: 2.2251[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 20ms/step - accuracy: 0.1737 - loss: 2.4512
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 20ms/step - accuracy: 0.1737 - loss: 2.4512
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.1737 - loss: 2.4512[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 95ms/step - accuracy: 0.2812 - loss: 2.0809[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 29ms/step - accuracy: 0.2063 - loss: 2.4107
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 29ms/step - accuracy: 0.2063 - loss: 2.4107
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 29ms/step - accuracy: 0.2063 - loss: 2.4107
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m300/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m7s[0m 26ms/step - accuracy: 0.3282 - loss: 1.8031
[1m302/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m7s[0m 26ms/step - accuracy: 0.3282 - loss: 1.8031[32m [repeated 97x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m474/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 34ms/step - accuracy: 0.2755 - loss: 1.9901[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m Epoch 17/24
[36m(train_cnn_ray_tune pid=2857955)[0m Epoch 20/24
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m205/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.2557 - loss: 2.1152 
[1m207/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.2557 - loss: 2.1153
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m17s[0m 25ms/step - accuracy: 0.2103 - loss: 2.3645
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m17s[0m 25ms/step - accuracy: 0.2103 - loss: 2.3645
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m17s[0m 25ms/step - accuracy: 0.2103 - loss: 2.3645
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 27ms/step - accuracy: 0.1926 - loss: 2.4757[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m121/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m17s[0m 38ms/step - accuracy: 0.2506 - loss: 2.1870[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m123/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m17s[0m 39ms/step - accuracy: 0.2506 - loss: 2.1874
[1m125/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m17s[0m 39ms/step - accuracy: 0.2506 - loss: 2.1878[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m26s[0m 31ms/step - accuracy: 0.1860 - loss: 2.5654
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m25s[0m 31ms/step - accuracy: 0.1860 - loss: 2.5655[32m [repeated 84x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m18s[0m 36ms/step - accuracy: 0.3664 - loss: 1.7067[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 29ms/step - accuracy: 0.2062 - loss: 2.4102
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 29ms/step - accuracy: 0.2062 - loss: 2.4102[32m [repeated 138x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m23s[0m 39ms/step - accuracy: 0.1897 - loss: 2.5120 - val_accuracy: 0.2104 - val_loss: 2.3511
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 29ms/step - accuracy: 0.2062 - loss: 2.4103
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 29ms/step - accuracy: 0.2062 - loss: 2.4103
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 29ms/step - accuracy: 0.2062 - loss: 2.4102[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 92ms/step - accuracy: 0.2812 - loss: 2.7121
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m31s[0m 26ms/step - accuracy: 0.2841 - loss: 1.9734 - val_accuracy: 0.2931 - val_loss: 1.9261
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:25[0m 73ms/step - accuracy: 0.3125 - loss: 2.1045
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3737 - loss: 1.9800 
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:18[0m 67ms/step - accuracy: 0.0000e+00 - loss: 3.4082
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m330/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m6s[0m 26ms/step - accuracy: 0.2571 - loss: 2.1173
[1m332/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m6s[0m 26ms/step - accuracy: 0.2572 - loss: 2.1173[32m [repeated 113x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m544/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 30ms/step - accuracy: 0.2260 - loss: 2.2994[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.0898 - loss: 3.1995     
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m367/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 26ms/step - accuracy: 0.2573 - loss: 2.1181
[1m369/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 26ms/step - accuracy: 0.2573 - loss: 2.1182
[1m371/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 26ms/step - accuracy: 0.2573 - loss: 2.1182
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 19ms/step - accuracy: 0.1875 - loss: 1.9615 
[36m(train_cnn_ray_tune pid=2857965)[0m Epoch 18/25[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m23s[0m 39ms/step - accuracy: 0.2757 - loss: 1.9915 - val_accuracy: 0.2840 - val_loss: 1.9816
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 29ms/step - accuracy: 0.2061 - loss: 2.4092[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m265/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 37ms/step - accuracy: 0.2511 - loss: 2.2033[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m 27/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 33ms/step - accuracy: 0.3001 - loss: 1.9291
[1m 29/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 33ms/step - accuracy: 0.3003 - loss: 1.9295[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 23ms/step - accuracy: 0.1524 - loss: 2.7696
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 23ms/step - accuracy: 0.1526 - loss: 2.7679[32m [repeated 123x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 176/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m21s[0m 21ms/step - accuracy: 0.3157 - loss: 1.9437[32m [repeated 124x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 25ms/step - accuracy: 0.2109 - loss: 2.3613
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 25ms/step - accuracy: 0.2109 - loss: 2.3612[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 29ms/step - accuracy: 0.2062 - loss: 2.4096
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 29ms/step - accuracy: 0.2062 - loss: 2.4096
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 29ms/step - accuracy: 0.2062 - loss: 2.4096
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 23ms/step - accuracy: 0.1741 - loss: 2.4513 - val_accuracy: 0.1735 - val_loss: 2.3593[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 72ms/step - accuracy: 0.1875 - loss: 2.4739
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 22ms/step - accuracy: 0.1927 - loss: 2.4007[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 27ms/step - accuracy: 0.1133 - loss: 2.5112     
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.1377 - loss: 2.4692
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:35[0m 82ms/step - accuracy: 0.0000e+00 - loss: 2.7086[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m521/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 26ms/step - accuracy: 0.2584 - loss: 2.1199
[1m523/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 26ms/step - accuracy: 0.2585 - loss: 2.1200[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m331/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.2514 - loss: 2.2053[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m Epoch 28/28[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m17s[0m 29ms/step - accuracy: 0.3277 - loss: 1.8032 - val_accuracy: 0.2805 - val_loss: 1.9860[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.3666 - loss: 1.7083 
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.3666 - loss: 1.7083
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 25ms/step - accuracy: 0.2112 - loss: 2.3594[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m176/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 34ms/step - accuracy: 0.2932 - loss: 1.9722[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m131/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 25ms/step - accuracy: 0.3304 - loss: 1.7739
[1m134/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 25ms/step - accuracy: 0.3304 - loss: 1.7743[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m15s[0m 19ms/step - accuracy: 0.2574 - loss: 2.0407
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m15s[0m 19ms/step - accuracy: 0.2574 - loss: 2.0406[32m [repeated 198x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m20s[0m 25ms/step - accuracy: 0.1529 - loss: 2.7326[32m [repeated 122x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.3666 - loss: 1.7084
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 36ms/step - accuracy: 0.3666 - loss: 1.7084[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m185/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 25ms/step - accuracy: 0.3307 - loss: 1.7788 
[1m188/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 25ms/step - accuracy: 0.3307 - loss: 1.7790
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m36s[0m 31ms/step - accuracy: 0.1922 - loss: 2.4770 - val_accuracy: 0.1972 - val_loss: 2.3495
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 74ms/step - accuracy: 0.3750 - loss: 1.5479
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.3750 - loss: 1.6488
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 76ms/step - accuracy: 0.3438 - loss: 2.1462
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 34ms/step - accuracy: 0.3108 - loss: 2.1544
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m39s[0m 33ms/step - accuracy: 0.2061 - loss: 2.4089 - val_accuracy: 0.2242 - val_loss: 2.3130
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 32ms/step - accuracy: 0.1875 - loss: 2.2413 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 29ms/step - accuracy: 0.1963 - loss: 2.2642
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:44[0m 90ms/step - accuracy: 0.1250 - loss: 2.3203
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m403/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 34ms/step - accuracy: 0.1862 - loss: 2.5162
[1m405/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 34ms/step - accuracy: 0.1862 - loss: 2.5161[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m228/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 25ms/step - accuracy: 0.3313 - loss: 1.7808[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m Epoch 12/21[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m18s[0m 31ms/step - accuracy: 0.2588 - loss: 2.1206 - val_accuracy: 0.2470 - val_loss: 2.1314
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 32ms/step - accuracy: 0.1924 - loss: 2.4109
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 31ms/step - accuracy: 0.1927 - loss: 2.4106
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 31ms/step - accuracy: 0.1929 - loss: 2.4105

Trial status: 15 RUNNING | 5 TERMINATED
Current time: 2025-11-07 14:03:03. Total running time: 10min 31s
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_a058a    RUNNING              3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21                                              │
│ trial_a058a    RUNNING              3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26                                              │
│ trial_a058a    RUNNING              2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21                                              │
│ trial_a058a    RUNNING              3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24                                              │
│ trial_a058a    RUNNING              2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23                                              │
│ trial_a058a    RUNNING              3   adam            relu                                   16                 64                  3                 1          0.000164705         24                                              │
│ trial_a058a    RUNNING              3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21                                              │
│ trial_a058a    RUNNING              3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24                                              │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25        1            370.735         0.272525 │
│ trial_a058a    TERMINATED           3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15        1            530.858         0.249029 │
│ trial_a058a    TERMINATED           3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23        1            498.889         0.264015 │
│ trial_a058a    TERMINATED           2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27        1            602.129         0.183349 │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24        1            524.007         0.272155 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 36ms/step - accuracy: 0.3669 - loss: 1.7085[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m 99/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m13s[0m 29ms/step - accuracy: 0.2646 - loss: 2.1425[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m118/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m13s[0m 29ms/step - accuracy: 0.2637 - loss: 2.1433
[1m120/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m13s[0m 29ms/step - accuracy: 0.2636 - loss: 2.1434[32m [repeated 74x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m16s[0m 25ms/step - accuracy: 0.1519 - loss: 2.7234
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m16s[0m 25ms/step - accuracy: 0.1519 - loss: 2.7233[32m [repeated 181x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 20ms/step - accuracy: 0.2597 - loss: 2.0359[32m [repeated 174x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 36ms/step - accuracy: 0.3669 - loss: 1.7084
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 36ms/step - accuracy: 0.3669 - loss: 1.7084[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m130/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m13s[0m 29ms/step - accuracy: 0.2632 - loss: 2.1437
[1m132/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m12s[0m 29ms/step - accuracy: 0.2631 - loss: 2.1438
[1m134/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m12s[0m 29ms/step - accuracy: 0.2630 - loss: 2.1438
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m296/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.2899 - loss: 1.9805 
[1m297/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.2899 - loss: 1.9806
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m381/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 35ms/step - accuracy: 0.2886 - loss: 1.9831
[1m383/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 35ms/step - accuracy: 0.2885 - loss: 1.9832[32m [repeated 105x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m381/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 30ms/step - accuracy: 0.2229 - loss: 2.3060[32m [repeated 106x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 28ms/step - accuracy: 0.2113 - loss: 2.3581 - val_accuracy: 0.2357 - val_loss: 2.1753
[36m(train_cnn_ray_tune pid=2857944)[0m Epoch 14/16
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:36[0m 82ms/step - accuracy: 0.0625 - loss: 2.5933
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1562 - loss: 2.4514 
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 20ms/step - accuracy: 0.2598 - loss: 2.0354
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 20ms/step - accuracy: 0.2598 - loss: 2.0353
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m10s[0m 20ms/step - accuracy: 0.2599 - loss: 2.0353
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 21ms/step - accuracy: 0.1743 - loss: 2.4488
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 21ms/step - accuracy: 0.1743 - loss: 2.4488
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 21ms/step - accuracy: 0.1743 - loss: 2.4487
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 43ms/step - accuracy: 0.2515 - loss: 2.2078 - val_accuracy: 0.2387 - val_loss: 2.2086
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 21ms/step - accuracy: 0.1744 - loss: 2.4488[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m222/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m10s[0m 28ms/step - accuracy: 0.2624 - loss: 2.1408[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m225/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m10s[0m 28ms/step - accuracy: 0.2624 - loss: 2.1406
[1m228/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.2624 - loss: 2.1405 [32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 85ms/step - accuracy: 0.3125 - loss: 2.2434
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m26s[0m 30ms/step - accuracy: 0.2003 - loss: 2.4008
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m26s[0m 30ms/step - accuracy: 0.2003 - loss: 2.4008[32m [repeated 163x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 25ms/step - accuracy: 0.1515 - loss: 2.7174[32m [repeated 83x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 19ms/step - accuracy: 0.2608 - loss: 2.0315
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 19ms/step - accuracy: 0.2608 - loss: 2.0314[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m342/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m6s[0m 26ms/step - accuracy: 0.2630 - loss: 2.1356
[1m344/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m6s[0m 26ms/step - accuracy: 0.2630 - loss: 2.1356
[1m346/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m6s[0m 26ms/step - accuracy: 0.2630 - loss: 2.1355
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 25ms/step - accuracy: 0.1514 - loss: 2.7168 
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 25ms/step - accuracy: 0.1514 - loss: 2.7168
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m538/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 34ms/step - accuracy: 0.2867 - loss: 1.9848
[1m540/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 34ms/step - accuracy: 0.2866 - loss: 1.9848[32m [repeated 112x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m417/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 26ms/step - accuracy: 0.2630 - loss: 2.1334[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m Epoch 21/24[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 307ms/step
[1m 6/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step  
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m12/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m18/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m22/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m27/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m32/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m36/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m41/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m46/86[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=2857954)[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=2857954)[0m 
[1m66/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 11ms/step
[1m71/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m76/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m82/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m48s[0m 41ms/step - accuracy: 0.3671 - loss: 1.7081 - val_accuracy: 0.2638 - val_loss: 2.0889
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m17s[0m 29ms/step - accuracy: 0.3340 - loss: 1.7887 - val_accuracy: 0.2575 - val_loss: 2.0347[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 23ms/step - accuracy: 0.3008 - loss: 1.9471
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 23ms/step - accuracy: 0.3008 - loss: 1.9471
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 23ms/step - accuracy: 0.3008 - loss: 1.9471
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 20ms/step - accuracy: 0.1739 - loss: 2.4475[32m [repeated 97x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m137/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 35ms/step - accuracy: 0.2638 - loss: 2.1640[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m139/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 35ms/step - accuracy: 0.2639 - loss: 2.1641
[1m141/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 35ms/step - accuracy: 0.2639 - loss: 2.1642[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:43[0m 89ms/step - accuracy: 0.5000 - loss: 1.3279[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 43ms/step - accuracy: 0.4236 - loss: 1.4921 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 42ms/step - accuracy: 0.4304 - loss: 1.5096
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 42ms/step
[1m  7/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m20s[0m 29ms/step - accuracy: 0.2028 - loss: 2.3956
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m20s[0m 29ms/step - accuracy: 0.2028 - loss: 2.3955[32m [repeated 100x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m19s[0m 22ms/step - accuracy: 0.2298 - loss: 2.2972[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 24ms/step - accuracy: 0.1513 - loss: 2.7141
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 24ms/step - accuracy: 0.1514 - loss: 2.7141[32m [repeated 148x across cluster][0m
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m 12/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[1m 16/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m 19/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 24/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m 29/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m 34/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[1m 38/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m 43/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 48/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m 52/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 57/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m 62/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 69/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m 75/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[1m 81/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m 86/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m 91/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m 95/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m100/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m104/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 11ms/step
[1m109/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m115/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 11ms/step
[1m120/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857954)[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=2857954)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m126/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 11ms/step
[1m131/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m136/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m141/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 11ms/step
[1m146/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m152/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 11ms/step
[1m157/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m161/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 11ms/step
[1m167/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857954)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 11ms/step

Trial trial_a058a finished iteration 1 at 2025-11-07 14:03:16. Total running time: 10min 43s
╭──────────────────────────────────────╮
│ Trial trial_a058a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             640.594 │
│ time_total_s                 640.594 │
│ training_iteration                 1 │
│ val_accuracy                 0.25754 │
╰──────────────────────────────────────╯

Trial trial_a058a completed after 1 iterations at 2025-11-07 14:03:16. Total running time: 10min 43s
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m579/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 26ms/step - accuracy: 0.2632 - loss: 2.1297
[1m581/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 26ms/step - accuracy: 0.2632 - loss: 2.1297[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 26ms/step - accuracy: 0.2632 - loss: 2.1296[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:34[0m 81ms/step - accuracy: 0.3125 - loss: 2.0514
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 18ms/step - accuracy: 0.2977 - loss: 2.0597 
[36m(train_cnn_ray_tune pid=2857966)[0m Epoch 27/28[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 21ms/step - accuracy: 0.2616 - loss: 2.0286 - val_accuracy: 0.2883 - val_loss: 1.9286
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m271/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1895 - loss: 2.4665 
[1m273/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1895 - loss: 2.4666
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m17s[0m 29ms/step - accuracy: 0.2632 - loss: 2.1296 - val_accuracy: 0.2503 - val_loss: 2.1196[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 24ms/step - accuracy: 0.1518 - loss: 2.7109[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m114/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m14s[0m 32ms/step - accuracy: 0.2862 - loss: 1.9901[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m289/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 35ms/step - accuracy: 0.2626 - loss: 2.1759
[1m291/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 35ms/step - accuracy: 0.2626 - loss: 2.1760[32m [repeated 124x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 74ms/step - accuracy: 0.3125 - loss: 2.0865[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m79s[0m 35ms/step - accuracy: 0.1883 - loss: 2.5605 - val_accuracy: 0.2176 - val_loss: 2.2966
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 29ms/step - accuracy: 0.2035 - loss: 2.3946
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 29ms/step - accuracy: 0.2035 - loss: 2.3945[32m [repeated 128x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 17ms/step - accuracy: 0.2668 - loss: 2.0399[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 27ms/step - accuracy: 0.1864 - loss: 2.4981
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 27ms/step - accuracy: 0.1864 - loss: 2.4980[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 18ms/step - accuracy: 0.2878 - loss: 1.8942 
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m343/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.1894 - loss: 2.4706
[1m345/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.1894 - loss: 2.4707[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m353/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 35ms/step - accuracy: 0.2619 - loss: 2.1784[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:32[0m 79ms/step - accuracy: 0.1250 - loss: 2.5151
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 19ms/step - accuracy: 0.1497 - loss: 2.5351 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m Epoch 16/26[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 20ms/step - accuracy: 0.1848 - loss: 2.4111
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 20ms/step - accuracy: 0.1847 - loss: 2.4110
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 20ms/step - accuracy: 0.1846 - loss: 2.4110
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1536 - loss: 2.5874 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1403 - loss: 2.6622
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m191/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 25ms/step - accuracy: 0.2601 - loss: 2.0987 
[1m194/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 25ms/step - accuracy: 0.2602 - loss: 2.0988
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 27ms/step - accuracy: 0.1874 - loss: 2.4947[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m252/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m10s[0m 33ms/step - accuracy: 0.2923 - loss: 1.9756[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m262/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m10s[0m 33ms/step - accuracy: 0.2923 - loss: 1.9749
[1m264/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 33ms/step - accuracy: 0.2923 - loss: 1.9747[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:33[0m 80ms/step - accuracy: 0.1875 - loss: 2.4748[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 27ms/step - accuracy: 0.1518 - loss: 2.7109 - val_accuracy: 0.1693 - val_loss: 2.4700[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m  45/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1516 - loss: 2.6242
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1526 - loss: 2.6222[32m [repeated 208x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m18s[0m 20ms/step - accuracy: 0.1830 - loss: 2.4122[32m [repeated 133x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2042 - loss: 2.3931
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2042 - loss: 2.3930[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 27ms/step - accuracy: 0.1878 - loss: 2.4931
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 27ms/step - accuracy: 0.1878 - loss: 2.4931
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 27ms/step - accuracy: 0.1878 - loss: 2.4931
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m485/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 36ms/step - accuracy: 0.2606 - loss: 2.1821
[1m487/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 36ms/step - accuracy: 0.2606 - loss: 2.1822[32m [repeated 105x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m429/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 29ms/step - accuracy: 0.2273 - loss: 2.2899[32m [repeated 94x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m339/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m6s[0m 26ms/step - accuracy: 0.2640 - loss: 2.0952
[1m341/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m6s[0m 26ms/step - accuracy: 0.2640 - loss: 2.0951
[1m343/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m6s[0m 26ms/step - accuracy: 0.2641 - loss: 2.0951
[36m(train_cnn_ray_tune pid=2857942)[0m Epoch 15/21
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 29ms/step - accuracy: 0.2047 - loss: 2.3919[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m274/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 33ms/step - accuracy: 0.2923 - loss: 1.9741
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m280/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 33ms/step - accuracy: 0.2922 - loss: 1.9738
[1m282/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2922 - loss: 1.9737 [32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m26s[0m 31ms/step - accuracy: 0.2051 - loss: 2.4957
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m26s[0m 31ms/step - accuracy: 0.2051 - loss: 2.4959[32m [repeated 165x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m22s[0m 25ms/step - accuracy: 0.1590 - loss: 2.6482[32m [repeated 139x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 29ms/step - accuracy: 0.2048 - loss: 2.3919
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 29ms/step - accuracy: 0.2048 - loss: 2.3919[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m36s[0m 31ms/step - accuracy: 0.1879 - loss: 2.4928 - val_accuracy: 0.2007 - val_loss: 2.3404
[36m(train_cnn_ray_tune pid=2857961)[0m Epoch 14/22
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:23[0m 72ms/step - accuracy: 0.2500 - loss: 2.1890
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2201 - loss: 2.3877 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2253 - loss: 2.3951
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 18ms/step - accuracy: 0.2643 - loss: 2.0254
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 18ms/step - accuracy: 0.2643 - loss: 2.0253
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 18ms/step - accuracy: 0.2643 - loss: 2.0252
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m486/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 33ms/step - accuracy: 0.2909 - loss: 1.9691
[1m489/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 33ms/step - accuracy: 0.2909 - loss: 1.9691[32m [repeated 114x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m550/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 25ms/step - accuracy: 0.2646 - loss: 2.0932[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m  45/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 23ms/step - accuracy: 0.2080 - loss: 2.4430
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 23ms/step - accuracy: 0.2077 - loss: 2.4429
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 23ms/step - accuracy: 0.2074 - loss: 2.4429
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m22s[0m 38ms/step - accuracy: 0.1893 - loss: 2.4785 - val_accuracy: 0.2096 - val_loss: 2.3501
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 76ms/step - accuracy: 0.3125 - loss: 2.4341
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 27ms/step - accuracy: 0.2396 - loss: 2.4842
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 33ms/step - accuracy: 0.3050 - loss: 2.0507
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  7/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 34ms/step - accuracy: 0.2977 - loss: 2.0750
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  9/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 35ms/step - accuracy: 0.2941 - loss: 2.0952
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 11/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 36ms/step - accuracy: 0.2939 - loss: 2.1064
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 18ms/step - accuracy: 0.2638 - loss: 2.0211
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 18ms/step - accuracy: 0.2638 - loss: 2.0210
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 18ms/step - accuracy: 0.2638 - loss: 2.0210

Trial status: 14 RUNNING | 6 TERMINATED
Current time: 2025-11-07 14:03:33. Total running time: 11min 1s
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_a058a    RUNNING              3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21                                              │
│ trial_a058a    RUNNING              3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21                                              │
│ trial_a058a    RUNNING              3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24                                              │
│ trial_a058a    RUNNING              2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23                                              │
│ trial_a058a    RUNNING              3   adam            relu                                   16                 64                  3                 1          0.000164705         24                                              │
│ trial_a058a    RUNNING              3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21                                              │
│ trial_a058a    RUNNING              3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24                                              │
│ trial_a058a    TERMINATED           2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28        1            640.594         0.257539 │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25        1            370.735         0.272525 │
│ trial_a058a    TERMINATED           3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15        1            530.858         0.249029 │
│ trial_a058a    TERMINATED           3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23        1            498.889         0.264015 │
│ trial_a058a    TERMINATED           2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27        1            602.129         0.183349 │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24        1            524.007         0.272155 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 18ms/step - accuracy: 0.2637 - loss: 2.0202[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 38/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 41ms/step - accuracy: 0.2848 - loss: 2.1314
[1m 40/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 40ms/step - accuracy: 0.2840 - loss: 2.1331[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m19s[0m 34ms/step - accuracy: 0.3816 - loss: 1.6851
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m19s[0m 34ms/step - accuracy: 0.3816 - loss: 1.6851[32m [repeated 171x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m16s[0m 24ms/step - accuracy: 0.1577 - loss: 2.6649[32m [repeated 84x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 19ms/step - accuracy: 0.1804 - loss: 2.4264
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 19ms/step - accuracy: 0.1804 - loss: 2.4264[32m [repeated 116x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m Epoch 28/28[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 64ms/step - accuracy: 0.3438 - loss: 2.0146[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 22ms/step - accuracy: 0.2901 - loss: 1.9391 
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 22ms/step - accuracy: 0.2901 - loss: 1.9391
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m582/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 32ms/step - accuracy: 0.2910 - loss: 1.9677
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 32ms/step - accuracy: 0.2910 - loss: 1.9677[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m568/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 32ms/step - accuracy: 0.2910 - loss: 1.9678[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m22s[0m 37ms/step - accuracy: 0.2910 - loss: 1.9677 - val_accuracy: 0.2770 - val_loss: 1.9796[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 86ms/step - accuracy: 0.3125 - loss: 1.9370
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 34ms/step - accuracy: 0.3177 - loss: 2.0017
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 447ms/step
[1m 5/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step  
[1m 8/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m140/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 36ms/step - accuracy: 0.2705 - loss: 2.1506[32m [repeated 58x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m14/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m18/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 14ms/step
[1m22/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m26/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m30/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 14ms/step
[1m34/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m38/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 14ms/step
[1m43/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m47/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 14ms/step
[1m50/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m31s[0m 26ms/step - accuracy: 0.2233 - loss: 2.3126 - val_accuracy: 0.2383 - val_loss: 2.1629
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m54/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 14ms/step
[1m58/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1224 - loss: 2.4642 
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m62/86[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=2857951)[0m 
[1m70/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 28ms/step - accuracy: 0.2951 - loss: 2.1919 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.2546 - loss: 2.2743
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.2392 - loss: 2.3088
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m74/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m78/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 14ms/step
[1m82/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m85/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m222/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.2171 - loss: 2.2982 
[1m224/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.2172 - loss: 2.2980
[36m(train_cnn_ray_tune pid=2857951)[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=2857943)[0m 
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.2910 - loss: 1.9382[32m [repeated 31x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m184/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m14s[0m 36ms/step - accuracy: 0.2699 - loss: 2.1503
[1m186/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m14s[0m 36ms/step - accuracy: 0.2699 - loss: 2.1503[32m [repeated 119x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 55ms/step
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 23ms/step - accuracy: 0.1572 - loss: 2.6693
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 23ms/step - accuracy: 0.1572 - loss: 2.6694[32m [repeated 128x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m13s[0m 34ms/step - accuracy: 0.3823 - loss: 1.6827[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 19ms/step - accuracy: 0.1803 - loss: 2.4285
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 19ms/step - accuracy: 0.1803 - loss: 2.4285[32m [repeated 84x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m  5/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m  9/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m 12/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[1m 16/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m 20/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[1m 24/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 19ms/step - accuracy: 0.1803 - loss: 2.4285
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 19ms/step - accuracy: 0.1803 - loss: 2.4285
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 19ms/step - accuracy: 0.1803 - loss: 2.4285
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m 29/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[1m 32/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m 35/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 39/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m 44/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 49/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m 53/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 57/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m 61/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 65/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m 69/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 73/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m 77/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 81/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 18ms/step - accuracy: 0.2682 - loss: 2.3548 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 19ms/step - accuracy: 0.2804 - loss: 2.2099
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m 85/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 89/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 92/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m 95/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 99/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857965)[0m Epoch 20/25[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m102/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 15ms/step
[1m106/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:34[0m 81ms/step - accuracy: 0.1875 - loss: 2.8537[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m263/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.2925 - loss: 2.0511
[1m265/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.2924 - loss: 2.0511
[1m267/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.2924 - loss: 2.0511
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m110/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 15ms/step
[1m115/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m119/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 15ms/step
[1m123/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m127/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 15ms/step
[1m131/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m305/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m7s[0m 28ms/step - accuracy: 0.2194 - loss: 2.2921
[1m307/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m7s[0m 28ms/step - accuracy: 0.2195 - loss: 2.2919[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m275/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.2922 - loss: 2.0512[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m135/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 15ms/step
[1m139/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m143/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 15ms/step
[1m148/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m152/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 15ms/step
[1m156/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m160/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 15ms/step
[1m165/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2857951)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 15ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 15ms/step

Trial trial_a058a finished iteration 1 at 2025-11-07 14:03:42. Total running time: 11min 9s
[36m(train_cnn_ray_tune pid=2857951)[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=2857951)[0m   _log_deprecation_warning(
╭──────────────────────────────────────╮
│ Trial trial_a058a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             666.513 │
│ time_total_s                 666.513 │
│ training_iteration                 1 │
│ val_accuracy                 0.27697 │
╰──────────────────────────────────────╯

Trial trial_a058a completed after 1 iterations at 2025-11-07 14:03:42. Total running time: 11min 9s
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m282/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.2697 - loss: 2.1514[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 20ms/step - accuracy: 0.2636 - loss: 2.0183 - val_accuracy: 0.2833 - val_loss: 1.9236[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.3828 - loss: 1.6814[32m [repeated 23x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m300/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.2695 - loss: 2.1519
[1m302/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.2694 - loss: 2.1520[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 18ms/step - accuracy: 0.2761 - loss: 2.0349
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 18ms/step - accuracy: 0.2761 - loss: 2.0342[32m [repeated 156x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m26s[0m 28ms/step - accuracy: 0.2168 - loss: 2.3362[32m [repeated 134x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2032 - loss: 2.4986
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2032 - loss: 2.4986[32m [repeated 97x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:41[0m 87ms/step - accuracy: 0.3125 - loss: 2.0575
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 17ms/step - accuracy: 0.2539 - loss: 2.2995 
[36m(train_cnn_ray_tune pid=2857960)[0m Epoch 18/23
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m396/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 35ms/step - accuracy: 0.2684 - loss: 2.1534
[1m398/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 35ms/step - accuracy: 0.2684 - loss: 2.1534[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m499/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 28ms/step - accuracy: 0.2225 - loss: 2.2834[32m [repeated 60x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m304/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.2694 - loss: 2.1520 [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m26s[0m 22ms/step - accuracy: 0.1803 - loss: 2.4289 - val_accuracy: 0.1761 - val_loss: 2.3611
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 23ms/step - accuracy: 0.1565 - loss: 2.6728[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 28ms/step - accuracy: 0.2175 - loss: 2.3388
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 28ms/step - accuracy: 0.2175 - loss: 2.3388
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 28ms/step - accuracy: 0.2175 - loss: 2.3389
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m11s[0m 17ms/step - accuracy: 0.2717 - loss: 2.0144
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m11s[0m 17ms/step - accuracy: 0.2716 - loss: 2.0144[32m [repeated 157x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m11s[0m 17ms/step - accuracy: 0.2716 - loss: 2.0143[32m [repeated 78x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 34ms/step - accuracy: 0.3834 - loss: 1.6792
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 34ms/step - accuracy: 0.3834 - loss: 1.6792[32m [repeated 93x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m29s[0m 25ms/step - accuracy: 0.2926 - loss: 1.9362 - val_accuracy: 0.2870 - val_loss: 1.9300
[36m(train_cnn_ray_tune pid=2857943)[0m Epoch 17/26
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 17ms/step - accuracy: 0.2712 - loss: 2.0134 
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 17ms/step - accuracy: 0.2712 - loss: 2.0133
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:19[0m 68ms/step - accuracy: 0.5000 - loss: 1.4418
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 17ms/step - accuracy: 0.3765 - loss: 1.7591 
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m18s[0m 31ms/step - accuracy: 0.2232 - loss: 2.2819 - val_accuracy: 0.2242 - val_loss: 2.2546
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 81ms/step - accuracy: 0.3750 - loss: 2.0800
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 26ms/step - accuracy: 0.3802 - loss: 2.0706
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 330ms/step
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m 7/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step  
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 17/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 24ms/step - accuracy: 0.3152 - loss: 2.1778
[1m 19/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.3110 - loss: 2.1838
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m12/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m18/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m23/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m27/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m554/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 34ms/step - accuracy: 0.2676 - loss: 2.1543
[1m556/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 34ms/step - accuracy: 0.2676 - loss: 2.1543[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m552/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 34ms/step - accuracy: 0.2676 - loss: 2.1542[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 25/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 24ms/step - accuracy: 0.3007 - loss: 2.1947
[1m 27/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 24ms/step - accuracy: 0.2981 - loss: 2.1961
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m32/86[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=2857964)[0m 
[1m 30/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.2941 - loss: 2.1989
[1m 33/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.2908 - loss: 2.2015
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m43/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m49/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m54/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 11ms/step
[1m60/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m65/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m70/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 10ms/step
[1m75/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m81/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 50/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 24ms/step - accuracy: 0.2789 - loss: 2.2116
[1m 53/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 24ms/step - accuracy: 0.2774 - loss: 2.2131
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.3838 - loss: 1.6777
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.3838 - loss: 1.6777
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.3838 - loss: 1.6776
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 71/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 24ms/step - accuracy: 0.2694 - loss: 2.2230
[1m 74/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 24ms/step - accuracy: 0.2683 - loss: 2.2244
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 39ms/step
[1m  7/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step 
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m 13/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 68/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 24ms/step - accuracy: 0.2705 - loss: 2.2215[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 77/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 24ms/step - accuracy: 0.2673 - loss: 2.2257
[1m 81/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 23ms/step - accuracy: 0.2662 - loss: 2.2270
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m 19/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[1m 26/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 84/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 23ms/step - accuracy: 0.2654 - loss: 2.2281
[1m 87/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 23ms/step - accuracy: 0.2645 - loss: 2.2292
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 69ms/step - accuracy: 0.2500 - loss: 2.4452
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m 33/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[1m 40/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 90/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 23ms/step - accuracy: 0.2636 - loss: 2.2303
[1m 93/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 23ms/step - accuracy: 0.2627 - loss: 2.2314
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m 47/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[1m 54/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 96/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 22ms/step - accuracy: 0.2619 - loss: 2.2324
[1m 99/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 22ms/step - accuracy: 0.2611 - loss: 2.2333
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m 60/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m 66/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 16ms/step - accuracy: 0.1354 - loss: 2.7334 
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m 73/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m 79/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m 85/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m 91/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m 99/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m106/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 8ms/step
[1m113/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m120/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 8ms/step
[1m127/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m126/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m9s[0m 22ms/step - accuracy: 0.2562 - loss: 2.2383 
[1m129/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m9s[0m 22ms/step - accuracy: 0.2558 - loss: 2.2388
[36m(train_cnn_ray_tune pid=2857966)[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=2857966)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m134/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 8ms/step
[1m141/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m148/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 8ms/step
[1m155/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857966)[0m 
[1m161/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 8ms/step
[1m168/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 8ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

Trial trial_a058a finished iteration 1 at 2025-11-07 14:03:54. Total running time: 11min 21s
╭──────────────────────────────────────╮
│ Trial trial_a058a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             678.664 │
│ time_total_s                 678.664 │
│ training_iteration                 1 │
│ val_accuracy                  0.2494 │
╰──────────────────────────────────────╯

Trial trial_a058a completed after 1 iterations at 2025-11-07 14:03:54. Total running time: 11min 21s
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 21ms/step - accuracy: 0.2217 - loss: 2.2914[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m  93/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 16ms/step - accuracy: 0.1453 - loss: 2.6814
[1m  96/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 16ms/step - accuracy: 0.1456 - loss: 2.6803[32m [repeated 142x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m16s[0m 18ms/step - accuracy: 0.3108 - loss: 1.9035[32m [repeated 89x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 16ms/step - accuracy: 0.2699 - loss: 2.0107
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 16ms/step - accuracy: 0.2699 - loss: 2.0107[32m [repeated 100x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m30s[0m 26ms/step - accuracy: 0.1564 - loss: 2.6730 - val_accuracy: 0.1706 - val_loss: 2.4650
[36m(train_cnn_ray_tune pid=2857952)[0m Epoch 20/24[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 26ms/step - accuracy: 0.2517 - loss: 2.1144
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 26ms/step - accuracy: 0.2423 - loss: 2.0906
[1m  7/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 26ms/step - accuracy: 0.2436 - loss: 2.0773
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 16ms/step - accuracy: 0.1954 - loss: 2.4080 
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 16ms/step - accuracy: 0.1953 - loss: 2.4081[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m22s[0m 38ms/step - accuracy: 0.2673 - loss: 2.1548 - val_accuracy: 0.2348 - val_loss: 2.1846[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m37s[0m 32ms/step - accuracy: 0.2035 - loss: 2.4984 - val_accuracy: 0.2228 - val_loss: 2.2673
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2826 - loss: 2.1593 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2641 - loss: 2.2876
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 66/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 26ms/step - accuracy: 0.2734 - loss: 2.0892
[1m 68/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 26ms/step - accuracy: 0.2732 - loss: 2.0903[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m266/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.2442 - loss: 2.2555
[1m269/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.2441 - loss: 2.2557[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m257/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.2446 - loss: 2.2548[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 16ms/step - accuracy: 0.1942 - loss: 2.4090
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 16ms/step - accuracy: 0.1941 - loss: 2.4090
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 16ms/step - accuracy: 0.1941 - loss: 2.4091[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 418ms/step
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m108/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 27ms/step - accuracy: 0.2708 - loss: 2.1060
[1m110/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 27ms/step - accuracy: 0.2707 - loss: 2.1066
[1m112/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 27ms/step - accuracy: 0.2706 - loss: 2.1073
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 6/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step  
[1m10/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m14/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m18/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m22/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 82/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 26ms/step - accuracy: 0.2723 - loss: 2.0964[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m26/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 14ms/step
[1m31/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 64ms/step - accuracy: 0.3750 - loss: 1.9695[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m36/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[1m40/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m44/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 13ms/step
[1m49/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 13ms/step
[1m57/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m61/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 13ms/step
[1m65/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m70/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 13ms/step
[1m74/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m79/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 13ms/step
[1m83/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m167/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.2005 - loss: 2.4852 
[1m169/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.2005 - loss: 2.4850
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 18ms/step
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m167/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 26ms/step - accuracy: 0.2688 - loss: 2.1167
[1m169/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 26ms/step - accuracy: 0.2687 - loss: 2.1169
[1m171/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 26ms/step - accuracy: 0.2687 - loss: 2.1172
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 41ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m  6/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[1m 12/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 16/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 17ms/step - accuracy: 0.3062 - loss: 1.9083[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m180/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 26ms/step - accuracy: 0.2687 - loss: 2.1182
[1m182/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 26ms/step - accuracy: 0.2687 - loss: 2.1184
[1m184/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 26ms/step - accuracy: 0.2686 - loss: 2.1186
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 21/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 25/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 30/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 17ms/step - accuracy: 0.1512 - loss: 2.6698
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 17ms/step - accuracy: 0.1512 - loss: 2.6697[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 22ms/step - accuracy: 0.2151 - loss: 2.4882[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.2152 - loss: 2.3426
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.2152 - loss: 2.3426[32m [repeated 141x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m Epoch 12/15
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 35/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 40/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 45/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 50/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 55/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 60/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 64/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 68/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m204/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.2685 - loss: 2.1206 
[1m207/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.2685 - loss: 2.1209
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 72/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 77/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 82/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 87/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m 92/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 12ms/step
[1m 97/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m102/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 12ms/step
[1m107/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m112/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 12ms/step
[1m117/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m122/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 12ms/step
[1m127/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857965)[0m Epoch 21/25
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m132/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 12ms/step
[1m137/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m142/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 12ms/step
[1m147/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m151/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m156/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step
[1m160/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857963)[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=2857963)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m245/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.2682 - loss: 2.1243
[1m247/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.2682 - loss: 2.1245
[1m249/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.2682 - loss: 2.1246
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m165/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m20s[0m 17ms/step - accuracy: 0.2692 - loss: 2.0086 - val_accuracy: 0.2901 - val_loss: 1.9172[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857963)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 12ms/step

Trial trial_a058a finished iteration 1 at 2025-11-07 14:04:01. Total running time: 11min 28s
╭──────────────────────────────────────╮
│ Trial trial_a058a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             685.685 │
│ time_total_s                 685.685 │
│ training_iteration                 1 │
│ val_accuracy                 0.28511 │
╰──────────────────────────────────────╯

Trial trial_a058a completed after 1 iterations at 2025-11-07 14:04:01. Total running time: 11min 28s
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 13ms/step - accuracy: 0.2025 - loss: 2.0805 
[1m  10/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.2217 - loss: 2.0663
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m196/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 26ms/step - accuracy: 0.2686 - loss: 2.1197
[1m198/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 26ms/step - accuracy: 0.2686 - loss: 2.1199[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 64ms/step - accuracy: 0.0625 - loss: 2.4099
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 18ms/step - accuracy: 0.1055 - loss: 2.4349 
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m268/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.2682 - loss: 2.1258
[1m270/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.2683 - loss: 2.1259[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m362/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 24ms/step - accuracy: 0.1990 - loss: 2.4762[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 16ms/step - accuracy: 0.1911 - loss: 2.4126
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 16ms/step - accuracy: 0.1911 - loss: 2.4126
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 16ms/step - accuracy: 0.1910 - loss: 2.4126
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m201/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 26ms/step - accuracy: 0.2685 - loss: 2.1202[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 59ms/step - accuracy: 0.1250 - loss: 2.2991

Trial status: 11 RUNNING | 9 TERMINATED
Current time: 2025-11-07 14:04:04. Total running time: 11min 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_a058a    RUNNING              3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21                                              │
│ trial_a058a    RUNNING              3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21                                              │
│ trial_a058a    RUNNING              3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23                                              │
│ trial_a058a    RUNNING              3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24                                              │
│ trial_a058a    TERMINATED           2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28        1            640.594         0.257539 │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25        1            370.735         0.272525 │
│ trial_a058a    TERMINATED           3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15        1            530.858         0.249029 │
│ trial_a058a    TERMINATED           2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28        1            678.664         0.249399 │
│ trial_a058a    TERMINATED           3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23        1            498.889         0.264015 │
│ trial_a058a    TERMINATED           2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27        1            602.129         0.183349 │
│ trial_a058a    TERMINATED           3   adam            relu                                   16                 64                  3                 1          0.000164705         24        1            685.685         0.285106 │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24        1            524.007         0.272155 │
│ trial_a058a    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21        1            666.513         0.276966 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 59ms/step - accuracy: 0.1875 - loss: 2.2380
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 17ms/step - accuracy: 0.1552 - loss: 2.4040 
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 16ms/step - accuracy: 0.1513 - loss: 2.4564
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 16ms/step - accuracy: 0.3054 - loss: 1.9091[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 299/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 13ms/step - accuracy: 0.2842 - loss: 1.9697
[1m 303/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 13ms/step - accuracy: 0.2842 - loss: 1.9697[32m [repeated 112x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 168/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 18ms/step - accuracy: 0.1960 - loss: 2.4314[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 23ms/step - accuracy: 0.2148 - loss: 2.3438
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 23ms/step - accuracy: 0.2148 - loss: 2.3439[32m [repeated 123x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m14s[0m 24ms/step - accuracy: 0.2384 - loss: 2.2671 - val_accuracy: 0.2246 - val_loss: 2.2525
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 429ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 8/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step   
[1m14/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m21/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m28/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m34/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m41/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m47/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857960)[0m Epoch 19/23[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m59/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 8ms/step
[1m65/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 62ms/step - accuracy: 0.1250 - loss: 2.7389
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 13ms/step - accuracy: 0.1335 - loss: 2.5248 
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 13ms/step - accuracy: 0.1608 - loss: 2.4546
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m72/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m78/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 8ms/step
[1m84/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m20s[0m 17ms/step - accuracy: 0.1889 - loss: 2.4140 - val_accuracy: 0.1693 - val_loss: 2.3647[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 40ms/step
[1m  8/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step 
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m472/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 25ms/step - accuracy: 0.2691 - loss: 2.1319
[1m475/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 25ms/step - accuracy: 0.2691 - loss: 2.1320[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m484/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 25ms/step - accuracy: 0.2692 - loss: 2.1322[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 15/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[1m 22/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 28/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 35/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[1m 42/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 48/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m 55/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857964)[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=2857964)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 62/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m 69/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 76/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m 82/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m 89/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m 96/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m14s[0m 18ms/step - accuracy: 0.1985 - loss: 2.4343
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m14s[0m 18ms/step - accuracy: 0.1985 - loss: 2.4343
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m14s[0m 18ms/step - accuracy: 0.1986 - loss: 2.4343
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m103/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 8ms/step
[1m110/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m116/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 8ms/step
[1m123/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m129/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 8ms/step
[1m136/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m143/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 8ms/step
[1m151/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 8ms/step
[1m157/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m162/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 8ms/step
[1m168/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857964)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

Trial trial_a058a finished iteration 1 at 2025-11-07 14:04:08. Total running time: 11min 35s
╭──────────────────────────────────────╮
│ Trial trial_a058a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s              692.81 │
│ time_total_s                  692.81 │
│ training_iteration                 1 │
│ val_accuracy                 0.22461 │
╰──────────────────────────────────────╯

Trial trial_a058a completed after 1 iterations at 2025-11-07 14:04:08. Total running time: 11min 35s
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 19ms/step - accuracy: 0.2493 - loss: 2.3820
[1m  7/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 20ms/step - accuracy: 0.2368 - loss: 2.4314
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 10/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 20ms/step - accuracy: 0.2291 - loss: 2.4536
[1m 13/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 20ms/step - accuracy: 0.2255 - loss: 2.4665
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 16/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 20ms/step - accuracy: 0.2228 - loss: 2.4713
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 19/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 20ms/step - accuracy: 0.2198 - loss: 2.4738
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 21/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.2179 - loss: 2.4763
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 24/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.2152 - loss: 2.4808
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:18[0m 67ms/step - accuracy: 0.1875 - loss: 2.2690[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 27/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 20ms/step - accuracy: 0.2137 - loss: 2.4819
[1m 30/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 20ms/step - accuracy: 0.2121 - loss: 2.4824
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 19ms/step - accuracy: 0.1641 - loss: 2.3850 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 19ms/step - accuracy: 0.1653 - loss: 2.4239
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 33/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 20ms/step - accuracy: 0.2109 - loss: 2.4817
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 36/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 20ms/step - accuracy: 0.2100 - loss: 2.4798
[1m 39/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 20ms/step - accuracy: 0.2093 - loss: 2.4780
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m12s[0m 17ms/step - accuracy: 0.1994 - loss: 2.4345
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m12s[0m 17ms/step - accuracy: 0.1994 - loss: 2.4345
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m12s[0m 17ms/step - accuracy: 0.1994 - loss: 2.4345
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 42/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 20ms/step - accuracy: 0.2085 - loss: 2.4768
[1m 46/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 20ms/step - accuracy: 0.2075 - loss: 2.4755
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 12ms/step - accuracy: 0.2826 - loss: 1.9734
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 12ms/step - accuracy: 0.2825 - loss: 1.9734
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 12ms/step - accuracy: 0.2825 - loss: 1.9735
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 49/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 20ms/step - accuracy: 0.2069 - loss: 2.4743
[1m 52/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 20ms/step - accuracy: 0.2063 - loss: 2.4734
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 16ms/step - accuracy: 0.3049 - loss: 1.9092[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 55/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 20ms/step - accuracy: 0.2056 - loss: 2.4728
[1m 58/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 20ms/step - accuracy: 0.2051 - loss: 2.4723
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 61/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 20ms/step - accuracy: 0.2046 - loss: 2.4722
[1m 64/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 20ms/step - accuracy: 0.2042 - loss: 2.4724
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 17ms/step - accuracy: 0.1953 - loss: 2.4104
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 17ms/step - accuracy: 0.1965 - loss: 2.4069[32m [repeated 156x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1808 - loss: 2.4295[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 16ms/step - accuracy: 0.1526 - loss: 2.6712
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 16ms/step - accuracy: 0.1526 - loss: 2.6712[32m [repeated 112x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 67/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 19ms/step - accuracy: 0.2040 - loss: 2.4724
[1m 70/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 19ms/step - accuracy: 0.2039 - loss: 2.4721 
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m16s[0m 27ms/step - accuracy: 0.1986 - loss: 2.4704 - val_accuracy: 0.2094 - val_loss: 2.3402
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 53ms/step - accuracy: 0.3750 - loss: 2.0237
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.3523 - loss: 1.9108 
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m16s[0m 27ms/step - accuracy: 0.2694 - loss: 2.1339 - val_accuracy: 0.2329 - val_loss: 2.1676
[36m(train_cnn_ray_tune pid=2857952)[0m Epoch 21/24[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 16ms/step - accuracy: 0.1995 - loss: 2.4350 
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 16ms/step - accuracy: 0.1995 - loss: 2.4350
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m21s[0m 18ms/step - accuracy: 0.3049 - loss: 1.9092 - val_accuracy: 0.2905 - val_loss: 1.9089[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m175/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 19ms/step - accuracy: 0.2042 - loss: 2.4592
[1m178/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m7s[0m 19ms/step - accuracy: 0.2041 - loss: 2.4590[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 96/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m9s[0m 19ms/step - accuracy: 0.2034 - loss: 2.4682[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 95/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.2535 - loss: 2.2070
[1m 98/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.2540 - loss: 2.2055[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m101/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.2544 - loss: 2.2041 [32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 52ms/step - accuracy: 0.1875 - loss: 2.3505[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 13ms/step - accuracy: 0.1342 - loss: 2.6400 
[1m  10/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 13ms/step - accuracy: 0.1434 - loss: 2.6928
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 19ms/step - accuracy: 0.2080 - loss: 2.4892
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 19ms/step - accuracy: 0.2080 - loss: 2.4892
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 19ms/step - accuracy: 0.2079 - loss: 2.4892
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 19ms/step - accuracy: 0.2076 - loss: 2.4895[32m [repeated 42x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m  58/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 14ms/step - accuracy: 0.1618 - loss: 2.6816
[1m  62/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 14ms/step - accuracy: 0.1618 - loss: 2.6798[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 302/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m11s[0m 13ms/step - accuracy: 0.3138 - loss: 1.8804[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 11ms/step - accuracy: 0.1826 - loss: 2.4228
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 11ms/step - accuracy: 0.1826 - loss: 2.4228[32m [repeated 185x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m Epoch 17/21
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.3122 - loss: 1.8821 
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.3122 - loss: 1.8822[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m Epoch 22/25
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 60ms/step - accuracy: 0.3750 - loss: 2.1180
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 10ms/step - accuracy: 0.2686 - loss: 1.9418 
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m15s[0m 13ms/step - accuracy: 0.2807 - loss: 1.9763 - val_accuracy: 0.2947 - val_loss: 1.9191[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m438/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 19ms/step - accuracy: 0.2036 - loss: 2.4513
[1m441/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 19ms/step - accuracy: 0.2036 - loss: 2.4514[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m298/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m5s[0m 21ms/step - accuracy: 0.2646 - loss: 2.1642[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m8s[0m 13ms/step - accuracy: 0.3112 - loss: 1.8832
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m8s[0m 13ms/step - accuracy: 0.3112 - loss: 1.8833
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m8s[0m 13ms/step - accuracy: 0.3111 - loss: 1.8834
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 14ms/step - accuracy: 0.2210 - loss: 2.2851[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m10s[0m 14ms/step - accuracy: 0.1639 - loss: 2.6493
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 14ms/step - accuracy: 0.1639 - loss: 2.6492 [32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 17ms/step - accuracy: 0.2162 - loss: 2.3506[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 17ms/step - accuracy: 0.2163 - loss: 2.3490
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 17ms/step - accuracy: 0.2163 - loss: 2.3489[32m [repeated 180x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 17ms/step - accuracy: 0.2162 - loss: 2.3503 
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 17ms/step - accuracy: 0.2162 - loss: 2.3502
[36m(train_cnn_ray_tune pid=2857950)[0m Epoch 13/15
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 22ms/step - accuracy: 0.2029 - loss: 2.4517 - val_accuracy: 0.2142 - val_loss: 2.3346
[36m(train_cnn_ray_tune pid=2857960)[0m Epoch 20/23
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.0625 - loss: 2.5121
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 14ms/step - accuracy: 0.1381 - loss: 2.3207 
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 51ms/step - accuracy: 0.1875 - loss: 2.5419
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 10ms/step - accuracy: 0.1896 - loss: 2.4413
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m15s[0m 13ms/step - accuracy: 0.1827 - loss: 2.4208 - val_accuracy: 0.1848 - val_loss: 2.3549[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 365ms/step
[1m 8/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step   
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m15/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m22/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m28/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m35/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m42/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m48/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m55/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m561/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 20ms/step - accuracy: 0.2672 - loss: 2.1465
[1m564/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 20ms/step - accuracy: 0.2672 - loss: 2.1464[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m558/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 20ms/step - accuracy: 0.2672 - loss: 2.1466[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 16ms/step - accuracy: 0.2164 - loss: 2.3478
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 16ms/step - accuracy: 0.2164 - loss: 2.3478
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 16ms/step - accuracy: 0.2164 - loss: 2.3477
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m61/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 8ms/step
[1m67/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m74/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 8ms/step
[1m81/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 35ms/step
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m  8/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 7ms/step 
[1m 16/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 356ms/step
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 23/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 7ms/step
[1m 30/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m10/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step   
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 38/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m 45/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 52/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 59/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m 66/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 73/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m 81/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m 88/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m 95/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m103/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 7ms/step
[1m110/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m117/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 7ms/step
[1m124/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.1825 - loss: 2.4038
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.1826 - loss: 2.4038
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m132/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 7ms/step
[1m140/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.1827 - loss: 2.4039
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.1828 - loss: 2.4039
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m148/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.1829 - loss: 2.4039
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m155/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 7ms/step
[1m162/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.1830 - loss: 2.4040
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.1831 - loss: 2.4040
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 36ms/step
[1m  9/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 7ms/step 
[36m(train_cnn_ray_tune pid=2857955)[0m 
[1m168/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 7ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 296/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.1831 - loss: 2.4040
[1m 301/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.1831 - loss: 2.4041
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 59ms/step - accuracy: 0.1562 - loss: 2.5928
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 17ms/step - accuracy: 0.1986 - loss: 2.4041 
[1m  7/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 18ms/step - accuracy: 0.2215 - loss: 2.3135

Trial trial_a058a finished iteration 1 at 2025-11-07 14:04:24. Total running time: 11min 51s
[36m(train_cnn_ray_tune pid=2857955)[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=2857955)[0m   _log_deprecation_warning(
╭──────────────────────────────────────╮
│ Trial trial_a058a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             708.597 │
│ time_total_s                 708.597 │
│ training_iteration                 1 │
│ val_accuracy                 0.21425 │
╰──────────────────────────────────────╯

Trial trial_a058a completed after 1 iterations at 2025-11-07 14:04:24. Total running time: 11min 51s
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 306/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.1832 - loss: 2.4042
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.1832 - loss: 2.4042
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 16ms/step - accuracy: 0.2163 - loss: 2.3459
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 16ms/step - accuracy: 0.2163 - loss: 2.3459
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 16ms/step - accuracy: 0.2163 - loss: 2.3458
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 16ms/step - accuracy: 0.2163 - loss: 2.3458[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.2800 - loss: 1.9772
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.2800 - loss: 1.9773
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.2800 - loss: 1.9773
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 13ms/step - accuracy: 0.2029 - loss: 2.4475
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 13ms/step - accuracy: 0.2029 - loss: 2.4473[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.2038 - loss: 2.4542[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 13ms/step - accuracy: 0.1625 - loss: 2.6437
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 13ms/step - accuracy: 0.1625 - loss: 2.6437[32m [repeated 174x across cluster][0m

Trial trial_a058a finished iteration 1 at 2025-11-07 14:04:25. Total running time: 11min 52s
╭──────────────────────────────────────╮
│ Trial trial_a058a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             709.723 │
│ time_total_s                 709.723 │
│ training_iteration                 1 │
│ val_accuracy                   0.237 │
╰──────────────────────────────────────╯

Trial trial_a058a completed after 1 iterations at 2025-11-07 14:04:25. Total running time: 11min 52s
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 22ms/step - accuracy: 0.2673 - loss: 2.1456 - val_accuracy: 0.2438 - val_loss: 2.1512
[36m(train_cnn_ray_tune pid=2857952)[0m Epoch 22/24[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 53ms/step - accuracy: 0.1250 - loss: 2.5531
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 11ms/step - accuracy: 0.1497 - loss: 2.5585 
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 16ms/step - accuracy: 0.2163 - loss: 2.3451
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 16ms/step - accuracy: 0.2163 - loss: 2.3451
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 15ms/step - accuracy: 0.2163 - loss: 2.3450
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m18s[0m 16ms/step - accuracy: 0.2211 - loss: 2.2849 - val_accuracy: 0.2370 - val_loss: 2.1443[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 10ms/step[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 53ms/step - accuracy: 0.3750 - loss: 1.6249
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 10ms/step - accuracy: 0.2622 - loss: 1.8142 
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m174/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 17ms/step - accuracy: 0.2696 - loss: 2.1140
[1m178/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m7s[0m 17ms/step - accuracy: 0.2696 - loss: 2.1137[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m136/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m7s[0m 18ms/step - accuracy: 0.2693 - loss: 2.1175[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.2028 - loss: 2.4431 
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.2028 - loss: 2.4431
[36m(train_cnn_ray_tune pid=2857944)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 6ms/step[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 11ms/step - accuracy: 0.2788 - loss: 1.9785 - val_accuracy: 0.2809 - val_loss: 1.9503
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m3s[0m 9ms/step - accuracy: 0.1861 - loss: 2.3999
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m3s[0m 9ms/step - accuracy: 0.1861 - loss: 2.3998[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.2901 - loss: 2.0698  
[1m  14/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 8ms/step - accuracy: 0.2938 - loss: 2.0544 
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.2788 - loss: 1.9785[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 55ms/step - accuracy: 0.3750 - loss: 2.2619
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 11ms/step - accuracy: 0.2387 - loss: 2.3837 
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m7s[0m 14ms/step - accuracy: 0.2106 - loss: 2.4285[32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 13ms/step - accuracy: 0.2171 - loss: 2.3552
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 13ms/step - accuracy: 0.2176 - loss: 2.3527[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 10ms/step - accuracy: 0.3028 - loss: 1.8798[32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m6s[0m 14ms/step - accuracy: 0.2101 - loss: 2.4311
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m6s[0m 14ms/step - accuracy: 0.2101 - loss: 2.4312[32m [repeated 121x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m Epoch 18/21[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m16s[0m 14ms/step - accuracy: 0.1614 - loss: 2.6446 - val_accuracy: 0.1732 - val_loss: 2.4506[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 51ms/step - accuracy: 0.0625 - loss: 2.7109[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m6s[0m 8ms/step - accuracy: 0.2851 - loss: 1.9652
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m6s[0m 8ms/step - accuracy: 0.2851 - loss: 1.9651
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m6s[0m 8ms/step - accuracy: 0.2851 - loss: 1.9650
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m498/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 16ms/step - accuracy: 0.2712 - loss: 2.1062
[1m502/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 16ms/step - accuracy: 0.2712 - loss: 2.1061[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m472/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 16ms/step - accuracy: 0.2711 - loss: 2.1065[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 141/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 10ms/step - accuracy: 0.3055 - loss: 1.8772 
[1m 147/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 10ms/step - accuracy: 0.3064 - loss: 1.8765[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 11ms/step - accuracy: 0.1867 - loss: 2.3992 - val_accuracy: 0.1806 - val_loss: 2.3680
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m4s[0m 8ms/step - accuracy: 0.2851 - loss: 1.9633
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m4s[0m 8ms/step - accuracy: 0.2850 - loss: 1.9633[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 8ms/step - accuracy: 0.1769 - loss: 2.3818  
[1m  15/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 8ms/step - accuracy: 0.1837 - loss: 2.3831

Trial status: 12 TERMINATED | 8 RUNNING
Current time: 2025-11-07 14:04:34. Total running time: 12min 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_a058a    RUNNING              3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21                                              │
│ trial_a058a    RUNNING              3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23                                              │
│ trial_a058a    RUNNING              3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24                                              │
│ trial_a058a    TERMINATED           3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16        1            709.723         0.237003 │
│ trial_a058a    TERMINATED           2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28        1            640.594         0.257539 │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25        1            370.735         0.272525 │
│ trial_a058a    TERMINATED           3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15        1            530.858         0.249029 │
│ trial_a058a    TERMINATED           3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26        1            692.81          0.224607 │
│ trial_a058a    TERMINATED           3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24        1            708.597         0.214246 │
│ trial_a058a    TERMINATED           2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28        1            678.664         0.249399 │
│ trial_a058a    TERMINATED           3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23        1            498.889         0.264015 │
│ trial_a058a    TERMINATED           2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27        1            602.129         0.183349 │
│ trial_a058a    TERMINATED           3   adam            relu                                   16                 64                  3                 1          0.000164705         24        1            685.685         0.285106 │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24        1            524.007         0.272155 │
│ trial_a058a    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21        1            666.513         0.276966 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m5s[0m 8ms/step - accuracy: 0.2852 - loss: 1.9634[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m3s[0m 8ms/step - accuracy: 0.2848 - loss: 1.9626
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m3s[0m 8ms/step - accuracy: 0.2848 - loss: 1.9625
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m3s[0m 8ms/step - accuracy: 0.2848 - loss: 1.9625
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m11s[0m 18ms/step - accuracy: 0.2713 - loss: 2.1055 - val_accuracy: 0.2364 - val_loss: 2.1434
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 59ms/step - accuracy: 0.3750 - loss: 1.9162
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 17ms/step - accuracy: 0.2931 - loss: 1.9347 
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m8s[0m 10ms/step - accuracy: 0.1685 - loss: 2.6025[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 13ms/step - accuracy: 0.2246 - loss: 2.3187
[1m 381/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.2246 - loss: 2.3185 [32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m11s[0m 13ms/step - accuracy: 0.2246 - loss: 2.3208[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 10ms/step - accuracy: 0.1675 - loss: 2.6079
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 10ms/step - accuracy: 0.1674 - loss: 2.6082[32m [repeated 153x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m Epoch 23/24[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 44ms/step - accuracy: 0.1875 - loss: 2.3726
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m150/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m6s[0m 16ms/step - accuracy: 0.2801 - loss: 2.0672
[1m154/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m6s[0m 16ms/step - accuracy: 0.2803 - loss: 2.0674[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 83/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 17ms/step - accuracy: 0.2740 - loss: 2.0627[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m16s[0m 13ms/step - accuracy: 0.2028 - loss: 2.4375 - val_accuracy: 0.2011 - val_loss: 2.3300
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 47ms/step - accuracy: 0.2500 - loss: 2.2346
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m4s[0m 8ms/step - accuracy: 0.1836 - loss: 2.3985
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m4s[0m 8ms/step - accuracy: 0.1836 - loss: 2.3985[32m [repeated 79x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 13ms/step - accuracy: 0.2056 - loss: 2.5781 
[1m  10/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 12ms/step - accuracy: 0.1981 - loss: 2.5556
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m4s[0m 8ms/step - accuracy: 0.1836 - loss: 2.3985[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m4s[0m 8ms/step - accuracy: 0.1837 - loss: 2.3984
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m4s[0m 8ms/step - accuracy: 0.1837 - loss: 2.3984
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m4s[0m 8ms/step - accuracy: 0.1837 - loss: 2.3984
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m11s[0m 9ms/step - accuracy: 0.2838 - loss: 1.9613 - val_accuracy: 0.2918 - val_loss: 1.9094
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.3292 - loss: 1.7982  
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.3179 - loss: 1.8201 
[1m  20/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 8ms/step - accuracy: 0.3056 - loss: 1.8638
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.2259 - loss: 2.3103[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 50ms/step - accuracy: 0.3750 - loss: 1.5313
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 11ms/step - accuracy: 0.3115 - loss: 1.7055
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 11ms/step - accuracy: 0.1985 - loss: 2.4206
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 11ms/step - accuracy: 0.1987 - loss: 2.4206[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 13ms/step - accuracy: 0.1998 - loss: 2.4518
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 10ms/step - accuracy: 0.1630 - loss: 2.6275
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 10ms/step - accuracy: 0.1630 - loss: 2.6276[32m [repeated 137x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 11ms/step - accuracy: 0.1994 - loss: 2.4204
[36m(train_cnn_ray_tune pid=2857943)[0m Epoch 20/26[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.1838 - loss: 2.3982
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.1838 - loss: 2.3982
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.1838 - loss: 2.3982
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m479/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 15ms/step - accuracy: 0.2787 - loss: 2.0758
[1m483/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 15ms/step - accuracy: 0.2786 - loss: 2.0759[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m475/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 15ms/step - accuracy: 0.2787 - loss: 2.0757[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m9s[0m 10ms/step - accuracy: 0.3039 - loss: 1.8672 
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m9s[0m 10ms/step - accuracy: 0.3042 - loss: 1.8671
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 11ms/step - accuracy: 0.3148 - loss: 1.8765 - val_accuracy: 0.2986 - val_loss: 1.9055[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 53ms/step - accuracy: 0.3750 - loss: 1.8077[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m5s[0m 9ms/step - accuracy: 0.2808 - loss: 1.9419
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m5s[0m 9ms/step - accuracy: 0.2807 - loss: 1.9421[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m5s[0m 9ms/step - accuracy: 0.2808 - loss: 1.9417[32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m10s[0m 17ms/step - accuracy: 0.2777 - loss: 2.0773 - val_accuracy: 0.2431 - val_loss: 2.1211
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 11ms/step - accuracy: 0.2039 - loss: 2.4168[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 51ms/step - accuracy: 0.2500 - loss: 2.1572
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 15ms/step - accuracy: 0.2327 - loss: 2.1348 
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 10ms/step - accuracy: 0.1842 - loss: 2.3980 - val_accuracy: 0.1902 - val_loss: 2.3586
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 13ms/step - accuracy: 0.2054 - loss: 2.4363
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.2054 - loss: 2.4364 [32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 11ms/step - accuracy: 0.2041 - loss: 2.4165
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 11ms/step - accuracy: 0.2041 - loss: 2.4164[32m [repeated 107x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.1634 - loss: 2.2936  
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.1585 - loss: 2.3219
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 13ms/step - accuracy: 0.2053 - loss: 2.4352[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 58ms/step - accuracy: 0.1875 - loss: 2.3833
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 14ms/step - accuracy: 0.1827 - loss: 2.3445 
[36m(train_cnn_ray_tune pid=2857962)[0m Epoch 16/21[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 8ms/step - accuracy: 0.2793 - loss: 1.9492
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 8ms/step - accuracy: 0.2793 - loss: 1.9492
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 8ms/step - accuracy: 0.2793 - loss: 1.9493
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m141/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m7s[0m 16ms/step - accuracy: 0.2705 - loss: 2.0892
[1m144/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m7s[0m 16ms/step - accuracy: 0.2706 - loss: 2.0891[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m130/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m7s[0m 16ms/step - accuracy: 0.2700 - loss: 2.0897[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.1854 - loss: 2.6595 
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.1873 - loss: 2.6490 
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 139/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 13ms/step - accuracy: 0.2361 - loss: 2.2732
[1m 143/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 13ms/step - accuracy: 0.2361 - loss: 2.2735
[1m 147/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 13ms/step - accuracy: 0.2361 - loss: 2.2738
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m17s[0m 14ms/step - accuracy: 0.2255 - loss: 2.3106 - val_accuracy: 0.2122 - val_loss: 2.2801[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 53ms/step - accuracy: 0.2500 - loss: 2.2300[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 8ms/step - accuracy: 0.2796 - loss: 1.9505
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 8ms/step - accuracy: 0.2796 - loss: 1.9505[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 8ms/step - accuracy: 0.2795 - loss: 1.9504[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 305/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m11s[0m 13ms/step - accuracy: 0.2352 - loss: 2.2790
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m11s[0m 13ms/step - accuracy: 0.2352 - loss: 2.2791
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m11s[0m 13ms/step - accuracy: 0.2351 - loss: 2.2792
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 11ms/step - accuracy: 0.1708 - loss: 2.6405[32m [repeated 50x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 13ms/step - accuracy: 0.2343 - loss: 2.2808
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 13ms/step - accuracy: 0.2341 - loss: 2.2810[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 11ms/step - accuracy: 0.1706 - loss: 2.6399
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 11ms/step - accuracy: 0.1706 - loss: 2.6398[32m [repeated 151x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m12s[0m 13ms/step - accuracy: 0.2358 - loss: 2.2773[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m11s[0m 10ms/step - accuracy: 0.2796 - loss: 1.9506 - val_accuracy: 0.2873 - val_loss: 1.8834
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 52ms/step - accuracy: 0.3125 - loss: 1.8425
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 8ms/step - accuracy: 0.3482 - loss: 1.8930   
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.2333 - loss: 2.2823 
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.2332 - loss: 2.2825
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.3158 - loss: 1.9140 
[1m  45/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.3145 - loss: 1.9121
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.3135 - loss: 1.9122
[36m(train_cnn_ray_tune pid=2857965)[0m Epoch 25/25
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m465/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m1s[0m 16ms/step - accuracy: 0.2741 - loss: 2.0836
[1m469/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 16ms/step - accuracy: 0.2741 - loss: 2.0835[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m413/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m2s[0m 16ms/step - accuracy: 0.2738 - loss: 2.0844[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 11ms/step - accuracy: 0.3089 - loss: 1.8687 - val_accuracy: 0.2973 - val_loss: 1.8877
[36m(train_cnn_ray_tune pid=2857943)[0m Epoch 21/26
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 50ms/step - accuracy: 0.1875 - loss: 2.6499
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m6s[0m 8ms/step - accuracy: 0.2948 - loss: 1.9379
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m6s[0m 8ms/step - accuracy: 0.2947 - loss: 1.9383
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m6s[0m 8ms/step - accuracy: 0.2946 - loss: 1.9386
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 382/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m6s[0m 8ms/step - accuracy: 0.2939 - loss: 1.9402
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m6s[0m 8ms/step - accuracy: 0.2938 - loss: 1.9406[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.1918 - loss: 2.3940[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 13ms/step - accuracy: 0.2300 - loss: 2.2884
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 13ms/step - accuracy: 0.2299 - loss: 2.2885
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 13ms/step - accuracy: 0.2299 - loss: 2.2885
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 13ms/step - accuracy: 0.2304 - loss: 2.2878[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 146/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 10ms/step - accuracy: 0.1969 - loss: 2.4133
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 10ms/step - accuracy: 0.1971 - loss: 2.4122[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 10ms/step - accuracy: 0.1685 - loss: 2.6326
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 10ms/step - accuracy: 0.1685 - loss: 2.6326[32m [repeated 129x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m9s[0m 10ms/step - accuracy: 0.1981 - loss: 2.4076 
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m9s[0m 10ms/step - accuracy: 0.1982 - loss: 2.4071
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m9s[0m 10ms/step - accuracy: 0.1982 - loss: 2.4068
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m4s[0m 8ms/step - accuracy: 0.2901 - loss: 1.9479
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m4s[0m 8ms/step - accuracy: 0.2900 - loss: 1.9481
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m4s[0m 8ms/step - accuracy: 0.2899 - loss: 1.9483
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m10s[0m 18ms/step - accuracy: 0.2750 - loss: 2.0815 - val_accuracy: 0.2601 - val_loss: 2.1127
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 10ms/step - accuracy: 0.1979 - loss: 2.4083[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 336ms/step
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 50ms/step - accuracy: 0.2500 - loss: 1.7091
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 10ms/step - accuracy: 0.2670 - loss: 1.7761
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m10/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step   
[1m19/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m28/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[1m37/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m45/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 6ms/step
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m61/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 6ms/step
[1m70/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m78/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 10ms/step - accuracy: 0.1920 - loss: 2.3931 - val_accuracy: 0.1915 - val_loss: 2.3508
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 43ms/step - accuracy: 0.1875 - loss: 2.3845
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 8ms/step - accuracy: 0.1732 - loss: 2.3503  
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 33ms/step
[1m 10/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step 
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 18/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[1m 27/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[1m 35/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 43/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[1m 51/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 60/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[1m 68/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 76/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[1m 84/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m 93/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 6ms/step
[1m102/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m574/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 16ms/step - accuracy: 0.2749 - loss: 2.0817
[1m578/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 16ms/step - accuracy: 0.2749 - loss: 2.0816[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m582/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 16ms/step - accuracy: 0.2750 - loss: 2.0815[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=2857952)[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=2857952)[0m   _log_deprecation_warning([32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 12ms/step - accuracy: 0.2289 - loss: 2.2895
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 12ms/step - accuracy: 0.2289 - loss: 2.2895
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 12ms/step - accuracy: 0.2289 - loss: 2.2895
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m110/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 6ms/step
[1m119/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m128/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 6ms/step
[1m137/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m145/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 6ms/step
[1m154/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m162/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 6ms/step
[1m168/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 6ms/step

Trial trial_a058a finished iteration 1 at 2025-11-07 14:04:58. Total running time: 12min 25s
╭──────────────────────────────────────╮
│ Trial trial_a058a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             742.263 │
│ time_total_s                 742.263 │
│ training_iteration                 1 │
│ val_accuracy                 0.26013 │
╰──────────────────────────────────────╯

Trial trial_a058a completed after 1 iterations at 2025-11-07 14:04:58. Total running time: 12min 25s
[36m(train_cnn_ray_tune pid=2857952)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 12ms/step - accuracy: 0.2288 - loss: 2.2895
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 12ms/step - accuracy: 0.2288 - loss: 2.2895
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 12ms/step - accuracy: 0.2288 - loss: 2.2895
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.1707 - loss: 2.6635 
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.1700 - loss: 2.6618
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m14s[0m 12ms/step - accuracy: 0.1682 - loss: 2.6319 - val_accuracy: 0.1691 - val_loss: 2.4407[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m Epoch 20/21[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 44ms/step - accuracy: 0.1875 - loss: 2.5094
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.1667 - loss: 2.6613 
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.1659 - loss: 2.6603
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.1603 - loss: 2.6596
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.1600 - loss: 2.6591[32m [repeated 120x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 7ms/step - accuracy: 0.2856 - loss: 1.9533[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step - accuracy: 0.2286 - loss: 2.2893[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 257/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 11ms/step - accuracy: 0.2207 - loss: 2.4146
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 11ms/step - accuracy: 0.2207 - loss: 2.4144[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m7s[0m 10ms/step - accuracy: 0.2197 - loss: 2.4105
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m7s[0m 10ms/step - accuracy: 0.2197 - loss: 2.4104[32m [repeated 83x across cluster][0m
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 266ms/step
[1m16/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step   
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m66/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 3ms/step
[1m81/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 3ms/step[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 9ms/step - accuracy: 0.2018 - loss: 2.3898
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.2018 - loss: 2.3898
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.2018 - loss: 2.3899
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 32ms/step
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m 17/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step 
[1m 34/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m10s[0m 8ms/step - accuracy: 0.2856 - loss: 1.9533 - val_accuracy: 0.2981 - val_loss: 1.8880
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 46ms/step - accuracy: 0.0625 - loss: 2.7705
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.1113 - loss: 2.5915 [32m [repeated 2x across cluster][0m

Trial trial_a058a finished iteration 1 at 2025-11-07 14:05:02. Total running time: 12min 29s
╭──────────────────────────────────────╮
│ Trial trial_a058a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             746.336 │
│ time_total_s                 746.336 │
│ training_iteration                 1 │
│ val_accuracy                 0.29806 │
╰──────────────────────────────────────╯

Trial trial_a058a completed after 1 iterations at 2025-11-07 14:05:02. Total running time: 12min 29s
[36m(train_cnn_ray_tune pid=2857965)[0m 
[1m168/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 3ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 3ms/step[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m9s[0m 11ms/step - accuracy: 0.2207 - loss: 2.4142 
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m9s[0m 11ms/step - accuracy: 0.2207 - loss: 2.4141
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m15s[0m 13ms/step - accuracy: 0.2286 - loss: 2.2893 - val_accuracy: 0.2331 - val_loss: 2.2575
[36m(train_cnn_ray_tune pid=2857962)[0m Epoch 17/21
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.1829 - loss: 2.3285 
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.1845 - loss: 2.3253
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m11s[0m 9ms/step - accuracy: 0.3144 - loss: 1.8530 - val_accuracy: 0.2805 - val_loss: 1.8868
[36m(train_cnn_ray_tune pid=2857943)[0m Epoch 22/26
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 42ms/step - accuracy: 0.3750 - loss: 1.8725

Trial status: 14 TERMINATED | 6 RUNNING
Current time: 2025-11-07 14:05:04. Total running time: 12min 31s
Logical resource usage: 6.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status         N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21                                              │
│ trial_a058a    RUNNING              3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15                                              │
│ trial_a058a    RUNNING              2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23                                              │
│ trial_a058a    TERMINATED           3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16        1            709.723         0.237003 │
│ trial_a058a    TERMINATED           2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28        1            640.594         0.257539 │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25        1            370.735         0.272525 │
│ trial_a058a    TERMINATED           3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15        1            530.858         0.249029 │
│ trial_a058a    TERMINATED           3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26        1            692.81          0.224607 │
│ trial_a058a    TERMINATED           3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24        1            708.597         0.214246 │
│ trial_a058a    TERMINATED           2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28        1            678.664         0.249399 │
│ trial_a058a    TERMINATED           2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25        1            746.336         0.298057 │
│ trial_a058a    TERMINATED           3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23        1            498.889         0.264015 │
│ trial_a058a    TERMINATED           2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27        1            602.129         0.183349 │
│ trial_a058a    TERMINATED           3   adam            relu                                   16                 64                  3                 1          0.000164705         24        1            685.685         0.285106 │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24        1            524.007         0.272155 │
│ trial_a058a    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21        1            666.513         0.276966 │
│ trial_a058a    TERMINATED           3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24        1            742.263         0.26013  │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m2s[0m 8ms/step - accuracy: 0.1602 - loss: 2.6368
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m2s[0m 8ms/step - accuracy: 0.1603 - loss: 2.6367[32m [repeated 168x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 6ms/step - accuracy: 0.2725 - loss: 1.9855  
[1m  17/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 6ms/step - accuracy: 0.2897 - loss: 1.9669
[36m(train_cnn_ray_tune pid=2857960)[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=2857960)[0m   _log_deprecation_warning([32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 7ms/step - accuracy: 0.1969 - loss: 2.3677[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m4s[0m 10ms/step - accuracy: 0.2186 - loss: 2.4056
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 9ms/step - accuracy: 0.2180 - loss: 2.4015 
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 9ms/step - accuracy: 0.2180 - loss: 2.4014
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 10ms/step - accuracy: 0.2181 - loss: 2.4016
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 10ms/step - accuracy: 0.2180 - loss: 2.4016[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 263ms/step
[1m17/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step   
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m34/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step
[1m51/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 3ms/step[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m5s[0m 8ms/step - accuracy: 0.1588 - loss: 2.6445
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m5s[0m 8ms/step - accuracy: 0.1588 - loss: 2.6443
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m5s[0m 8ms/step - accuracy: 0.1588 - loss: 2.6441
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 32ms/step
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m 17/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step 
[1m 34/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step

Trial trial_a058a finished iteration 1 at 2025-11-07 14:05:07. Total running time: 12min 34s
╭──────────────────────────────────────╮
│ Trial trial_a058a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             751.443 │
│ time_total_s                 751.443 │
│ training_iteration                 1 │
│ val_accuracy                  0.1889 │
╰──────────────────────────────────────╯

Trial trial_a058a completed after 1 iterations at 2025-11-07 14:05:07. Total running time: 12min 34s
[36m(train_cnn_ray_tune pid=2857960)[0m 
[1m160/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 3ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 39ms/step - accuracy: 0.0625 - loss: 2.8061
[1m  10/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 6ms/step - accuracy: 0.1226 - loss: 2.7464  
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 328ms/step
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m15/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step   
[1m29/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 30ms/step
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 10ms/step - accuracy: 0.2178 - loss: 2.4003 - val_accuracy: 0.2211 - val_loss: 2.2200[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m Epoch 21/21[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 39ms/step - accuracy: 0.1875 - loss: 2.4734
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m5s[0m 6ms/step - accuracy: 0.1596 - loss: 2.5963
[1m 257/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m5s[0m 6ms/step - accuracy: 0.1596 - loss: 2.5960[32m [repeated 173x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 8ms/step - accuracy: 0.2716 - loss: 2.3250  
[1m  15/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 7ms/step - accuracy: 0.2513 - loss: 2.3736
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m2s[0m 6ms/step - accuracy: 0.3221 - loss: 1.8208[32m [repeated 21x across cluster][0m

Trial trial_a058a finished iteration 1 at 2025-11-07 14:05:09. Total running time: 12min 37s
[36m(train_cnn_ray_tune pid=2857942)[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=2857942)[0m   _log_deprecation_warning([32m [repeated 2x across cluster][0m
╭──────────────────────────────────────╮
│ Trial trial_a058a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             754.026 │
│ time_total_s                 754.026 │
│ training_iteration                 1 │
│ val_accuracy                 0.22109 │
╰──────────────────────────────────────╯

Trial trial_a058a completed after 1 iterations at 2025-11-07 14:05:09. Total running time: 12min 37s
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 37ms/step - accuracy: 0.5000 - loss: 1.7209
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  10/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 6ms/step - accuracy: 0.3628 - loss: 1.9510  
[1m  19/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 6ms/step - accuracy: 0.3143 - loss: 2.0690
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m 15/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step 
[1m 30/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=2857950)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 36ms/step - accuracy: 0.2500 - loss: 1.6095
[1m  12/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 5ms/step - accuracy: 0.2858 - loss: 1.7695  
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 36ms/step - accuracy: 0.2500 - loss: 2.1437
[1m  10/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 6ms/step - accuracy: 0.2034 - loss: 2.3885  
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m8s[0m 7ms/step - accuracy: 0.2110 - loss: 2.3886 - val_accuracy: 0.2120 - val_loss: 2.2991[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m Epoch 20/22[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m2s[0m 5ms/step - accuracy: 0.3275 - loss: 1.8124
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m2s[0m 5ms/step - accuracy: 0.3275 - loss: 1.8126[32m [repeated 154x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 5ms/step - accuracy: 0.1610 - loss: 2.6015[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 309ms/step
[1m21/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step   
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m2s[0m 6ms/step - accuracy: 0.2439 - loss: 2.2360
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m2s[0m 6ms/step - accuracy: 0.2440 - loss: 2.2360
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m2s[0m 6ms/step - accuracy: 0.2440 - loss: 2.2360
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 26ms/step
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m 21/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step 
[1m 43/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 6ms/step[32m [repeated 4x across cluster][0m

Trial trial_a058a finished iteration 1 at 2025-11-07 14:05:16. Total running time: 12min 43s
╭──────────────────────────────────────╮
│ Trial trial_a058a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             760.653 │
│ time_total_s                 760.653 │
│ training_iteration                 1 │
│ val_accuracy                 0.17502 │
╰──────────────────────────────────────╯

Trial trial_a058a completed after 1 iterations at 2025-11-07 14:05:16. Total running time: 12min 43s
[36m(train_cnn_ray_tune pid=2857942)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 33ms/step - accuracy: 0.1875 - loss: 2.0706
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 4ms/step - accuracy: 0.2965 - loss: 1.9364  
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 4ms/step - accuracy: 0.2952 - loss: 1.9030
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 5ms/step - accuracy: 0.2516 - loss: 2.2426  
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m8s[0m 7ms/step - accuracy: 0.2438 - loss: 2.2359 - val_accuracy: 0.2302 - val_loss: 2.2264[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m Epoch 19/21[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m3s[0m 4ms/step - accuracy: 0.3148 - loss: 1.8124
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m3s[0m 4ms/step - accuracy: 0.3149 - loss: 1.8123[32m [repeated 119x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  60/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 5ms/step - accuracy: 0.2668 - loss: 2.1726[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 33ms/step - accuracy: 0.2500 - loss: 2.4040[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m  12/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 5ms/step - accuracy: 0.2187 - loss: 2.3336  
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 5ms/step - accuracy: 0.2210 - loss: 2.3284
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 4ms/step - accuracy: 0.3118 - loss: 1.7081  
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 4ms/step - accuracy: 0.3215 - loss: 1.7464
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m6s[0m 5ms/step - accuracy: 0.3208 - loss: 1.8099 - val_accuracy: 0.2849 - val_loss: 1.8927[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m Epoch 25/26[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 4ms/step - accuracy: 0.3436 - loss: 1.7802
[1m 144/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 4ms/step - accuracy: 0.3432 - loss: 1.7802[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.3208 - loss: 1.8099[32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 32ms/step - accuracy: 0.1250 - loss: 2.6962[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 5ms/step - accuracy: 0.1810 - loss: 2.5188  
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 5ms/step - accuracy: 0.1835 - loss: 2.4877[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 6ms/step - accuracy: 0.2161 - loss: 2.3600 - val_accuracy: 0.2146 - val_loss: 2.2944[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m Epoch 22/22[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m3s[0m 5ms/step - accuracy: 0.2177 - loss: 2.3606
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m3s[0m 5ms/step - accuracy: 0.2179 - loss: 2.3599[32m [repeated 104x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 4ms/step - accuracy: 0.3310 - loss: 1.7977[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 34ms/step - accuracy: 0.3125 - loss: 1.6717
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 4ms/step - accuracy: 0.3537 - loss: 1.6925  
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 31ms/step - accuracy: 0.1250 - loss: 2.6820
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 207ms/step
[1m25/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step   
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m50/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step
[1m76/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 5ms/step - accuracy: 0.2231 - loss: 2.3290  
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 5ms/step - accuracy: 0.2372 - loss: 2.2756
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step

Trial status: 17 TERMINATED | 3 RUNNING
Current time: 2025-11-07 14:05:34. Total running time: 13min 1s
Logical resource usage: 3.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status         N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_a058a    RUNNING              2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26                                              │
│ trial_a058a    RUNNING              2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22                                              │
│ trial_a058a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21                                              │
│ trial_a058a    TERMINATED           3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16        1            709.723         0.237003 │
│ trial_a058a    TERMINATED           3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21        1            760.653         0.175023 │
│ trial_a058a    TERMINATED           3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15        1            754.026         0.221092 │
│ trial_a058a    TERMINATED           2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28        1            640.594         0.257539 │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25        1            370.735         0.272525 │
│ trial_a058a    TERMINATED           3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15        1            530.858         0.249029 │
│ trial_a058a    TERMINATED           3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26        1            692.81          0.224607 │
│ trial_a058a    TERMINATED           3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24        1            708.597         0.214246 │
│ trial_a058a    TERMINATED           2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28        1            678.664         0.249399 │
│ trial_a058a    TERMINATED           2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25        1            746.336         0.298057 │
│ trial_a058a    TERMINATED           2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23        1            751.443         0.188899 │
│ trial_a058a    TERMINATED           3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23        1            498.889         0.264015 │
│ trial_a058a    TERMINATED           2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27        1            602.129         0.183349 │
│ trial_a058a    TERMINATED           3   adam            relu                                   16                 64                  3                 1          0.000164705         24        1            685.685         0.285106 │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24        1            524.007         0.272155 │
│ trial_a058a    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21        1            666.513         0.276966 │
│ trial_a058a    TERMINATED           3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24        1            742.263         0.26013  │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 24ms/step
[1m 27/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step 
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m 53/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step
[1m 81/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=2857961)[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=2857961)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=2857943)[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=2857943)[0m   _log_deprecation_warning(
2025-11-07 14:05:39,294	INFO tune.py:1009 -- Wrote the latest version of all result files and experiment state to '/mnt/nvme1n2/git/uniovi-simur-wearablepermed-data/output/Paper_results/cases_dataset_C/case_C_CAPTURE24_acc_17_classes/CAPTURE24_hyperparameters_tuning' in 0.0056s.
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 6ms/step - accuracy: 0.2206 - loss: 2.3472 - val_accuracy: 0.2146 - val_loss: 2.2771[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m Epoch 21/21[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m107/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step
[1m134/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m162/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=2857961)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m4s[0m 5ms/step - accuracy: 0.2451 - loss: 2.1892
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m4s[0m 5ms/step - accuracy: 0.2450 - loss: 2.1895[32m [repeated 108x across cluster][0m

Trial trial_a058a finished iteration 1 at 2025-11-07 14:05:34. Total running time: 13min 1s
╭──────────────────────────────────────╮
│ Trial trial_a058a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             778.893 │
│ time_total_s                 778.893 │
│ training_iteration                 1 │
│ val_accuracy                 0.21462 │
╰──────────────────────────────────────╯

Trial trial_a058a completed after 1 iterations at 2025-11-07 14:05:34. Total running time: 13min 1s
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 307/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m4s[0m 5ms/step - accuracy: 0.2443 - loss: 2.1899[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 179ms/step
[1m31/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step   
[36m(train_cnn_ray_tune pid=2857943)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step
[1m 33/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step 

Trial trial_a058a finished iteration 1 at 2025-11-07 14:05:36. Total running time: 13min 3s
╭──────────────────────────────────────╮
│ Trial trial_a058a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             780.443 │
│ time_total_s                 780.443 │
│ training_iteration                 1 │
│ val_accuracy                 0.29491 │
╰──────────────────────────────────────╯

Trial trial_a058a completed after 1 iterations at 2025-11-07 14:05:36. Total running time: 13min 3s
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 154ms/step
[1m29/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step   
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m60/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[1m 30/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step 
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m155/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step[32m [repeated 6x across cluster][0m

Trial trial_a058a finished iteration 1 at 2025-11-07 14:05:39. Total running time: 13min 6s
╭──────────────────────────────────────╮
│ Trial trial_a058a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             783.701 │
│ time_total_s                 783.701 │
│ training_iteration                 1 │
│ val_accuracy                 0.23756 │
╰──────────────────────────────────────╯

Trial trial_a058a completed after 1 iterations at 2025-11-07 14:05:39. Total running time: 13min 6s

Trial status: 20 TERMINATED
Current time: 2025-11-07 14:05:39. Total running time: 13min 6s
Logical resource usage: 1.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
I0000 00:00:1762520739.423686 2856325 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
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ 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_a058a    TERMINATED           3   rmsprop         relu                                   16                 16                  3                 0          2.13416e-05         16        1            709.723         0.237003 │
│ trial_a058a    TERMINATED           3   rmsprop         tanh                                   16                 16                  3                 1          8.17154e-06         21        1            760.653         0.175023 │
│ trial_a058a    TERMINATED           3   adam            relu                                   16                 32                  5                 0          7.20388e-06         15        1            754.026         0.221092 │
│ trial_a058a    TERMINATED           2   adam            relu                                   16                 32                  3                 1          4.90988e-05         26        1            780.443         0.294912 │
│ trial_a058a    TERMINATED           2   rmsprop         tanh                                   32                 32                  3                 0          0.000110087         28        1            640.594         0.257539 │
│ trial_a058a    TERMINATED           2   adam            tanh                                   16                 64                  5                 0          8.87248e-06         22        1            778.893         0.214616 │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 0          0.000178587         25        1            370.735         0.272525 │
│ trial_a058a    TERMINATED           3   rmsprop         tanh                                   32                 32                  3                 0          0.000198115         15        1            530.858         0.249029 │
│ trial_a058a    TERMINATED           3   rmsprop         tanh                                   16                 32                  3                 0          2.64217e-05         21        1            783.701         0.237558 │
│ trial_a058a    TERMINATED           3   adam            tanh                                   32                 16                  5                 1          2.57894e-05         26        1            692.81          0.224607 │
│ trial_a058a    TERMINATED           3   rmsprop         tanh                                   32                 32                  5                 1          7.5801e-06          24        1            708.597         0.214246 │
│ trial_a058a    TERMINATED           2   rmsprop         tanh                                   32                 64                  3                 1          1.95063e-05         28        1            678.664         0.249399 │
│ trial_a058a    TERMINATED           2   adam            relu                                   16                 16                  3                 0          5.28466e-05         25        1            746.336         0.298057 │
│ trial_a058a    TERMINATED           2   adam            tanh                                   16                 16                  5                 0          2.68225e-05         23        1            751.443         0.188899 │
│ trial_a058a    TERMINATED           3   rmsprop         relu                                   32                 64                  5                 1          0.000151649         23        1            498.889         0.264015 │
│ trial_a058a    TERMINATED           2   adam            tanh                                   32                 16                  5                 1          1.90661e-05         27        1            602.129         0.183349 │
│ trial_a058a    TERMINATED           3   adam            relu                                   16                 64                  3                 1          0.000164705         24        1            685.685         0.285106 │
│ trial_a058a    TERMINATED           2   rmsprop         relu                                   32                 16                  3                 0          3.07216e-05         24        1            524.007         0.272155 │
│ trial_a058a    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 0          2.27208e-05         21        1            666.513         0.276966 │
│ trial_a058a    TERMINATED           3   adam            tanh                                   32                 64                  3                 0          1.43535e-05         24        1            742.263         0.26013  │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯

Mejores hiperparámetros: {'N_capas': 2, 'optimizador': 'adam', 'funcion_activacion': 'relu', 'tamanho_minilote': 16, 'numero_filtros': 16, 'tamanho_filtro': 3, 'num_resblocks': 0, 'tasa_aprendizaje': 5.2846609811217576e-05, 'epochs': 25}
Epoch 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762520741.138503 2908092 service.cc:152] XLA service 0x7529ac00bca0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762520741.138554 2908092 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:05:41.168033: 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 00:00:1762520741.327605 2908092 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762520742.732932 2908092 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51:16[0m 3s/step - accuracy: 0.0625 - loss: 2.7329
[1m  31/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0587 - loss: 3.2809  
[1m  71/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0633 - loss: 3.2876
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0655 - loss: 3.2794
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0676 - loss: 3.2687
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0690 - loss: 3.2578
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0698 - loss: 3.2490
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0704 - loss: 3.2387
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0709 - loss: 3.2294
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0713 - loss: 3.2206
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0718 - loss: 3.2111
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0723 - loss: 3.2018
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0728 - loss: 3.1930
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0733 - loss: 3.1843
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0737 - loss: 3.1761
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0740 - loss: 3.1678
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0744 - loss: 3.1596
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0749 - loss: 3.1514
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0752 - loss: 3.1441
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0756 - loss: 3.1373
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0762 - loss: 3.1293
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0767 - loss: 3.1224
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0772 - loss: 3.1154
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0778 - loss: 3.1090
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0783 - loss: 3.1026
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0788 - loss: 3.0960
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0794 - loss: 3.0895
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0800 - loss: 3.0831
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0806 - loss: 3.0775
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0811 - loss: 3.0724
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m8s[0m 4ms/step - accuracy: 0.0811 - loss: 3.0723 - val_accuracy: 0.1610 - val_loss: 2.5715
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.2500 - loss: 2.6356
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1470 - loss: 2.6795  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1378 - loss: 2.6839
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1358 - loss: 2.6821
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1354 - loss: 2.6810
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1356 - loss: 2.6803
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1360 - loss: 2.6785
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1363 - loss: 2.6773
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1367 - loss: 2.6759
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1371 - loss: 2.6746
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1374 - loss: 2.6732
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1378 - loss: 2.6717
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1381 - loss: 2.6704
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1383 - loss: 2.6692
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1385 - loss: 2.6680
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1388 - loss: 2.6666
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1391 - loss: 2.6655
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1393 - loss: 2.6644
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1395 - loss: 2.6633
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1398 - loss: 2.6621
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1402 - loss: 2.6606
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1405 - loss: 2.6590
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1409 - loss: 2.6574
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1412 - loss: 2.6560
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1416 - loss: 2.6546
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1419 - loss: 2.6532
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1423 - loss: 2.6517
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1426 - loss: 2.6502
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1430 - loss: 2.6488
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1432 - loss: 2.6479 - val_accuracy: 0.1909 - val_loss: 2.4700
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.4248
[1m  44/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1821 - loss: 2.5459  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1700 - loss: 2.5442
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1677 - loss: 2.5390
[1m 172/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1677 - loss: 2.5336
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1668 - loss: 2.5306
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1665 - loss: 2.5278
[1m 299/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1666 - loss: 2.5246
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1666 - loss: 2.5223
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1663 - loss: 2.5211
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1664 - loss: 2.5202
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1666 - loss: 2.5191
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1667 - loss: 2.5178
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1669 - loss: 2.5163
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1670 - loss: 2.5151
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1671 - loss: 2.5139
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1673 - loss: 2.5128
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1676 - loss: 2.5117
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1679 - loss: 2.5105
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1683 - loss: 2.5093
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1687 - loss: 2.5083
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1691 - loss: 2.5072
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1696 - loss: 2.5059
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1700 - loss: 2.5050
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1703 - loss: 2.5039
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1707 - loss: 2.5028
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1711 - loss: 2.5017
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1715 - loss: 2.5007
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1718 - loss: 2.4997
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1721 - loss: 2.4987 - val_accuracy: 0.2065 - val_loss: 2.3673
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.3980
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1762 - loss: 2.4426  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1800 - loss: 2.4471
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1814 - loss: 2.4458
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1838 - loss: 2.4441
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1846 - loss: 2.4432
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1851 - loss: 2.4428
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1859 - loss: 2.4416
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1863 - loss: 2.4404
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1868 - loss: 2.4390
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1873 - loss: 2.4375
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1876 - loss: 2.4360
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1880 - loss: 2.4345
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1883 - loss: 2.4333
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1886 - loss: 2.4319
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1889 - loss: 2.4308
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1892 - loss: 2.4295
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1895 - loss: 2.4282
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1896 - loss: 2.4269
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1898 - loss: 2.4257
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1900 - loss: 2.4245
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1902 - loss: 2.4234
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1904 - loss: 2.4222
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1906 - loss: 2.4211
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1908 - loss: 2.4201
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1910 - loss: 2.4190
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1911 - loss: 2.4180
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1912 - loss: 2.4172
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1913 - loss: 2.4162
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1914 - loss: 2.4153
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1915 - loss: 2.4150 - val_accuracy: 0.2320 - val_loss: 2.2855
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.4716
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1962 - loss: 2.3309  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1980 - loss: 2.3376
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1975 - loss: 2.3460
[1m 170/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1974 - loss: 2.3497
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1971 - loss: 2.3523
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1968 - loss: 2.3544
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1964 - loss: 2.3557
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1960 - loss: 2.3568
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1959 - loss: 2.3572
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1961 - loss: 2.3571
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1963 - loss: 2.3569
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1964 - loss: 2.3567
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1965 - loss: 2.3563
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1967 - loss: 2.3557
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1970 - loss: 2.3552
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1972 - loss: 2.3547
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1974 - loss: 2.3542
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1977 - loss: 2.3536
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1979 - loss: 2.3532
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1981 - loss: 2.3526
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1983 - loss: 2.3520
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1985 - loss: 2.3514
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1987 - loss: 2.3509
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1989 - loss: 2.3503
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1990 - loss: 2.3498
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1992 - loss: 2.3493
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1993 - loss: 2.3489
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1994 - loss: 2.3485
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1995 - loss: 2.3481 - val_accuracy: 0.2342 - val_loss: 2.2320
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 1.9564
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2183 - loss: 2.2641  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2169 - loss: 2.2802
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2168 - loss: 2.2846
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2163 - loss: 2.2905
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2149 - loss: 2.2953
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2149 - loss: 2.2973
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2152 - loss: 2.2971
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2154 - loss: 2.2973
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2154 - loss: 2.2973
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2154 - loss: 2.2970
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2152 - loss: 2.2971
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2151 - loss: 2.2974
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2150 - loss: 2.2975
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2149 - loss: 2.2973
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2149 - loss: 2.2970
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2150 - loss: 2.2966
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2151 - loss: 2.2962
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2152 - loss: 2.2958
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2153 - loss: 2.2953
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2153 - loss: 2.2950
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2154 - loss: 2.2946
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2155 - loss: 2.2943
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2155 - loss: 2.2940
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2156 - loss: 2.2937
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2156 - loss: 2.2934
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2157 - loss: 2.2931
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2158 - loss: 2.2929
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2158 - loss: 2.2926
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2159 - loss: 2.2924 - val_accuracy: 0.2483 - val_loss: 2.1839
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 20ms/step - accuracy: 0.3750 - loss: 2.0365
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2477 - loss: 2.2128  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2372 - loss: 2.2347
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2327 - loss: 2.2441
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2311 - loss: 2.2471
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2302 - loss: 2.2479
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2296 - loss: 2.2488
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2290 - loss: 2.2497
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2285 - loss: 2.2504
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2281 - loss: 2.2508
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2278 - loss: 2.2510
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2274 - loss: 2.2512
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2271 - loss: 2.2512
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2269 - loss: 2.2512
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2267 - loss: 2.2512
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2266 - loss: 2.2511
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2264 - loss: 2.2509
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2262 - loss: 2.2506
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2260 - loss: 2.2503
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2258 - loss: 2.2501
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2256 - loss: 2.2499
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2255 - loss: 2.2497
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2253 - loss: 2.2495
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2251 - loss: 2.2493
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2249 - loss: 2.2491
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2248 - loss: 2.2490
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2247 - loss: 2.2489
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2246 - loss: 2.2487
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2245 - loss: 2.2485
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2244 - loss: 2.2483 - val_accuracy: 0.2614 - val_loss: 2.1259
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.1891
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2408 - loss: 2.2401  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2411 - loss: 2.2291
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2370 - loss: 2.2272
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2345 - loss: 2.2258
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2341 - loss: 2.2236
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2332 - loss: 2.2226
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2327 - loss: 2.2213
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2323 - loss: 2.2210
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2322 - loss: 2.2207
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2323 - loss: 2.2198
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2325 - loss: 2.2186
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2327 - loss: 2.2174
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2328 - loss: 2.2166
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2328 - loss: 2.2162
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2328 - loss: 2.2158
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2328 - loss: 2.2155
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2327 - loss: 2.2152
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2327 - loss: 2.2149
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2327 - loss: 2.2147
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2327 - loss: 2.2144
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2326 - loss: 2.2142
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2326 - loss: 2.2141
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2325 - loss: 2.2140
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2324 - loss: 2.2140
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2324 - loss: 2.2139
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2324 - loss: 2.2137
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2323 - loss: 2.2135
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2323 - loss: 2.2133
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2323 - loss: 2.2131
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2323 - loss: 2.2131 - val_accuracy: 0.2572 - val_loss: 2.1052
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.1065
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2299 - loss: 2.2188  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2202 - loss: 2.2293
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2183 - loss: 2.2290
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2182 - loss: 2.2251
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2191 - loss: 2.2201
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2202 - loss: 2.2155
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2211 - loss: 2.2119
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2220 - loss: 2.2096
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2229 - loss: 2.2070
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2238 - loss: 2.2048
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2245 - loss: 2.2030
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2252 - loss: 2.2013
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2259 - loss: 2.1997
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2265 - loss: 2.1987
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2270 - loss: 2.1979
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2275 - loss: 2.1974
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2278 - loss: 2.1970
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2280 - loss: 2.1968
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2283 - loss: 2.1964
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2286 - loss: 2.1958
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2288 - loss: 2.1953
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2290 - loss: 2.1949
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2292 - loss: 2.1945
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2293 - loss: 2.1941
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2295 - loss: 2.1935
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2297 - loss: 2.1931
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2299 - loss: 2.1926
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2301 - loss: 2.1922
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2302 - loss: 2.1917
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2302 - loss: 2.1917 - val_accuracy: 0.2692 - val_loss: 2.0717
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.1062
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2428 - loss: 2.1812  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2439 - loss: 2.1713
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2421 - loss: 2.1705
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2397 - loss: 2.1705
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2387 - loss: 2.1702
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2385 - loss: 2.1697
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2386 - loss: 2.1686
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2388 - loss: 2.1676
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2390 - loss: 2.1665
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2394 - loss: 2.1650
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2397 - loss: 2.1641
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2399 - loss: 2.1634
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2401 - loss: 2.1627
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2404 - loss: 2.1623
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2406 - loss: 2.1620
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2408 - loss: 2.1618
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2411 - loss: 2.1616
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2414 - loss: 2.1614
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2417 - loss: 2.1611
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1608
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2422 - loss: 2.1605
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2423 - loss: 2.1603
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2424 - loss: 2.1601
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2425 - loss: 2.1599
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2426 - loss: 2.1598
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2428 - loss: 2.1597
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2429 - loss: 2.1595
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2430 - loss: 2.1594
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2431 - loss: 2.1592
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2431 - loss: 2.1592 - val_accuracy: 0.2520 - val_loss: 2.0609
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3750 - loss: 2.0402
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2688 - loss: 2.1652  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2571 - loss: 2.1530
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2545 - loss: 2.1435
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2514 - loss: 2.1396
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2495 - loss: 2.1369
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2483 - loss: 2.1351
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2472 - loss: 2.1342
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2461 - loss: 2.1341
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2459 - loss: 2.1337
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2456 - loss: 2.1333
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1332
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.1331
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.1332
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2453 - loss: 2.1333
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1337
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1341
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2450 - loss: 2.1345
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2450 - loss: 2.1348
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1350
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1351
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1351
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2453 - loss: 2.1351
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.1351
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1351
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1351
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1351
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2456 - loss: 2.1351
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2456 - loss: 2.1350
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2456 - loss: 2.1350 - val_accuracy: 0.2548 - val_loss: 2.0308
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.1769
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2884 - loss: 2.0685  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2820 - loss: 2.0626
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0685
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2685 - loss: 2.0760
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2643 - loss: 2.0819
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2617 - loss: 2.0856
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2601 - loss: 2.0890
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2591 - loss: 2.0915
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2585 - loss: 2.0930
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.0944
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0955
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.0964
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0971
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2554 - loss: 2.0981
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2549 - loss: 2.0992
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2545 - loss: 2.1002
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2541 - loss: 2.1012
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2538 - loss: 2.1018
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2533 - loss: 2.1024
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2529 - loss: 2.1030
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2525 - loss: 2.1036
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2522 - loss: 2.1042
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2518 - loss: 2.1047
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2516 - loss: 2.1051
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2514 - loss: 2.1054
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2512 - loss: 2.1057
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2511 - loss: 2.1060
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2510 - loss: 2.1062
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2509 - loss: 2.1065
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2509 - loss: 2.1066 - val_accuracy: 0.2640 - val_loss: 2.0237
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 1.9378
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2727 - loss: 2.1234  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2670 - loss: 2.1173
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2660 - loss: 2.1184
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2655 - loss: 2.1177
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2640 - loss: 2.1180
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2621 - loss: 2.1170
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2599 - loss: 2.1164
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2585 - loss: 2.1154
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2575 - loss: 2.1150
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.1146
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2566 - loss: 2.1139
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.1132
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.1126
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.1121
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2557 - loss: 2.1113
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2557 - loss: 2.1106
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2556 - loss: 2.1097
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2556 - loss: 2.1089
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2556 - loss: 2.1080
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2556 - loss: 2.1072
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2556 - loss: 2.1066
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2556 - loss: 2.1059
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2556 - loss: 2.1053
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2557 - loss: 2.1047
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2557 - loss: 2.1041
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2558 - loss: 2.1036
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.1030
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.1024
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.1019
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2560 - loss: 2.1018 - val_accuracy: 0.2766 - val_loss: 2.0122
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.1757
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2215 - loss: 2.1525  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2307 - loss: 2.1253
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2345 - loss: 2.1187
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2360 - loss: 2.1164
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2370 - loss: 2.1162
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2378 - loss: 2.1158
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2388 - loss: 2.1148
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2392 - loss: 2.1143
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2394 - loss: 2.1138
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2395 - loss: 2.1135
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2399 - loss: 2.1127
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2404 - loss: 2.1119
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2410 - loss: 2.1110
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2416 - loss: 2.1098
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2422 - loss: 2.1085
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2428 - loss: 2.1076
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2433 - loss: 2.1067
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2439 - loss: 2.1059
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2444 - loss: 2.1052
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2450 - loss: 2.1043
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2456 - loss: 2.1034
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2461 - loss: 2.1027
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2466 - loss: 2.1020
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2471 - loss: 2.1014
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2475 - loss: 2.1008
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2480 - loss: 2.1002
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2483 - loss: 2.0997
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2487 - loss: 2.0992
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2490 - loss: 2.0986
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2491 - loss: 2.0985 - val_accuracy: 0.2659 - val_loss: 2.0069
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5625 - loss: 1.8482
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2843 - loss: 2.1083  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2797 - loss: 2.0858
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2775 - loss: 2.0715
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2762 - loss: 2.0673
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0667
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2737 - loss: 2.0666
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2723 - loss: 2.0662
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0663
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0662
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0659
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0657
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2688 - loss: 2.0657
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2685 - loss: 2.0656
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0656
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0654
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0653
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0650
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0647
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0646
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0644
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0642
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0639
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0636
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0633
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0632
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0629
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0628
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0626
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0625
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2659 - loss: 2.0625 - val_accuracy: 0.2818 - val_loss: 1.9926
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.2849
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2301 - loss: 2.0939  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2363 - loss: 2.0915
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2413 - loss: 2.0900
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2439 - loss: 2.0845
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2466 - loss: 2.0797
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2487 - loss: 2.0761
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2504 - loss: 2.0732
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2518 - loss: 2.0701
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2532 - loss: 2.0672
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2539 - loss: 2.0654
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2545 - loss: 2.0640
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2549 - loss: 2.0632
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2555 - loss: 2.0625
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2558 - loss: 2.0620
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2562 - loss: 2.0615
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2564 - loss: 2.0610
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0606
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.0603
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0601
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0598
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2575 - loss: 2.0595
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2576 - loss: 2.0592
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.0588
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.0585
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2580 - loss: 2.0582
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0579
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2582 - loss: 2.0578
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2583 - loss: 2.0576
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2584 - loss: 2.0575 - val_accuracy: 0.2740 - val_loss: 1.9796
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.2650
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2110 - loss: 2.1324  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2176 - loss: 2.1218
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2233 - loss: 2.1098
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2281 - loss: 2.1028
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2312 - loss: 2.0987
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2348 - loss: 2.0920
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2373 - loss: 2.0874
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2396 - loss: 2.0829
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2417 - loss: 2.0796
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2439 - loss: 2.0763
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2455 - loss: 2.0738
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2473 - loss: 2.0711
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2488 - loss: 2.0688
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2503 - loss: 2.0666
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.0649
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2523 - loss: 2.0635
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2532 - loss: 2.0623
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2539 - loss: 2.0613
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2546 - loss: 2.0604
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2553 - loss: 2.0596
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2558 - loss: 2.0590
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0583
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.0577
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2575 - loss: 2.0570
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2580 - loss: 2.0562
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2585 - loss: 2.0555
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2589 - loss: 2.0549
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2593 - loss: 2.0543
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2597 - loss: 2.0538
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2599 - loss: 2.0535 - val_accuracy: 0.2548 - val_loss: 2.0042
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.8081
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2492 - loss: 1.9695  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2530 - loss: 1.9749
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2542 - loss: 1.9896
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2546 - loss: 2.0037
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2558 - loss: 2.0111
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0164
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0193
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2580 - loss: 2.0210
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2585 - loss: 2.0224
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2590 - loss: 2.0229
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2595 - loss: 2.0235
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2600 - loss: 2.0240
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0245
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2605 - loss: 2.0250
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0255
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0260
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2615 - loss: 2.0263
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2617 - loss: 2.0265
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2619 - loss: 2.0267
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2621 - loss: 2.0268
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2623 - loss: 2.0269
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2625 - loss: 2.0270
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2627 - loss: 2.0271
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2629 - loss: 2.0271
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0272
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0273
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0273
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2634 - loss: 2.0273
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2635 - loss: 2.0273 - val_accuracy: 0.2772 - val_loss: 1.9693
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.0330
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0608  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2597 - loss: 2.0534
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0476
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0430
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0395
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0374
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0359
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0350
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0350
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0351
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0349
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0349
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0348
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0345
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0337
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0328
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0321
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0315
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0309
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0304
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0300
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0297
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2673 - loss: 2.0295
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0291
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0288
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0285
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0282
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2678 - loss: 2.0279
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2679 - loss: 2.0277 - val_accuracy: 0.2788 - val_loss: 1.9607
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.2411
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2828 - loss: 2.0158  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2815 - loss: 2.0024
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2820 - loss: 2.0034
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2817 - loss: 2.0039
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2812 - loss: 2.0046
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2801 - loss: 2.0063
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2795 - loss: 2.0071
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2789 - loss: 2.0079
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2783 - loss: 2.0094
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2780 - loss: 2.0105
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2778 - loss: 2.0112
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 2.0116
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 2.0118
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 2.0118
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 2.0118
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 2.0115
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 2.0113
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2774 - loss: 2.0111
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2773 - loss: 2.0110
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2772 - loss: 2.0108
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2771 - loss: 2.0107
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2770 - loss: 2.0107
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2769 - loss: 2.0106
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2768 - loss: 2.0106
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2767 - loss: 2.0106
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2766 - loss: 2.0105
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2766 - loss: 2.0105
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2765 - loss: 2.0104
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2764 - loss: 2.0104
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2764 - loss: 2.0104 - val_accuracy: 0.2692 - val_loss: 1.9539
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.4510
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2719 - loss: 2.1073  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2854 - loss: 2.0553
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2887 - loss: 2.0368
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2863 - loss: 2.0296
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2841 - loss: 2.0245
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2832 - loss: 2.0191
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2829 - loss: 2.0147
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2827 - loss: 2.0117
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2825 - loss: 2.0100
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2823 - loss: 2.0089
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2821 - loss: 2.0085
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2822 - loss: 2.0082
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2822 - loss: 2.0081
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2822 - loss: 2.0080
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2822 - loss: 2.0080
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2822 - loss: 2.0078
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2823 - loss: 2.0076
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2824 - loss: 2.0073
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2824 - loss: 2.0070
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2825 - loss: 2.0068
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2825 - loss: 2.0065
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2825 - loss: 2.0062
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2826 - loss: 2.0058
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2827 - loss: 2.0053
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2827 - loss: 2.0049
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2827 - loss: 2.0046
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2827 - loss: 2.0044
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2827 - loss: 2.0042
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2827 - loss: 2.0040 - val_accuracy: 0.2786 - val_loss: 1.9524
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 25ms/step - accuracy: 0.3125 - loss: 2.0813
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2837 - loss: 1.9995  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2817 - loss: 1.9950
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2784 - loss: 1.9993
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2763 - loss: 2.0019
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0010
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2743 - loss: 2.0004
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2734 - loss: 2.0003
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2727 - loss: 2.0005
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0005
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2719 - loss: 2.0001
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 1.9996
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 1.9994
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 1.9992
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 1.9992
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 1.9991
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 1.9990
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 1.9990
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 1.9989
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 1.9988
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 1.9988
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 1.9988
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2712 - loss: 1.9988
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2714 - loss: 1.9987
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 1.9987
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 1.9986
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2719 - loss: 1.9986
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2721 - loss: 1.9984
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2723 - loss: 1.9983
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2725 - loss: 1.9981
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2725 - loss: 1.9981 - val_accuracy: 0.2614 - val_loss: 1.9763
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.5625 - loss: 1.7945
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2879 - loss: 2.0254  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2763 - loss: 2.0048
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2788 - loss: 1.9902
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2778 - loss: 1.9846
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2773 - loss: 1.9802
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2772 - loss: 1.9783
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2774 - loss: 1.9766
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2778 - loss: 1.9752
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2781 - loss: 1.9751
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2784 - loss: 1.9749
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2785 - loss: 1.9751
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2788 - loss: 1.9757
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2790 - loss: 1.9762
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2792 - loss: 1.9767
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2793 - loss: 1.9772
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2794 - loss: 1.9776
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2794 - loss: 1.9780
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2794 - loss: 1.9782
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 1.9785
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 1.9788
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 1.9791
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 1.9793
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 1.9795
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9797
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9799
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9800
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9802
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9804
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9807
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2796 - loss: 1.9808 - val_accuracy: 0.2788 - val_loss: 1.9373
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.1559
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2793 - loss: 1.9918  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2770 - loss: 1.9862
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9798
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2818 - loss: 1.9748
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2829 - loss: 1.9724
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2829 - loss: 1.9733
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2826 - loss: 1.9748
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2821 - loss: 1.9760
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2817 - loss: 1.9771
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2814 - loss: 1.9781
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9787
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 1.9793
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 1.9798
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2809 - loss: 1.9802
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2808 - loss: 1.9803
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2809 - loss: 1.9801
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 1.9801
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 1.9801
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2809 - loss: 1.9803
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2807 - loss: 1.9806
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 1.9809
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 1.9812
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2803 - loss: 1.9814
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2802 - loss: 1.9816
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 1.9816
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 1.9817
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 1.9816
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2800 - loss: 1.9816
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2800 - loss: 1.9816
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2800 - loss: 1.9815 - val_accuracy: 0.2722 - val_loss: 1.9316
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.0957
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2974 - loss: 1.8827  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2941 - loss: 1.8969
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2925 - loss: 1.9091
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2940 - loss: 1.9164
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2944 - loss: 1.9222
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2941 - loss: 1.9267
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2940 - loss: 1.9294
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2939 - loss: 1.9312
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2936 - loss: 1.9332
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2934 - loss: 1.9351
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2933 - loss: 1.9369
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2931 - loss: 1.9383
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2929 - loss: 1.9399
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2927 - loss: 1.9416
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2926 - loss: 1.9429
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2924 - loss: 1.9442
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2923 - loss: 1.9455
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2922 - loss: 1.9468
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2920 - loss: 1.9480
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2919 - loss: 1.9491
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2918 - loss: 1.9501
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2916 - loss: 1.9510
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2914 - loss: 1.9519
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2912 - loss: 1.9527
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2910 - loss: 1.9534
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2908 - loss: 1.9541
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2907 - loss: 1.9548
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2905 - loss: 1.9553
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2904 - loss: 1.9557
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2903 - loss: 1.9558 - val_accuracy: 0.2860 - val_loss: 1.9490

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 630ms/step
[1m55/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 928us/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.
[36m(train_cnn_ray_tune pid=2857962)[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=2857962)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m5s[0m 5ms/step - accuracy: 0.2425 - loss: 2.1960 - val_accuracy: 0.2376 - val_loss: 2.1973[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 4ms/step - accuracy: 0.2425 - loss: 2.1963
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 4ms/step - accuracy: 0.2425 - loss: 2.1962[32m [repeated 31x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 4ms/step - accuracy: 0.2425 - loss: 2.1961[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2857962)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step
2025-11-07 14:06:46.761565: 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 14:06:46.772914: 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 00:00:1762520806.786043 2911759 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762520806.790191 2911759 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762520806.800019 2911759 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762520806.800039 2911759 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762520806.800042 2911759 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762520806.800043 2911759 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:06:46.803286: 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 00:00:1762520809.080515 2911759 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762520810.583970 2911869 service.cc:152] XLA service 0x7b327000ba40 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762520810.584003 2911869 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:06:50.612218: 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 00:00:1762520810.758997 2911869 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762520812.169010 2911869 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47:23[0m 2s/step - accuracy: 0.0000e+00 - loss: 3.1903
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0525 - loss: 3.1409      
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0553 - loss: 3.1313
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0578 - loss: 3.1259
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0599 - loss: 3.1169
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0621 - loss: 3.1071
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0642 - loss: 3.0965
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0661 - loss: 3.0858
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0680 - loss: 3.0755
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0694 - loss: 3.0666
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0707 - loss: 3.0579
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0718 - loss: 3.0500
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0726 - loss: 3.0432
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0736 - loss: 3.0359
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0746 - loss: 3.0291
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0755 - loss: 3.0223
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0763 - loss: 3.0162
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0771 - loss: 3.0102
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0779 - loss: 3.0050
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0787 - loss: 2.9989
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0795 - loss: 2.9932
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0801 - loss: 2.9885
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0807 - loss: 2.9841
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0814 - loss: 2.9794
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0821 - loss: 2.9744
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0828 - loss: 2.9696
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0834 - loss: 2.9651
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0841 - loss: 2.9602
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0848 - loss: 2.9559
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0854 - loss: 2.9519
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0854 - loss: 2.9518 - val_accuracy: 0.1584 - val_loss: 2.5509
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.2500 - loss: 2.4641
[1m  44/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1600 - loss: 2.6178  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1539 - loss: 2.6476
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1493 - loss: 2.6602
[1m 170/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1468 - loss: 2.6631
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1456 - loss: 2.6634
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1449 - loss: 2.6632
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1447 - loss: 2.6623
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1446 - loss: 2.6606
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1444 - loss: 2.6589
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1442 - loss: 2.6573
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1441 - loss: 2.6558
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1441 - loss: 2.6543
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1441 - loss: 2.6528
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1440 - loss: 2.6512
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1441 - loss: 2.6495
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1441 - loss: 2.6477
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1442 - loss: 2.6459
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1443 - loss: 2.6442
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1443 - loss: 2.6425
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1444 - loss: 2.6410
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1445 - loss: 2.6395
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1445 - loss: 2.6381
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1446 - loss: 2.6367
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1446 - loss: 2.6354
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1447 - loss: 2.6340
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1448 - loss: 2.6327
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1450 - loss: 2.6313
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1451 - loss: 2.6302
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1452 - loss: 2.6293 - val_accuracy: 0.1774 - val_loss: 2.4865
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.0625 - loss: 2.9292
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1831 - loss: 2.5748  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1751 - loss: 2.5626
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1705 - loss: 2.5599
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1683 - loss: 2.5563
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1666 - loss: 2.5539
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1661 - loss: 2.5509
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1659 - loss: 2.5494
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1658 - loss: 2.5484
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1659 - loss: 2.5473
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1661 - loss: 2.5464
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1663 - loss: 2.5454
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1665 - loss: 2.5444
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1666 - loss: 2.5436
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1667 - loss: 2.5426
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1668 - loss: 2.5415
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1669 - loss: 2.5403
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1672 - loss: 2.5389
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1674 - loss: 2.5377
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1676 - loss: 2.5366
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1678 - loss: 2.5354
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1680 - loss: 2.5344
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1682 - loss: 2.5333
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1684 - loss: 2.5322
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1686 - loss: 2.5311
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1688 - loss: 2.5301
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1690 - loss: 2.5291
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1692 - loss: 2.5280
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1694 - loss: 2.5269
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1696 - loss: 2.5259 - val_accuracy: 0.1728 - val_loss: 2.4028
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.2000
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1855 - loss: 2.3950  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1825 - loss: 2.4237
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1825 - loss: 2.4328
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1824 - loss: 2.4372
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1820 - loss: 2.4404
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1814 - loss: 2.4424
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1810 - loss: 2.4438
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1808 - loss: 2.4443
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1806 - loss: 2.4449
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1806 - loss: 2.4449
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1805 - loss: 2.4447
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1806 - loss: 2.4445
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1806 - loss: 2.4440
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1806 - loss: 2.4435
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1807 - loss: 2.4432
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1808 - loss: 2.4427
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1809 - loss: 2.4423
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1810 - loss: 2.4417
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1811 - loss: 2.4412
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1813 - loss: 2.4408
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1815 - loss: 2.4403
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1817 - loss: 2.4398
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1819 - loss: 2.4393
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1821 - loss: 2.4388
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1823 - loss: 2.4384
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1825 - loss: 2.4378
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1827 - loss: 2.4374
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1828 - loss: 2.4369
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1830 - loss: 2.4364
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1830 - loss: 2.4364 - val_accuracy: 0.1906 - val_loss: 2.3364
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.4762
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2119 - loss: 2.3681  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2115 - loss: 2.3691
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2112 - loss: 2.3691
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2115 - loss: 2.3684
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2114 - loss: 2.3673
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2111 - loss: 2.3671
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2102 - loss: 2.3677
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2091 - loss: 2.3685
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2081 - loss: 2.3691
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2072 - loss: 2.3693
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2067 - loss: 2.3692
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2064 - loss: 2.3691
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2061 - loss: 2.3690
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2060 - loss: 2.3687
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2060 - loss: 2.3682
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2059 - loss: 2.3679
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2057 - loss: 2.3676
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2056 - loss: 2.3674
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2055 - loss: 2.3673
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2054 - loss: 2.3671
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2054 - loss: 2.3670
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2054 - loss: 2.3668
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2055 - loss: 2.3666
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2055 - loss: 2.3663
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2054 - loss: 2.3661
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2054 - loss: 2.3658
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2054 - loss: 2.3656
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2053 - loss: 2.3654
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2052 - loss: 2.3653 - val_accuracy: 0.2089 - val_loss: 2.2946
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 20ms/step - accuracy: 0.1250 - loss: 2.5460
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2011 - loss: 2.3646  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2030 - loss: 2.3576
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2037 - loss: 2.3525
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2032 - loss: 2.3501
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2021 - loss: 2.3481
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2023 - loss: 2.3452
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2026 - loss: 2.3422
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2029 - loss: 2.3395
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2032 - loss: 2.3372
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2036 - loss: 2.3354
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2042 - loss: 2.3336
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2046 - loss: 2.3319
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2051 - loss: 2.3303
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2056 - loss: 2.3286
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2059 - loss: 2.3274
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2062 - loss: 2.3265
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2065 - loss: 2.3255
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2067 - loss: 2.3246
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2070 - loss: 2.3238
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2073 - loss: 2.3231
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2074 - loss: 2.3225
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2075 - loss: 2.3220
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2076 - loss: 2.3217
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2076 - loss: 2.3214
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2077 - loss: 2.3211
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2077 - loss: 2.3208
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2078 - loss: 2.3206
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2079 - loss: 2.3203
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2079 - loss: 2.3202
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2079 - loss: 2.3201 - val_accuracy: 0.2115 - val_loss: 2.2433
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 20ms/step - accuracy: 0.1875 - loss: 2.1031
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2279 - loss: 2.2017  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2197 - loss: 2.2285
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2188 - loss: 2.2401
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2177 - loss: 2.2489
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2168 - loss: 2.2563
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2161 - loss: 2.2611
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2155 - loss: 2.2653
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2151 - loss: 2.2687
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2150 - loss: 2.2714
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2150 - loss: 2.2735
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2151 - loss: 2.2747
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2153 - loss: 2.2755
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2155 - loss: 2.2760
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2156 - loss: 2.2764
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2157 - loss: 2.2769
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2159 - loss: 2.2772
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2161 - loss: 2.2774
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2163 - loss: 2.2775
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2165 - loss: 2.2777
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2167 - loss: 2.2778
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2168 - loss: 2.2779
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2169 - loss: 2.2779
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2170 - loss: 2.2779
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2170 - loss: 2.2778
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2171 - loss: 2.2777
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2172 - loss: 2.2777
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2172 - loss: 2.2776
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2173 - loss: 2.2775
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2173 - loss: 2.2773 - val_accuracy: 0.2167 - val_loss: 2.1945
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.1470
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2460 - loss: 2.2132  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2419 - loss: 2.2190
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2375 - loss: 2.2238
[1m 168/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2351 - loss: 2.2266
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2337 - loss: 2.2291
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2317 - loss: 2.2330
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2298 - loss: 2.2368
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2284 - loss: 2.2393
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2275 - loss: 2.2408
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2269 - loss: 2.2421
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2262 - loss: 2.2439
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2259 - loss: 2.2453
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2256 - loss: 2.2461
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2255 - loss: 2.2467
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2252 - loss: 2.2472
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2251 - loss: 2.2475
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2250 - loss: 2.2476
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2249 - loss: 2.2476
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2248 - loss: 2.2476
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2248 - loss: 2.2474
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2247 - loss: 2.2473
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2246 - loss: 2.2473
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2245 - loss: 2.2473
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2244 - loss: 2.2473
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2243 - loss: 2.2472
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2242 - loss: 2.2471
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2242 - loss: 2.2470
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2241 - loss: 2.2468
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2241 - loss: 2.2467 - val_accuracy: 0.2586 - val_loss: 2.1490
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0724
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2231 - loss: 2.2347  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2272 - loss: 2.2349
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2286 - loss: 2.2311
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2301 - loss: 2.2257
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2313 - loss: 2.2213
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2322 - loss: 2.2191
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2327 - loss: 2.2172
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2329 - loss: 2.2162
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2331 - loss: 2.2156
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2333 - loss: 2.2153
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2333 - loss: 2.2149
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2332 - loss: 2.2148
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2332 - loss: 2.2147
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2330 - loss: 2.2148
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2328 - loss: 2.2150
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2326 - loss: 2.2156
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2326 - loss: 2.2159
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2326 - loss: 2.2161
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2327 - loss: 2.2163
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2327 - loss: 2.2163
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2326 - loss: 2.2164
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2325 - loss: 2.2164
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2325 - loss: 2.2163
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2325 - loss: 2.2161
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2325 - loss: 2.2158
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2326 - loss: 2.2156
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2326 - loss: 2.2153
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2326 - loss: 2.2149
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2325 - loss: 2.2146 - val_accuracy: 0.2444 - val_loss: 2.1388
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.0674
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2534 - loss: 2.1561  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2510 - loss: 2.1655
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2475 - loss: 2.1685
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2445 - loss: 2.1706
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2431 - loss: 2.1712
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2423 - loss: 2.1720
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2424 - loss: 2.1724
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2427 - loss: 2.1724
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2427 - loss: 2.1728
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2428 - loss: 2.1732
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2428 - loss: 2.1736
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2426 - loss: 2.1741
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2423 - loss: 2.1748
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2420 - loss: 2.1753
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2417 - loss: 2.1760
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2416 - loss: 2.1764
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2414 - loss: 2.1770
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2413 - loss: 2.1774
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2412 - loss: 2.1778
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2412 - loss: 2.1781
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2411 - loss: 2.1784
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2411 - loss: 2.1787
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2410 - loss: 2.1789
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2410 - loss: 2.1792
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2410 - loss: 2.1793
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2410 - loss: 2.1795
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2410 - loss: 2.1796
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2411 - loss: 2.1797
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2411 - loss: 2.1798 - val_accuracy: 0.2609 - val_loss: 2.0913
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.9164
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2254 - loss: 2.1879  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2317 - loss: 2.1736
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2376 - loss: 2.1674
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2394 - loss: 2.1666
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2398 - loss: 2.1671
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2397 - loss: 2.1685
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2394 - loss: 2.1699
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2390 - loss: 2.1708
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2386 - loss: 2.1718
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2381 - loss: 2.1723
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2378 - loss: 2.1727
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2376 - loss: 2.1726
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2375 - loss: 2.1724
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2375 - loss: 2.1722
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2376 - loss: 2.1720
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2376 - loss: 2.1719
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2378 - loss: 2.1717
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2379 - loss: 2.1716
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2379 - loss: 2.1714
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2380 - loss: 2.1712
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2381 - loss: 2.1708
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2383 - loss: 2.1705
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2384 - loss: 2.1701
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2386 - loss: 2.1697
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2387 - loss: 2.1693
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2388 - loss: 2.1690
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2389 - loss: 2.1686
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2390 - loss: 2.1683
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2390 - loss: 2.1681 - val_accuracy: 0.2511 - val_loss: 2.0967
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.2664
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2305 - loss: 2.2095  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2479 - loss: 2.1737
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2521 - loss: 2.1590
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2526 - loss: 2.1539
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2524 - loss: 2.1526
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2521 - loss: 2.1527
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2521 - loss: 2.1526
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2527 - loss: 2.1521
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2531 - loss: 2.1514
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2534 - loss: 2.1509
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2535 - loss: 2.1503
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2537 - loss: 2.1497
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2539 - loss: 2.1490
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2541 - loss: 2.1485
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2541 - loss: 2.1481
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2542 - loss: 2.1477
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2542 - loss: 2.1474
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2542 - loss: 2.1470
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1465
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1462
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1459
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1455
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1451
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2544 - loss: 2.1446
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2544 - loss: 2.1441
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2545 - loss: 2.1436
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2545 - loss: 2.1433
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2545 - loss: 2.1429
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2546 - loss: 2.1426 - val_accuracy: 0.2648 - val_loss: 2.0622
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0439
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0982  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2688 - loss: 2.1048
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2702 - loss: 2.1018
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2703 - loss: 2.1014
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2697 - loss: 2.0996
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0987
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2669 - loss: 2.1009
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2655 - loss: 2.1025
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2645 - loss: 2.1035
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2638 - loss: 2.1045
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2631 - loss: 2.1058
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2623 - loss: 2.1069
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2619 - loss: 2.1075
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2615 - loss: 2.1081
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2610 - loss: 2.1086
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2607 - loss: 2.1089
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2603 - loss: 2.1091
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.1094
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2595 - loss: 2.1098
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2590 - loss: 2.1101
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2586 - loss: 2.1104
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2582 - loss: 2.1105
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.1106
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2576 - loss: 2.1107
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2573 - loss: 2.1108
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2571 - loss: 2.1108
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.1108
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.1108
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2565 - loss: 2.1108 - val_accuracy: 0.2755 - val_loss: 2.0697
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 1.9974
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2672 - loss: 2.1399  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2616 - loss: 2.1321
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2588 - loss: 2.1393
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2586 - loss: 2.1417
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2584 - loss: 2.1412
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2579 - loss: 2.1405
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2575 - loss: 2.1390
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2575 - loss: 2.1365
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2575 - loss: 2.1341
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2576 - loss: 2.1320
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.1302
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.1289
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.1278
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.1268
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.1258
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.1249
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.1241
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.1235
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.1227
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.1219
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.1212
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.1206
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.1200
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.1196
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.1191
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.1186
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.1181
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.1175
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2578 - loss: 2.1170 - val_accuracy: 0.2777 - val_loss: 2.0607
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0419
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2279 - loss: 2.1744  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2469 - loss: 2.1485
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2489 - loss: 2.1387
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2508 - loss: 2.1330
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2511 - loss: 2.1298
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2525 - loss: 2.1264
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2537 - loss: 2.1232
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2546 - loss: 2.1205
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2553 - loss: 2.1178
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2557 - loss: 2.1159
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.1144
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.1131
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.1119
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2566 - loss: 2.1105
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.1094
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.1083
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2571 - loss: 2.1071
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2573 - loss: 2.1060
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2574 - loss: 2.1050
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2575 - loss: 2.1041
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.1033
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.1027
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.1021
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2580 - loss: 2.1015
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.1011
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.1007
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.1003
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2582 - loss: 2.1000
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2582 - loss: 2.0999 - val_accuracy: 0.2755 - val_loss: 2.0166
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.3049
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0867  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0806
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0769
[1m 168/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0764
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0764
[1m 253/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0759
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0754
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0754
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0754
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0761
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0763
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0765
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0766
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0765
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0767
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0768
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0767
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0767
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0764
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0762
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0761
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0759
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0756
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0755
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0754
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0754
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0753
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0752
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2657 - loss: 2.0752 - val_accuracy: 0.2723 - val_loss: 2.0285
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.4375 - loss: 2.0952
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2447 - loss: 2.0841  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2457 - loss: 2.0747
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2499 - loss: 2.0723
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2525 - loss: 2.0703
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2541 - loss: 2.0683
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2555 - loss: 2.0659
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0634
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2577 - loss: 2.0621
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2580 - loss: 2.0620
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2582 - loss: 2.0623
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2585 - loss: 2.0626
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2587 - loss: 2.0631
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2590 - loss: 2.0636
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2594 - loss: 2.0637
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2596 - loss: 2.0641
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0645
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0646
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2606 - loss: 2.0647
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0647
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2613 - loss: 2.0646
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2616 - loss: 2.0643
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2619 - loss: 2.0640
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2622 - loss: 2.0637
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2624 - loss: 2.0634
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2626 - loss: 2.0632
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2628 - loss: 2.0631
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0629
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0628
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2632 - loss: 2.0627 - val_accuracy: 0.2742 - val_loss: 2.0297
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.6293
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2832 - loss: 1.9814  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2755 - loss: 1.9899
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2738 - loss: 1.9958
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2746 - loss: 1.9998
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2755 - loss: 2.0035
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2767 - loss: 2.0055
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2770 - loss: 2.0078
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2773 - loss: 2.0093
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2774 - loss: 2.0110
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 2.0125
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 2.0137
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 2.0147
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 2.0159
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2773 - loss: 2.0170
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2770 - loss: 2.0182
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2768 - loss: 2.0193
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2764 - loss: 2.0205
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0216
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2758 - loss: 2.0227
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2755 - loss: 2.0237
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0247
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0255
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0263
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0270
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2742 - loss: 2.0277
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2739 - loss: 2.0283
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 2.0288
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2735 - loss: 2.0293
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2733 - loss: 2.0298 - val_accuracy: 0.2660 - val_loss: 2.0063
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 31ms/step - accuracy: 0.3750 - loss: 1.8084
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2741 - loss: 2.0182  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2746 - loss: 2.0140
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2734 - loss: 2.0123
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0157
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0204
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0227
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2705 - loss: 2.0246
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0257
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0256
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0248
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0241
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0235
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0230
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0224
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0221
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0218
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0214
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0212
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0211
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2706 - loss: 2.0211
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0212
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0214
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2701 - loss: 2.0216
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0220
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0222
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2697 - loss: 2.0224
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 2.0225
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2695 - loss: 2.0227
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0228
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2694 - loss: 2.0229 - val_accuracy: 0.2759 - val_loss: 1.9929
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.0757
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2349 - loss: 2.0199  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2605 - loss: 2.0148
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0146
[1m 168/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2641 - loss: 2.0160
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0172
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2648 - loss: 2.0185
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0201
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0210
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0213
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0213
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0214
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0215
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2690 - loss: 2.0216
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0217
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2697 - loss: 2.0217
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0215
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0216
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2706 - loss: 2.0216
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0217
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0220
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0224
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0227
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2712 - loss: 2.0230
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0232
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0235
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0237
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0239
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2719 - loss: 2.0240
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2720 - loss: 2.0241
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2720 - loss: 2.0241 - val_accuracy: 0.2816 - val_loss: 1.9719
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 1.7276
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2292 - loss: 2.0034  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2424 - loss: 2.0073
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2485 - loss: 2.0111
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2526 - loss: 2.0172
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2556 - loss: 2.0216
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2589 - loss: 2.0231
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2613 - loss: 2.0227
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0219
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2648 - loss: 2.0213
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0209
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0204
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2678 - loss: 2.0201
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2684 - loss: 2.0199
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2690 - loss: 2.0196
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 2.0194
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0194
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0192
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2706 - loss: 2.0189
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0185
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0183
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2714 - loss: 2.0180
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0178
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0176
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0174
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0173
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2724 - loss: 2.0173
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2725 - loss: 2.0172
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2726 - loss: 2.0173
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2728 - loss: 2.0173
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2728 - loss: 2.0173 - val_accuracy: 0.2831 - val_loss: 1.9604
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.5861
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2510 - loss: 2.0816  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0528
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2760 - loss: 2.0398
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2790 - loss: 2.0323
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2804 - loss: 2.0264
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2814 - loss: 2.0238
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2820 - loss: 2.0224
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2822 - loss: 2.0212
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2824 - loss: 2.0202
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2822 - loss: 2.0196
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2820 - loss: 2.0193
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2818 - loss: 2.0188
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2816 - loss: 2.0183
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2814 - loss: 2.0182
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 2.0181
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2807 - loss: 2.0182
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 2.0182
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 2.0180
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 2.0179
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2797 - loss: 2.0177
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 2.0174
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2794 - loss: 2.0172
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2794 - loss: 2.0168
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2793 - loss: 2.0164
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2793 - loss: 2.0160
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2793 - loss: 2.0156
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2792 - loss: 2.0152
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2792 - loss: 2.0149
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2792 - loss: 2.0145
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2792 - loss: 2.0143 - val_accuracy: 0.2759 - val_loss: 1.9923
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.2978
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3242 - loss: 2.0307  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3107 - loss: 2.0173
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3071 - loss: 2.0074
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3033 - loss: 2.0047
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2996 - loss: 2.0040
[1m 249/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2974 - loss: 2.0016
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2957 - loss: 1.9995
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2940 - loss: 1.9981
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2928 - loss: 1.9976
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2918 - loss: 1.9972
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2910 - loss: 1.9971
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2903 - loss: 1.9971
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2897 - loss: 1.9971
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2890 - loss: 1.9970
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2884 - loss: 1.9970
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2878 - loss: 1.9970
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2872 - loss: 1.9971
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2867 - loss: 1.9972
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2863 - loss: 1.9972
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2859 - loss: 1.9972
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2856 - loss: 1.9971
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2854 - loss: 1.9970
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2852 - loss: 1.9969
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2851 - loss: 1.9966
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2849 - loss: 1.9963
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2848 - loss: 1.9960
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2846 - loss: 1.9957
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2844 - loss: 1.9955
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2843 - loss: 1.9954 - val_accuracy: 0.2975 - val_loss: 1.9512
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 19ms/step - accuracy: 0.3125 - loss: 2.0775
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3062 - loss: 1.9774  
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3131 - loss: 1.9626
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3116 - loss: 1.9602
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3079 - loss: 1.9644
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3050 - loss: 1.9670
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3021 - loss: 1.9696
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2997 - loss: 1.9722
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2980 - loss: 1.9744
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2968 - loss: 1.9758
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2960 - loss: 1.9766
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2953 - loss: 1.9770
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2947 - loss: 1.9777
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2940 - loss: 1.9786
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2933 - loss: 1.9797
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2928 - loss: 1.9808
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2924 - loss: 1.9816
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2921 - loss: 1.9823
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2917 - loss: 1.9829
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2913 - loss: 1.9834
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2909 - loss: 1.9838
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2905 - loss: 1.9841
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2902 - loss: 1.9844
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2899 - loss: 1.9846
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2896 - loss: 1.9847
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2894 - loss: 1.9848
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2892 - loss: 1.9849
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2890 - loss: 1.9850
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2888 - loss: 1.9851 - val_accuracy: 0.2751 - val_loss: 1.9645
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 2.0347
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3221 - loss: 1.9735  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3054 - loss: 1.9855
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2995 - loss: 1.9891
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2977 - loss: 1.9880
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2967 - loss: 1.9885
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2967 - loss: 1.9875
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2967 - loss: 1.9868
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2966 - loss: 1.9869
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2962 - loss: 1.9876
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2961 - loss: 1.9878
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2958 - loss: 1.9879
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2955 - loss: 1.9879
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2953 - loss: 1.9877
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2951 - loss: 1.9872
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2949 - loss: 1.9868
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2946 - loss: 1.9863
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2943 - loss: 1.9859
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2941 - loss: 1.9856
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2938 - loss: 1.9853
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2936 - loss: 1.9852
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2934 - loss: 1.9849
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2932 - loss: 1.9848
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2931 - loss: 1.9846
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2929 - loss: 1.9844
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2929 - loss: 1.9842
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2928 - loss: 1.9840
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2927 - loss: 1.9837
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2927 - loss: 1.9834
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2926 - loss: 1.9832 - val_accuracy: 0.2788 - val_loss: 1.9685

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 626ms/step
[1m64/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 802us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7:47[0m 802ms/step
[1m 70/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 728us/step  
[1m141/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 719us/step
[1m211/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 719us/step
[1m282/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 716us/step
[1m351/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 718us/step
[1m423/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 715us/step
[1m493/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 715us/step
[1m564/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 714us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m67/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 760us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 65/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 789us/step
[1m138/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 734us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 28.6 [%]
Global F1 score (validation) = 24.66 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.11460207 0.13933861 0.16129087 ... 0.00247064 0.0826941  0.01361594]
 [0.14288685 0.19148542 0.2172681  ... 0.00122196 0.10752144 0.0213616 ]
 [0.10761796 0.14719872 0.13119017 ... 0.00514652 0.07365541 0.01176317]
 ...
 [0.14934704 0.19855607 0.19500643 ... 0.00154208 0.10751739 0.02558014]
 [0.20867547 0.16327068 0.20257849 ... 0.00111167 0.12577331 0.04803491]
 [0.10985429 0.15228248 0.14376211 ... 0.0035738  0.07452627 0.01139904]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 29.55 [%]
Global accuracy score (test) = 24.77 [%]
Global F1 score (train) = 25.62 [%]
Global F1 score (test) = 21.71 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.00      0.00      0.00       184
 CAMINAR CON MÓVIL O LIBRO       0.21      0.21      0.21       184
       CAMINAR USUAL SPEED       0.17      0.29      0.21       184
            CAMINAR ZIGZAG       0.12      0.10      0.11       184
          DE PIE BARRIENDO       0.14      0.46      0.21       184
   DE PIE DOBLANDO TOALLAS       0.26      0.33      0.29       184
    DE PIE MOVIENDO LIBROS       0.13      0.02      0.04       184
          DE PIE USANDO PC       0.27      0.76      0.40       184
        FASE REPOSO CON K5       0.79      0.70      0.74       184
INCREMENTAL CICLOERGOMETRO       0.45      0.08      0.14       184
           SENTADO LEYENDO       0.23      0.38      0.28       184
         SENTADO USANDO PC       0.08      0.03      0.05       184
      SENTADO VIENDO LA TV       0.50      0.08      0.13       184
   SUBIR Y BAJAR ESCALERAS       0.00      0.00      0.00       184
                    TROTAR       1.00      0.29      0.44       161

                  accuracy                           0.25      2737
                 macro avg       0.29      0.25      0.22      2737
              weighted avg       0.28      0.25      0.22      2737


Accuracy capturado en la ejecución 1: 24.77 [%]
F1-score capturado en la ejecución 1: 21.71 [%]

=== EJECUCIÓN 2 ===

--- TRAIN (ejecución 2) ---

--- TEST (ejecución 2) ---
2025-11-07 14:07:53.834862: 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 14:07:53.846500: 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 00:00:1762520873.859992 2915515 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762520873.864168 2915515 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762520873.873915 2915515 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762520873.873933 2915515 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762520873.873935 2915515 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762520873.873936 2915515 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:07:53.877054: 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 00:00:1762520876.139653 2915515 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762520877.625806 2915625 service.cc:152] XLA service 0x75e41c003e20 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762520877.625845 2915625 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:07:57.653275: 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 00:00:1762520877.800368 2915625 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762520879.207950 2915625 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47:05[0m 2s/step - accuracy: 0.0000e+00 - loss: 4.1749
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0688 - loss: 3.4699      
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0720 - loss: 3.3989
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0746 - loss: 3.3744
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0762 - loss: 3.3578
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0780 - loss: 3.3420
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0795 - loss: 3.3280
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0808 - loss: 3.3136
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0822 - loss: 3.2996
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0833 - loss: 3.2875
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0842 - loss: 3.2758
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0850 - loss: 3.2660
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0855 - loss: 3.2569
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0860 - loss: 3.2471
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0866 - loss: 3.2374
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0870 - loss: 3.2297
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0874 - loss: 3.2207
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0878 - loss: 3.2120
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0883 - loss: 3.2033
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0887 - loss: 3.1948
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0891 - loss: 3.1864
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0895 - loss: 3.1785
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0899 - loss: 3.1717
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0904 - loss: 3.1641
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0908 - loss: 3.1572
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0913 - loss: 3.1506
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0918 - loss: 3.1435
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0923 - loss: 3.1364
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0927 - loss: 3.1300
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0931 - loss: 3.1252
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0931 - loss: 3.1250 - val_accuracy: 0.1711 - val_loss: 2.5297
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.1250 - loss: 2.7642
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1208 - loss: 2.7707  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1305 - loss: 2.7490
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1361 - loss: 2.7331
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1394 - loss: 2.7197
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1414 - loss: 2.7098
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1425 - loss: 2.7027
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1432 - loss: 2.6974
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1438 - loss: 2.6928
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1444 - loss: 2.6885
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1448 - loss: 2.6844
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1452 - loss: 2.6810
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1457 - loss: 2.6774
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1460 - loss: 2.6742
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1463 - loss: 2.6717
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1465 - loss: 2.6691
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1469 - loss: 2.6663
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1473 - loss: 2.6637
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1477 - loss: 2.6611
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1480 - loss: 2.6587
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1484 - loss: 2.6561
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1488 - loss: 2.6533
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1492 - loss: 2.6509
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1496 - loss: 2.6486
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1499 - loss: 2.6466
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1503 - loss: 2.6441
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1507 - loss: 2.6420
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1511 - loss: 2.6398
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1515 - loss: 2.6375
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1519 - loss: 2.6352
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1519 - loss: 2.6349 - val_accuracy: 0.2100 - val_loss: 2.3901
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.5365
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1641 - loss: 2.4900  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1585 - loss: 2.4981
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1613 - loss: 2.4981
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1651 - loss: 2.4969
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1677 - loss: 2.4959
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1701 - loss: 2.4932
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1719 - loss: 2.4906
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1734 - loss: 2.4884
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1748 - loss: 2.4865
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1757 - loss: 2.4850
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1766 - loss: 2.4835
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1774 - loss: 2.4819
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1780 - loss: 2.4807
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1786 - loss: 2.4794
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1790 - loss: 2.4782
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1794 - loss: 2.4771
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1798 - loss: 2.4758
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1801 - loss: 2.4747
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1805 - loss: 2.4736
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1809 - loss: 2.4724
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1813 - loss: 2.4713
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1818 - loss: 2.4701
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1822 - loss: 2.4690
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1825 - loss: 2.4680
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1828 - loss: 2.4670
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1831 - loss: 2.4661
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1833 - loss: 2.4652
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1836 - loss: 2.4644
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1838 - loss: 2.4636 - val_accuracy: 0.2178 - val_loss: 2.3182
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.4015
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2241 - loss: 2.3571  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2194 - loss: 2.3646
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2142 - loss: 2.3689
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2113 - loss: 2.3711
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2099 - loss: 2.3707
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2090 - loss: 2.3716
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2084 - loss: 2.3721
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2083 - loss: 2.3718
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2080 - loss: 2.3720
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2077 - loss: 2.3721
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2075 - loss: 2.3721
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2072 - loss: 2.3722
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2070 - loss: 2.3721
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2067 - loss: 2.3722
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2065 - loss: 2.3724
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2062 - loss: 2.3724
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2059 - loss: 2.3726
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2057 - loss: 2.3727
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2055 - loss: 2.3728
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2053 - loss: 2.3728
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2052 - loss: 2.3727
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2051 - loss: 2.3725
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2050 - loss: 2.3724
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2049 - loss: 2.3722
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2049 - loss: 2.3720
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2048 - loss: 2.3718
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2048 - loss: 2.3715
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2048 - loss: 2.3712
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2049 - loss: 2.3709
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2049 - loss: 2.3708 - val_accuracy: 0.2422 - val_loss: 2.2552
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.3908
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1805 - loss: 2.3267  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1979 - loss: 2.3061
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2027 - loss: 2.3070
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2041 - loss: 2.3093
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2051 - loss: 2.3111
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2058 - loss: 2.3117
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2059 - loss: 2.3127
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2060 - loss: 2.3132
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2061 - loss: 2.3138
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2059 - loss: 2.3148
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2057 - loss: 2.3156
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2057 - loss: 2.3160
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2057 - loss: 2.3163
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2055 - loss: 2.3168
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2054 - loss: 2.3172
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2055 - loss: 2.3174
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2057 - loss: 2.3175
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2060 - loss: 2.3174
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2063 - loss: 2.3172
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2066 - loss: 2.3168
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2069 - loss: 2.3165
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2072 - loss: 2.3163
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2076 - loss: 2.3158
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2080 - loss: 2.3154
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2083 - loss: 2.3151
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2086 - loss: 2.3148
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2089 - loss: 2.3145
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2091 - loss: 2.3142
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2094 - loss: 2.3138
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.2097 - loss: 2.3135
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2097 - loss: 2.3135 - val_accuracy: 0.2300 - val_loss: 2.2242
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.5814
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2162 - loss: 2.2930  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2152 - loss: 2.2840
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2133 - loss: 2.2922
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2125 - loss: 2.2941
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2123 - loss: 2.2946
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2121 - loss: 2.2942
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2119 - loss: 2.2948
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2119 - loss: 2.2947
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2122 - loss: 2.2940
[1m 387/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2124 - loss: 2.2935
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2127 - loss: 2.2926
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2131 - loss: 2.2914
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2135 - loss: 2.2903
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2140 - loss: 2.2892
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2143 - loss: 2.2882
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2146 - loss: 2.2873
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2150 - loss: 2.2863
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2153 - loss: 2.2855
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2156 - loss: 2.2845
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2160 - loss: 2.2834
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2163 - loss: 2.2825
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2165 - loss: 2.2816
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2168 - loss: 2.2808
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2169 - loss: 2.2800
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2172 - loss: 2.2793
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2173 - loss: 2.2787
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2175 - loss: 2.2781
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2176 - loss: 2.2776
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2178 - loss: 2.2771
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2179 - loss: 2.2768 - val_accuracy: 0.2472 - val_loss: 2.1858
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.1121
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2270 - loss: 2.2290  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2311 - loss: 2.2259
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2272 - loss: 2.2350
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2266 - loss: 2.2394
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2274 - loss: 2.2393
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2281 - loss: 2.2388
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2289 - loss: 2.2386
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2293 - loss: 2.2388
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2296 - loss: 2.2385
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2301 - loss: 2.2377
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2304 - loss: 2.2370
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2306 - loss: 2.2367
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2308 - loss: 2.2362
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2310 - loss: 2.2359
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2311 - loss: 2.2355
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2313 - loss: 2.2352
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2315 - loss: 2.2349
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2316 - loss: 2.2346
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2317 - loss: 2.2342
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2319 - loss: 2.2337
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2320 - loss: 2.2330
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2321 - loss: 2.2326
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2322 - loss: 2.2321
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2322 - loss: 2.2318
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2322 - loss: 2.2316
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2322 - loss: 2.2313
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2322 - loss: 2.2310
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2323 - loss: 2.2307
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2323 - loss: 2.2304
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2324 - loss: 2.2301 - val_accuracy: 0.2459 - val_loss: 2.1408
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 1.9320
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2717 - loss: 2.1746  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2585 - loss: 2.1833
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2547 - loss: 2.1854
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2531 - loss: 2.1874
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2526 - loss: 2.1882
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2517 - loss: 2.1897
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2504 - loss: 2.1917
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2492 - loss: 2.1930
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2480 - loss: 2.1941
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2468 - loss: 2.1953
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2458 - loss: 2.1961
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2450 - loss: 2.1966
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2443 - loss: 2.1970
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2438 - loss: 2.1972
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2434 - loss: 2.1972
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2430 - loss: 2.1972
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2427 - loss: 2.1970
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2425 - loss: 2.1968
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2422 - loss: 2.1967
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2420 - loss: 2.1964
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2418 - loss: 2.1962
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2417 - loss: 2.1960
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2416 - loss: 2.1957
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2415 - loss: 2.1954
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2415 - loss: 2.1951
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2413 - loss: 2.1948
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2412 - loss: 2.1946
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2411 - loss: 2.1944
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2411 - loss: 2.1942
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2411 - loss: 2.1942 - val_accuracy: 0.2570 - val_loss: 2.1253
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.1875 - loss: 2.1028
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2416 - loss: 2.2355  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2394 - loss: 2.2232
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2431 - loss: 2.2110
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2439 - loss: 2.2057
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2435 - loss: 2.2023
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2431 - loss: 2.2004
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2427 - loss: 2.1981
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2425 - loss: 2.1957
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2424 - loss: 2.1943
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2425 - loss: 2.1925
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2425 - loss: 2.1911
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2425 - loss: 2.1899
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2425 - loss: 2.1891
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2425 - loss: 2.1885
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2425 - loss: 2.1882
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2424 - loss: 2.1880
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2423 - loss: 2.1877
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2423 - loss: 2.1873
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2423 - loss: 2.1869
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2423 - loss: 2.1865
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2423 - loss: 2.1861
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2424 - loss: 2.1856
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2424 - loss: 2.1852
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2424 - loss: 2.1848
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2424 - loss: 2.1843
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2424 - loss: 2.1838
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2423 - loss: 2.1835
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2423 - loss: 2.1830
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2423 - loss: 2.1825
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2423 - loss: 2.1824 - val_accuracy: 0.2605 - val_loss: 2.1148
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.1173
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2624 - loss: 2.1535  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2492 - loss: 2.1476
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2501 - loss: 2.1422
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2490 - loss: 2.1408
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2484 - loss: 2.1409
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2480 - loss: 2.1400
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2486 - loss: 2.1386
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2492 - loss: 2.1372
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2494 - loss: 2.1370
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2495 - loss: 2.1366
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2497 - loss: 2.1362
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2498 - loss: 2.1361
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2497 - loss: 2.1364
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2496 - loss: 2.1369
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2494 - loss: 2.1375
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2492 - loss: 2.1381
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2490 - loss: 2.1386
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2489 - loss: 2.1389
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2489 - loss: 2.1391
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2490 - loss: 2.1391
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2490 - loss: 2.1392
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2491 - loss: 2.1392
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2491 - loss: 2.1392
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2491 - loss: 2.1392
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2491 - loss: 2.1391
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2492 - loss: 2.1390
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2492 - loss: 2.1389
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2493 - loss: 2.1387
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2494 - loss: 2.1385
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2494 - loss: 2.1385 - val_accuracy: 0.2651 - val_loss: 2.0734
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0000e+00 - loss: 2.3869
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2276 - loss: 2.1686      
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2443 - loss: 2.1367
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2473 - loss: 2.1323
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2487 - loss: 2.1334
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2501 - loss: 2.1348
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2506 - loss: 2.1364
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2513 - loss: 2.1363
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2523 - loss: 2.1353
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2531 - loss: 2.1347
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2540 - loss: 2.1341
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.1333
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2553 - loss: 2.1327
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.1318
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2562 - loss: 2.1312
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2564 - loss: 2.1308
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.1306
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2566 - loss: 2.1304
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.1302
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.1300
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.1298
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.1295
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.1293
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.1292
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.1290
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.1287
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.1285
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.1282
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.1279
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2567 - loss: 2.1277 - val_accuracy: 0.2640 - val_loss: 2.0723
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.1625
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2396 - loss: 2.1616  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2454 - loss: 2.1411
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2460 - loss: 2.1356
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2468 - loss: 2.1289
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2488 - loss: 2.1230
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2511 - loss: 2.1179
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2524 - loss: 2.1155
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2539 - loss: 2.1131
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2549 - loss: 2.1111
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2555 - loss: 2.1101
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.1095
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2564 - loss: 2.1092
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.1092
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.1093
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2571 - loss: 2.1091
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2574 - loss: 2.1089
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2575 - loss: 2.1087
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2576 - loss: 2.1085
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.1082
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.1081
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.1079
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2580 - loss: 2.1077
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.1075
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.1074
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2582 - loss: 2.1072
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2583 - loss: 2.1069
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2585 - loss: 2.1066
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2587 - loss: 2.1063
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2588 - loss: 2.1060
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2589 - loss: 2.1058 - val_accuracy: 0.2760 - val_loss: 2.0418
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 1.9479
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2758 - loss: 2.0198  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2714 - loss: 2.0533
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2692 - loss: 2.0649
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2673 - loss: 2.0713
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0763
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0790
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0803
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0810
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0811
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0813
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0816
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0817
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0819
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0823
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0827
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0829
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0831
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0833
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0835
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0836
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0836
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0837
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0836
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0835
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0833
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0832
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0830
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0829
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0828
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2663 - loss: 2.0827 - val_accuracy: 0.2755 - val_loss: 2.0334
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.4375 - loss: 2.0556
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3046 - loss: 2.0786  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2881 - loss: 2.0700
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2821 - loss: 2.0632
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2792 - loss: 2.0616
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2784 - loss: 2.0616
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2780 - loss: 2.0606
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2774 - loss: 2.0597
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2767 - loss: 2.0585
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0580
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2756 - loss: 2.0576
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2753 - loss: 2.0571
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0570
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0570
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0571
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0575
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2734 - loss: 2.0581
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2730 - loss: 2.0586
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2726 - loss: 2.0590
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2723 - loss: 2.0595
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2719 - loss: 2.0600
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0604
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2714 - loss: 2.0607
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2712 - loss: 2.0610
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0612
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0613
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0614
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0615
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2706 - loss: 2.0615
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2706 - loss: 2.0616
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2706 - loss: 2.0616 - val_accuracy: 0.2809 - val_loss: 2.0130
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 1.9681
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2427 - loss: 2.0889  
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2601 - loss: 2.0692
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0628
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0644
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0646
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2680 - loss: 2.0633
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2683 - loss: 2.0630
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2680 - loss: 2.0639
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2678 - loss: 2.0647
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0650
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0648
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0649
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0649
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0648
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0645
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0642
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0640
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0639
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0638
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0638
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0637
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0637
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0636
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0634
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0632
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0631
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0629
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0627
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0625
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2669 - loss: 2.0624 - val_accuracy: 0.2755 - val_loss: 2.0280
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.2500 - loss: 1.8384
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2764 - loss: 1.9825  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0166
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2728 - loss: 2.0332
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0377
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0421
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0453
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0478
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0502
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2654 - loss: 2.0521
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2647 - loss: 2.0531
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0536
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2640 - loss: 2.0538
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2640 - loss: 2.0537
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2641 - loss: 2.0536
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0534
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2643 - loss: 2.0532
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0530
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2647 - loss: 2.0528
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0522
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2654 - loss: 2.0516
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0511
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0508
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0505
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0502
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0498
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0494
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0490
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0488
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0486
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2668 - loss: 2.0486 - val_accuracy: 0.2931 - val_loss: 1.9943
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.0083
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3303 - loss: 1.9202  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3093 - loss: 1.9421
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3020 - loss: 1.9556
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2984 - loss: 1.9663
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2955 - loss: 1.9739
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2925 - loss: 1.9816
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2901 - loss: 1.9876
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2886 - loss: 1.9914
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2875 - loss: 1.9945
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2865 - loss: 1.9973
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2856 - loss: 1.9996
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2844 - loss: 2.0023
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2834 - loss: 2.0045
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2826 - loss: 2.0064
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2818 - loss: 2.0082
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 2.0098
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 2.0112
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 2.0123
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 2.0135
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2791 - loss: 2.0143
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2787 - loss: 2.0152
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2784 - loss: 2.0159
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2782 - loss: 2.0167
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2780 - loss: 2.0173
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2779 - loss: 2.0177
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2778 - loss: 2.0181
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 2.0184
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 2.0186
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2774 - loss: 2.0189
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2774 - loss: 2.0190 - val_accuracy: 0.2871 - val_loss: 1.9915
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.0045
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2986 - loss: 2.0343  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2985 - loss: 2.0085
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2950 - loss: 2.0051
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2925 - loss: 2.0049
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2901 - loss: 2.0049
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2880 - loss: 2.0056
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2861 - loss: 2.0066
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2847 - loss: 2.0080
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2835 - loss: 2.0095
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2828 - loss: 2.0104
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2821 - loss: 2.0116
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2814 - loss: 2.0127
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 2.0134
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2807 - loss: 2.0140
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 2.0144
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 2.0145
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 2.0146
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 2.0147
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 2.0148
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 2.0150
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 2.0152
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 2.0154
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 2.0156
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 2.0158
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 2.0159
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 2.0160
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 2.0161
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 2.0163
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 2.0164
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2804 - loss: 2.0164 - val_accuracy: 0.2812 - val_loss: 1.9735
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.4713
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3033 - loss: 1.9411  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2975 - loss: 1.9472
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2936 - loss: 1.9575
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2905 - loss: 1.9666
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2875 - loss: 1.9738
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2857 - loss: 1.9784
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2847 - loss: 1.9819
[1m 306/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2841 - loss: 1.9848
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2837 - loss: 1.9875
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2834 - loss: 1.9897
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2831 - loss: 1.9922
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2829 - loss: 1.9947
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2827 - loss: 1.9966
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2826 - loss: 1.9981
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2826 - loss: 1.9991
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2826 - loss: 1.9999
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2827 - loss: 2.0007
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2828 - loss: 2.0014
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2829 - loss: 2.0017
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2830 - loss: 2.0020
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2831 - loss: 2.0021
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2832 - loss: 2.0024
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2833 - loss: 2.0026
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2834 - loss: 2.0028
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2835 - loss: 2.0030
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2835 - loss: 2.0033
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2835 - loss: 2.0035
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2834 - loss: 2.0038
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2834 - loss: 2.0040
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2834 - loss: 2.0041 - val_accuracy: 0.2932 - val_loss: 1.9745
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.8210
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3014 - loss: 2.0361  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2864 - loss: 2.0371
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2813 - loss: 2.0323
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2778 - loss: 2.0283
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2767 - loss: 2.0249
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2760 - loss: 2.0227
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2755 - loss: 2.0213
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0211
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2746 - loss: 2.0208
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2746 - loss: 2.0207
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0204
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0201
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0198
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2753 - loss: 2.0197
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2754 - loss: 2.0194
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2756 - loss: 2.0190
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2757 - loss: 2.0183
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2758 - loss: 2.0177
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2760 - loss: 2.0170
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2763 - loss: 2.0163
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2764 - loss: 2.0158
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2767 - loss: 2.0152
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2769 - loss: 2.0146
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2771 - loss: 2.0140
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2774 - loss: 2.0134
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 2.0129
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2777 - loss: 2.0124
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2779 - loss: 2.0121
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2780 - loss: 2.0117
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2781 - loss: 2.0116 - val_accuracy: 0.2886 - val_loss: 1.9548
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 19ms/step - accuracy: 0.3125 - loss: 1.8692
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2395 - loss: 2.1034  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2521 - loss: 2.0711
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2574 - loss: 2.0559
[1m 172/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2606 - loss: 2.0500
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0463
[1m 249/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0420
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2683 - loss: 2.0379
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0346
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2720 - loss: 2.0314
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2734 - loss: 2.0288
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0264
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2755 - loss: 2.0247
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0235
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2766 - loss: 2.0222
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2772 - loss: 2.0206
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2778 - loss: 2.0192
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2783 - loss: 2.0179
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2787 - loss: 2.0166
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2790 - loss: 2.0156
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2793 - loss: 2.0147
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 2.0138
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2798 - loss: 2.0129
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2800 - loss: 2.0121
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2802 - loss: 2.0114
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2803 - loss: 2.0107
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 2.0102
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 2.0096
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 2.0091
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2806 - loss: 2.0088 - val_accuracy: 0.2870 - val_loss: 1.9687
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 2.2566
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3161 - loss: 1.9422  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3084 - loss: 1.9410
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3069 - loss: 1.9400
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3061 - loss: 1.9417
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3052 - loss: 1.9448
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3038 - loss: 1.9488
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3031 - loss: 1.9527
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3022 - loss: 1.9566
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3011 - loss: 1.9595
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3002 - loss: 1.9615
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2993 - loss: 1.9632
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2985 - loss: 1.9647
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2977 - loss: 1.9663
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2969 - loss: 1.9680
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2962 - loss: 1.9696
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2955 - loss: 1.9709
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2951 - loss: 1.9718
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2946 - loss: 1.9728
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2943 - loss: 1.9736
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2940 - loss: 1.9742
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2938 - loss: 1.9746
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2936 - loss: 1.9750
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2934 - loss: 1.9754
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2933 - loss: 1.9757
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2932 - loss: 1.9760
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2931 - loss: 1.9762
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2930 - loss: 1.9764
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2929 - loss: 1.9766
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2927 - loss: 1.9768 - val_accuracy: 0.2969 - val_loss: 1.9693
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0035
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3206 - loss: 1.8954  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3075 - loss: 1.9214
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2974 - loss: 1.9439
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2930 - loss: 1.9531
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2913 - loss: 1.9570
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2901 - loss: 1.9594
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2899 - loss: 1.9608
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2904 - loss: 1.9609
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2908 - loss: 1.9611
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2913 - loss: 1.9613
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2919 - loss: 1.9613
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2925 - loss: 1.9611
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2929 - loss: 1.9610
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2931 - loss: 1.9612
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2933 - loss: 1.9615
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2934 - loss: 1.9618
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2935 - loss: 1.9619
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2935 - loss: 1.9620
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2935 - loss: 1.9622
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2934 - loss: 1.9624
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2933 - loss: 1.9626
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2932 - loss: 1.9627
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2931 - loss: 1.9629
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2930 - loss: 1.9631
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2929 - loss: 1.9632
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2928 - loss: 1.9634
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2927 - loss: 1.9636
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2927 - loss: 1.9639
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2926 - loss: 1.9641
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2925 - loss: 1.9642 - val_accuracy: 0.2962 - val_loss: 1.9470
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 1.9813
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3151 - loss: 1.8543  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3034 - loss: 1.8943
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2972 - loss: 1.9187
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2946 - loss: 1.9274
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2928 - loss: 1.9352
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2920 - loss: 1.9401
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2918 - loss: 1.9444
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2919 - loss: 1.9474
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2923 - loss: 1.9498
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2924 - loss: 1.9515
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2924 - loss: 1.9532
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2925 - loss: 1.9545
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2925 - loss: 1.9554
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2925 - loss: 1.9563
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2924 - loss: 1.9570
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2924 - loss: 1.9574
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2923 - loss: 1.9577
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2922 - loss: 1.9579
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2921 - loss: 1.9582
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2921 - loss: 1.9582
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2921 - loss: 1.9583
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2921 - loss: 1.9583
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2921 - loss: 1.9583
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2921 - loss: 1.9584
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2921 - loss: 1.9586
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2922 - loss: 1.9587
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2922 - loss: 1.9588
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2923 - loss: 1.9590
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2923 - loss: 1.9591
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.2923 - loss: 1.9593
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2923 - loss: 1.9593 - val_accuracy: 0.2768 - val_loss: 1.9820
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 1.9345
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2982 - loss: 2.0028  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2978 - loss: 1.9814
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2997 - loss: 1.9763
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2995 - loss: 1.9735
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2988 - loss: 1.9728
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2989 - loss: 1.9704
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2988 - loss: 1.9691
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2979 - loss: 1.9688
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2973 - loss: 1.9680
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2967 - loss: 1.9676
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2966 - loss: 1.9669
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2967 - loss: 1.9664
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2967 - loss: 1.9662
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2965 - loss: 1.9663
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2963 - loss: 1.9664
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2961 - loss: 1.9665
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2960 - loss: 1.9666
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2958 - loss: 1.9669
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2957 - loss: 1.9670
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2957 - loss: 1.9672
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2956 - loss: 1.9672
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2955 - loss: 1.9671
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2955 - loss: 1.9670
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2955 - loss: 1.9668
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2955 - loss: 1.9665
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2955 - loss: 1.9663
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2955 - loss: 1.9660
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2955 - loss: 1.9659
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2955 - loss: 1.9657 - val_accuracy: 0.2873 - val_loss: 1.9598

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 644ms/step
[1m65/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 786us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7:53[0m 811ms/step
[1m 66/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 776us/step  
[1m133/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 763us/step
[1m203/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 748us/step
[1m270/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 750us/step
[1m339/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 746us/step
[1m409/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 742us/step
[1m479/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 738us/step
[1m547/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 738us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m70/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 729us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 66/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 780us/step
[1m132/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 770us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 27.88 [%]
Global F1 score (validation) = 25.81 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.17513952 0.19968244 0.15179807 ... 0.00308872 0.11157373 0.01499727]
 [0.20166543 0.22174646 0.17806703 ... 0.00043754 0.13015823 0.03774919]
 [0.10665143 0.14081244 0.1638073  ... 0.0058196  0.10185832 0.0270646 ]
 ...
 [0.22203551 0.22131255 0.1747745  ... 0.00165989 0.13145164 0.02868024]
 [0.16640534 0.17909506 0.17422253 ... 0.00261513 0.13060746 0.01643953]
 [0.10963723 0.11873872 0.09550044 ... 0.0139314  0.09501833 0.01153223]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 31.9 [%]
Global accuracy score (test) = 24.19 [%]
Global F1 score (train) = 29.77 [%]
Global F1 score (test) = 22.56 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.10      0.07      0.08       184
 CAMINAR CON MÓVIL O LIBRO       0.16      0.47      0.24       184
       CAMINAR USUAL SPEED       0.13      0.13      0.13       184
            CAMINAR ZIGZAG       0.11      0.03      0.04       184
          DE PIE BARRIENDO       0.18      0.29      0.22       184
   DE PIE DOBLANDO TOALLAS       0.12      0.11      0.12       184
    DE PIE MOVIENDO LIBROS       0.23      0.24      0.23       184
          DE PIE USANDO PC       0.26      0.76      0.39       184
        FASE REPOSO CON K5       0.88      0.51      0.64       184
INCREMENTAL CICLOERGOMETRO       0.73      0.15      0.24       184
           SENTADO LEYENDO       0.22      0.23      0.23       184
         SENTADO USANDO PC       0.21      0.27      0.24       184
      SENTADO VIENDO LA TV       0.06      0.01      0.01       184
   SUBIR Y BAJAR ESCALERAS       0.00      0.00      0.00       184
                    TROTAR       1.00      0.40      0.58       161

                  accuracy                           0.24      2737
                 macro avg       0.29      0.24      0.23      2737
              weighted avg       0.29      0.24      0.22      2737


Accuracy capturado en la ejecución 2: 24.19 [%]
F1-score capturado en la ejecución 2: 22.56 [%]

=== EJECUCIÓN 3 ===

--- TRAIN (ejecución 3) ---

--- TEST (ejecución 3) ---
2025-11-07 14:09:01.531815: 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 14:09:01.543340: 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 00:00:1762520941.556650 2919252 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762520941.560734 2919252 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762520941.570628 2919252 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762520941.570646 2919252 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762520941.570647 2919252 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762520941.570648 2919252 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:09:01.573836: 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 00:00:1762520943.864789 2919252 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762520945.363419 2919384 service.cc:152] XLA service 0x79fb9401d530 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762520945.363477 2919384 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:09:05.395662: 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 00:00:1762520945.539559 2919384 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762520946.925677 2919384 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46:49[0m 2s/step - accuracy: 0.0625 - loss: 3.5639
[1m  32/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0487 - loss: 3.2904  
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0511 - loss: 3.2571
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0549 - loss: 3.2268
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0570 - loss: 3.2082
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0582 - loss: 3.1976
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0595 - loss: 3.1878
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0609 - loss: 3.1797
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0622 - loss: 3.1720
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0634 - loss: 3.1653
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0645 - loss: 3.1582
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0655 - loss: 3.1519
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0664 - loss: 3.1446
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0673 - loss: 3.1381
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0681 - loss: 3.1315
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0689 - loss: 3.1260
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0695 - loss: 3.1204
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0701 - loss: 3.1155
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0707 - loss: 3.1102
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0713 - loss: 3.1057
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0719 - loss: 3.1005
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0723 - loss: 3.0964
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0729 - loss: 3.0913
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0736 - loss: 3.0864
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0742 - loss: 3.0818
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0747 - loss: 3.0776
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0753 - loss: 3.0733
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0758 - loss: 3.0693
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0763 - loss: 3.0649
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0767 - loss: 3.0611
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0769 - loss: 3.0595
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0769 - loss: 3.0594 - val_accuracy: 0.1558 - val_loss: 2.6624
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.4830
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1388 - loss: 2.6788  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1333 - loss: 2.7065
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1279 - loss: 2.7248
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1240 - loss: 2.7390
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1219 - loss: 2.7448
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1207 - loss: 2.7489
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1201 - loss: 2.7521
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1199 - loss: 2.7542
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1198 - loss: 2.7551
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1198 - loss: 2.7557
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1198 - loss: 2.7563
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1198 - loss: 2.7566
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1198 - loss: 2.7566
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1198 - loss: 2.7564
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1199 - loss: 2.7557
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1200 - loss: 2.7550
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1202 - loss: 2.7540
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1205 - loss: 2.7528
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1207 - loss: 2.7514
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1209 - loss: 2.7500
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1212 - loss: 2.7486
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1214 - loss: 2.7473
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1216 - loss: 2.7459
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1218 - loss: 2.7444
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1220 - loss: 2.7430
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1222 - loss: 2.7417
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1224 - loss: 2.7403
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1226 - loss: 2.7390
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1227 - loss: 2.7378 - val_accuracy: 0.1865 - val_loss: 2.5373
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.0625 - loss: 2.9427
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1351 - loss: 2.6669  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1409 - loss: 2.6364
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1409 - loss: 2.6307
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1407 - loss: 2.6297
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1406 - loss: 2.6297
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1405 - loss: 2.6291
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1410 - loss: 2.6274
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1415 - loss: 2.6255
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1421 - loss: 2.6235
[1m 387/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1429 - loss: 2.6212
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1438 - loss: 2.6191
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1446 - loss: 2.6170
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1453 - loss: 2.6152
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1461 - loss: 2.6132
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1468 - loss: 2.6116
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1475 - loss: 2.6099
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1482 - loss: 2.6081
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1489 - loss: 2.6063
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1494 - loss: 2.6049
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1499 - loss: 2.6033
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1504 - loss: 2.6017
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1509 - loss: 2.6001
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1513 - loss: 2.5988
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1518 - loss: 2.5974
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1523 - loss: 2.5960
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1527 - loss: 2.5948
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1531 - loss: 2.5935
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1534 - loss: 2.5923
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1538 - loss: 2.5911
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1539 - loss: 2.5906 - val_accuracy: 0.2096 - val_loss: 2.4325
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.3811
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1992 - loss: 2.4521  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1936 - loss: 2.4589
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1896 - loss: 2.4664
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1877 - loss: 2.4717
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1854 - loss: 2.4752
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1848 - loss: 2.4761
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1843 - loss: 2.4761
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1839 - loss: 2.4761
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1834 - loss: 2.4765
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1830 - loss: 2.4769
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1827 - loss: 2.4770
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1827 - loss: 2.4769
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1827 - loss: 2.4766
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1827 - loss: 2.4764
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1828 - loss: 2.4761
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1828 - loss: 2.4756
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1828 - loss: 2.4752
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1829 - loss: 2.4747
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1829 - loss: 2.4742
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1829 - loss: 2.4738
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1830 - loss: 2.4732
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1830 - loss: 2.4727
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1831 - loss: 2.4723
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1832 - loss: 2.4718
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1833 - loss: 2.4713
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1834 - loss: 2.4707
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1836 - loss: 2.4701
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1837 - loss: 2.4695
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1839 - loss: 2.4689
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1839 - loss: 2.4687 - val_accuracy: 0.2089 - val_loss: 2.3345
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.0625 - loss: 2.6417
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1872 - loss: 2.4451  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1887 - loss: 2.4302
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1893 - loss: 2.4262
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1911 - loss: 2.4230
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1926 - loss: 2.4208
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1934 - loss: 2.4189
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1934 - loss: 2.4168
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1935 - loss: 2.4144
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1936 - loss: 2.4118
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1939 - loss: 2.4094
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1940 - loss: 2.4076
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1942 - loss: 2.4061
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1943 - loss: 2.4048
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1945 - loss: 2.4034
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1946 - loss: 2.4022
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1947 - loss: 2.4012
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1949 - loss: 2.4003
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1950 - loss: 2.3994
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1952 - loss: 2.3985
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1954 - loss: 2.3976
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1956 - loss: 2.3967
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1958 - loss: 2.3958
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1960 - loss: 2.3950
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1963 - loss: 2.3941
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1965 - loss: 2.3933
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1967 - loss: 2.3925
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1969 - loss: 2.3917
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1971 - loss: 2.3909
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1973 - loss: 2.3901 - val_accuracy: 0.2209 - val_loss: 2.2603
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.3336
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2056 - loss: 2.3366  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2047 - loss: 2.3377
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2055 - loss: 2.3397
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2051 - loss: 2.3441
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2050 - loss: 2.3464
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2058 - loss: 2.3462
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2066 - loss: 2.3462
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2069 - loss: 2.3461
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2070 - loss: 2.3459
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2073 - loss: 2.3450
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2074 - loss: 2.3443
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2074 - loss: 2.3432
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2075 - loss: 2.3420
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2077 - loss: 2.3407
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2079 - loss: 2.3394
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2080 - loss: 2.3382
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2081 - loss: 2.3370
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2080 - loss: 2.3358
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2080 - loss: 2.3348
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2080 - loss: 2.3338
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2081 - loss: 2.3329
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2081 - loss: 2.3321
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2082 - loss: 2.3313
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2083 - loss: 2.3304
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2085 - loss: 2.3296
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2086 - loss: 2.3287
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2088 - loss: 2.3279
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2089 - loss: 2.3272
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2090 - loss: 2.3265
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2090 - loss: 2.3265 - val_accuracy: 0.2266 - val_loss: 2.2159
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.3406
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1983 - loss: 2.3460  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2055 - loss: 2.3182
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2080 - loss: 2.3073
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2084 - loss: 2.3030
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2090 - loss: 2.3002
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2095 - loss: 2.2978
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2096 - loss: 2.2962
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2095 - loss: 2.2948
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2097 - loss: 2.2934
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2100 - loss: 2.2918
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2103 - loss: 2.2905
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2105 - loss: 2.2897
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2109 - loss: 2.2889
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2113 - loss: 2.2880
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2116 - loss: 2.2869
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2121 - loss: 2.2858
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2125 - loss: 2.2848
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2129 - loss: 2.2839
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2131 - loss: 2.2833
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2133 - loss: 2.2827
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2136 - loss: 2.2820
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2140 - loss: 2.2813
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2143 - loss: 2.2806
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2145 - loss: 2.2799
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2148 - loss: 2.2793
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2149 - loss: 2.2789
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2151 - loss: 2.2784
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2152 - loss: 2.2779
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2154 - loss: 2.2774
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2154 - loss: 2.2774 - val_accuracy: 0.2424 - val_loss: 2.1519
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.3750 - loss: 2.1773
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2712 - loss: 2.2329  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2484 - loss: 2.2543
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2412 - loss: 2.2579
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2367 - loss: 2.2586
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2342 - loss: 2.2589
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2326 - loss: 2.2590
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2313 - loss: 2.2589
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2306 - loss: 2.2582
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2303 - loss: 2.2568
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2298 - loss: 2.2556
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2296 - loss: 2.2546
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2295 - loss: 2.2533
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2295 - loss: 2.2521
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2294 - loss: 2.2512
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2293 - loss: 2.2504
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2292 - loss: 2.2496
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2292 - loss: 2.2489
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2292 - loss: 2.2479
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2292 - loss: 2.2472
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2291 - loss: 2.2464
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2291 - loss: 2.2456
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2292 - loss: 2.2446
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2292 - loss: 2.2437
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2292 - loss: 2.2428
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2293 - loss: 2.2419
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2293 - loss: 2.2409
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2293 - loss: 2.2401
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2293 - loss: 2.2395
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2293 - loss: 2.2388
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2293 - loss: 2.2383 - val_accuracy: 0.2455 - val_loss: 2.1111
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.1378
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2305 - loss: 2.1860  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2302 - loss: 2.1860
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2276 - loss: 2.1924
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2269 - loss: 2.1962
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2277 - loss: 2.1953
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2289 - loss: 2.1930
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2301 - loss: 2.1913
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2313 - loss: 2.1902
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2319 - loss: 2.1899
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2324 - loss: 2.1897
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2326 - loss: 2.1897
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2326 - loss: 2.1899
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2327 - loss: 2.1900
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2328 - loss: 2.1899
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2330 - loss: 2.1898
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2331 - loss: 2.1898
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2333 - loss: 2.1899
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2334 - loss: 2.1900
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2335 - loss: 2.1901
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2336 - loss: 2.1903
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2338 - loss: 2.1903
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2340 - loss: 2.1903
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2342 - loss: 2.1904
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2344 - loss: 2.1905
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2345 - loss: 2.1905
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2347 - loss: 2.1905
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2349 - loss: 2.1905
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2350 - loss: 2.1905
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2352 - loss: 2.1904
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2352 - loss: 2.1904 - val_accuracy: 0.2372 - val_loss: 2.1038
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.2500 - loss: 2.4214
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2796 - loss: 2.1012  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2705 - loss: 2.1052
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2662 - loss: 2.1202
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2630 - loss: 2.1308
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2607 - loss: 2.1368
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2587 - loss: 2.1417
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2573 - loss: 2.1451
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2561 - loss: 2.1479
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2550 - loss: 2.1505
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2540 - loss: 2.1525
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2530 - loss: 2.1543
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2521 - loss: 2.1557
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.1570
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2505 - loss: 2.1579
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2499 - loss: 2.1589
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2493 - loss: 2.1597
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2489 - loss: 2.1606
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2485 - loss: 2.1612
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2483 - loss: 2.1616
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2481 - loss: 2.1619
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2479 - loss: 2.1623
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2478 - loss: 2.1626
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2477 - loss: 2.1628
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2476 - loss: 2.1629
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2475 - loss: 2.1630
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2475 - loss: 2.1631
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2474 - loss: 2.1631
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2474 - loss: 2.1631
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2473 - loss: 2.1631
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2473 - loss: 2.1630 - val_accuracy: 0.2472 - val_loss: 2.0712
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3125 - loss: 2.3575
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2601 - loss: 2.1735  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2604 - loss: 2.1565
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2600 - loss: 2.1494
[1m 150/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2600 - loss: 2.1443
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2583 - loss: 2.1418
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2566 - loss: 2.1407
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2552 - loss: 2.1407
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2544 - loss: 2.1403
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2536 - loss: 2.1402
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2531 - loss: 2.1402
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.1401
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2524 - loss: 2.1403
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2520 - loss: 2.1408
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2517 - loss: 2.1409
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2516 - loss: 2.1407
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.1406
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2511 - loss: 2.1406
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2508 - loss: 2.1407
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2506 - loss: 2.1408
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2504 - loss: 2.1408
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2503 - loss: 2.1406
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.1404
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2501 - loss: 2.1402
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2501 - loss: 2.1399
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2500 - loss: 2.1396
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2500 - loss: 2.1393
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2500 - loss: 2.1390
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2501 - loss: 2.1387
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2501 - loss: 2.1384
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2501 - loss: 2.1383 - val_accuracy: 0.2574 - val_loss: 2.0564
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.1170
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2469 - loss: 2.1794  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2356 - loss: 2.1856
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2343 - loss: 2.1794
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2358 - loss: 2.1748
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2366 - loss: 2.1706
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2375 - loss: 2.1672
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2385 - loss: 2.1636
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2392 - loss: 2.1606
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2397 - loss: 2.1584
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2403 - loss: 2.1557
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2409 - loss: 2.1534
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2416 - loss: 2.1510
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2421 - loss: 2.1492
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2426 - loss: 2.1474
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2432 - loss: 2.1455
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2438 - loss: 2.1436
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2444 - loss: 2.1419
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2449 - loss: 2.1404
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.1389
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2459 - loss: 2.1375
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2463 - loss: 2.1363
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2467 - loss: 2.1352
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2470 - loss: 2.1342
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2473 - loss: 2.1334
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2476 - loss: 2.1326
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2478 - loss: 2.1319
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2481 - loss: 2.1312
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2483 - loss: 2.1306
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2484 - loss: 2.1304 - val_accuracy: 0.2625 - val_loss: 2.0551
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.5785
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2409 - loss: 2.1815  
[1m  86/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2428 - loss: 2.1906
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2467 - loss: 2.1843
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2496 - loss: 2.1747
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2519 - loss: 2.1663
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2537 - loss: 2.1601
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2550 - loss: 2.1557
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2555 - loss: 2.1527
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2554 - loss: 2.1507
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2556 - loss: 2.1482
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2557 - loss: 2.1461
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2557 - loss: 2.1441
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2557 - loss: 2.1421
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2558 - loss: 2.1403
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2558 - loss: 2.1387
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2558 - loss: 2.1376
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2558 - loss: 2.1364
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.1353
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.1343
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.1335
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.1325
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.1316
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.1307
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.1298
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.1289
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.1279
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.1270
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.1260
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2561 - loss: 2.1254 - val_accuracy: 0.2603 - val_loss: 2.0195
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 1.9772
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0724  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0728
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0692
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0692
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2696 - loss: 2.0691
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0692
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2692 - loss: 2.0694
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0700
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2690 - loss: 2.0710
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0720
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0729
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2678 - loss: 2.0737
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0741
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2673 - loss: 2.0746
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0750
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0755
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0759
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0764
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0770
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0775
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0778
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0780
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2647 - loss: 2.0782
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0786
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2643 - loss: 2.0789
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2641 - loss: 2.0791
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0793
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0795
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2636 - loss: 2.0796 - val_accuracy: 0.2736 - val_loss: 1.9958
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.3125 - loss: 1.8428
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2466 - loss: 2.0422  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2481 - loss: 2.0678
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2479 - loss: 2.0757
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2488 - loss: 2.0791
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2512 - loss: 2.0787
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2535 - loss: 2.0779
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2554 - loss: 2.0770
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0756
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2585 - loss: 2.0748
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2593 - loss: 2.0739
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2600 - loss: 2.0732
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2608 - loss: 2.0723
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2613 - loss: 2.0723
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2617 - loss: 2.0725
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2619 - loss: 2.0728
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2621 - loss: 2.0730
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2624 - loss: 2.0732
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2626 - loss: 2.0733
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2628 - loss: 2.0734
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0735
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2632 - loss: 2.0736
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0736
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2635 - loss: 2.0736
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0735
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2638 - loss: 2.0733
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2640 - loss: 2.0731
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2641 - loss: 2.0730
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2643 - loss: 2.0729
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0728
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2644 - loss: 2.0728 - val_accuracy: 0.2751 - val_loss: 1.9875
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 2.0336
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2970 - loss: 2.0522  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2811 - loss: 2.0706
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2801 - loss: 2.0708
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2803 - loss: 2.0680
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2798 - loss: 2.0672
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2797 - loss: 2.0658
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2797 - loss: 2.0641
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2793 - loss: 2.0627
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2787 - loss: 2.0617
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2780 - loss: 2.0612
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2774 - loss: 2.0615
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2770 - loss: 2.0616
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2765 - loss: 2.0621
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0623
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2758 - loss: 2.0623
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2755 - loss: 2.0624
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0624
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0624
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0623
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2742 - loss: 2.0620
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0616
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2738 - loss: 2.0612
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0609
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2735 - loss: 2.0604
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2733 - loss: 2.0600
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0596
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2729 - loss: 2.0592
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2727 - loss: 2.0589
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2726 - loss: 2.0587 - val_accuracy: 0.2779 - val_loss: 1.9822
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 2.0087
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2797 - loss: 2.0149  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2777 - loss: 2.0323
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2742 - loss: 2.0442
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2728 - loss: 2.0490
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0500
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0488
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0484
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2691 - loss: 2.0485
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0487
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2684 - loss: 2.0489
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2683 - loss: 2.0486
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2684 - loss: 2.0482
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2684 - loss: 2.0480
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2684 - loss: 2.0481
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2685 - loss: 2.0481
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0479
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0475
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2689 - loss: 2.0470
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2691 - loss: 2.0465
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2692 - loss: 2.0461
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2692 - loss: 2.0459
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2692 - loss: 2.0459
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2692 - loss: 2.0458
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2691 - loss: 2.0458
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2691 - loss: 2.0457
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2690 - loss: 2.0457
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2689 - loss: 2.0457
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2689 - loss: 2.0457
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2688 - loss: 2.0457 - val_accuracy: 0.2755 - val_loss: 1.9922
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.2628
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2374 - loss: 2.1337  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2451 - loss: 2.0986
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2500 - loss: 2.0829
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2536 - loss: 2.0724
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2551 - loss: 2.0667
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2566 - loss: 2.0615
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2576 - loss: 2.0587
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2582 - loss: 2.0573
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2588 - loss: 2.0556
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2594 - loss: 2.0542
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0534
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0523
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0512
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2615 - loss: 2.0500
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2618 - loss: 2.0491
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2621 - loss: 2.0481
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2624 - loss: 2.0472
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2628 - loss: 2.0463
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0456
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2634 - loss: 2.0450
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0445
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2640 - loss: 2.0440
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0436
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0431
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2647 - loss: 2.0425
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0421
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0417
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0413
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0410
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2657 - loss: 2.0408 - val_accuracy: 0.2762 - val_loss: 1.9739
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.4453
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2432 - loss: 2.0896  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2586 - loss: 2.0511
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0352
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0275
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0240
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2725 - loss: 2.0203
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2735 - loss: 2.0175
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2742 - loss: 2.0156
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0142
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0136
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0133
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0131
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0132
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0134
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0136
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0140
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2751 - loss: 2.0144
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0150
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2751 - loss: 2.0154
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2751 - loss: 2.0157
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2751 - loss: 2.0160
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2751 - loss: 2.0162
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0164
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0166
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0169
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2753 - loss: 2.0171
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2753 - loss: 2.0172
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2754 - loss: 2.0173
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2755 - loss: 2.0172
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2755 - loss: 2.0172 - val_accuracy: 0.2616 - val_loss: 2.0037
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 1.9821
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2508 - loss: 2.0278  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2627 - loss: 2.0260
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0249
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0224
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0214
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0196
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0176
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0164
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2705 - loss: 2.0158
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0148
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2725 - loss: 2.0140
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0135
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2739 - loss: 2.0132
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0128
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0122
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0118
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2755 - loss: 2.0114
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2755 - loss: 2.0113
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2756 - loss: 2.0112
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2756 - loss: 2.0111
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2757 - loss: 2.0110
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2758 - loss: 2.0109
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 2.0108
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2760 - loss: 2.0107
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2760 - loss: 2.0106
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0104
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2762 - loss: 2.0103
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2762 - loss: 2.0102
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2763 - loss: 2.0101 - val_accuracy: 0.2884 - val_loss: 1.9514
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3750 - loss: 1.9503
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3091 - loss: 1.9355  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3086 - loss: 1.9545
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3025 - loss: 1.9685
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2987 - loss: 1.9784
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2947 - loss: 1.9850
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2917 - loss: 1.9895
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2896 - loss: 1.9917
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2881 - loss: 1.9929
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2873 - loss: 1.9928
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2869 - loss: 1.9924
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2864 - loss: 1.9925
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2861 - loss: 1.9926
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2857 - loss: 1.9927
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2855 - loss: 1.9925
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2853 - loss: 1.9925
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2850 - loss: 1.9926
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2847 - loss: 1.9928
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2844 - loss: 1.9930
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2842 - loss: 1.9929
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2840 - loss: 1.9929
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2838 - loss: 1.9931
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2836 - loss: 1.9933
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2834 - loss: 1.9935
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2833 - loss: 1.9937
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2832 - loss: 1.9940
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2831 - loss: 1.9942
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2831 - loss: 1.9943
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2831 - loss: 1.9943
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2831 - loss: 1.9944
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2831 - loss: 1.9945 - val_accuracy: 0.2768 - val_loss: 1.9533
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3750 - loss: 1.9618
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2883 - loss: 1.9924  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2883 - loss: 1.9849
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2856 - loss: 1.9861
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2821 - loss: 1.9901
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2804 - loss: 1.9926
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2795 - loss: 1.9956
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2791 - loss: 1.9978
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2788 - loss: 1.9995
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2786 - loss: 2.0006
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2784 - loss: 2.0017
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2783 - loss: 2.0025
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2784 - loss: 2.0029
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2788 - loss: 2.0028
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2792 - loss: 2.0026
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 2.0023
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2797 - loss: 2.0019
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2800 - loss: 2.0014
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2802 - loss: 2.0010
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2803 - loss: 2.0007
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 2.0004
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 2.0002
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2807 - loss: 2.0001
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2808 - loss: 2.0000
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2809 - loss: 1.9998
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 1.9996
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 1.9995
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9993
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9990
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2813 - loss: 1.9988
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2814 - loss: 1.9987 - val_accuracy: 0.2807 - val_loss: 1.9596
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.1875 - loss: 2.1503
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0163  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0104
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2792 - loss: 2.0082
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2828 - loss: 2.0078
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2850 - loss: 2.0077
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2861 - loss: 2.0072
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2868 - loss: 2.0066
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2874 - loss: 2.0055
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2882 - loss: 2.0039
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2887 - loss: 2.0025
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2889 - loss: 2.0013
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2891 - loss: 2.0000
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2893 - loss: 1.9986
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2895 - loss: 1.9970
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2897 - loss: 1.9955
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2899 - loss: 1.9938
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2900 - loss: 1.9922
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2901 - loss: 1.9910
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2902 - loss: 1.9899
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2904 - loss: 1.9889
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2905 - loss: 1.9882
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2906 - loss: 1.9875
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2906 - loss: 1.9870
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2907 - loss: 1.9865
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2907 - loss: 1.9861
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2906 - loss: 1.9857
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2906 - loss: 1.9855
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2905 - loss: 1.9853
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2905 - loss: 1.9851
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2905 - loss: 1.9850 - val_accuracy: 0.2779 - val_loss: 1.9670
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.6731
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3073 - loss: 1.9014  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3026 - loss: 1.9276
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3006 - loss: 1.9442
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2989 - loss: 1.9509
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2977 - loss: 1.9546
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2973 - loss: 1.9568
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2972 - loss: 1.9581
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2974 - loss: 1.9586
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2976 - loss: 1.9586
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2978 - loss: 1.9586
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2979 - loss: 1.9588
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2980 - loss: 1.9592
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2979 - loss: 1.9595
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2978 - loss: 1.9600
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2975 - loss: 1.9605
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2971 - loss: 1.9610
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2968 - loss: 1.9615
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2966 - loss: 1.9621
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2963 - loss: 1.9626
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2960 - loss: 1.9629
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2958 - loss: 1.9633
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2956 - loss: 1.9637
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2954 - loss: 1.9642
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2952 - loss: 1.9646
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2950 - loss: 1.9650
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2948 - loss: 1.9653
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2947 - loss: 1.9655
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2946 - loss: 1.9657
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2944 - loss: 1.9659
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2944 - loss: 1.9660 - val_accuracy: 0.2912 - val_loss: 1.9509
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.1875 - loss: 2.0393
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2575 - loss: 1.9853  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2670 - loss: 1.9911
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2723 - loss: 1.9957
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2769 - loss: 1.9915
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2799 - loss: 1.9878
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2822 - loss: 1.9851
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2837 - loss: 1.9832
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2850 - loss: 1.9810
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2863 - loss: 1.9789
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2870 - loss: 1.9779
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2876 - loss: 1.9768
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2880 - loss: 1.9755
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2882 - loss: 1.9744
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2884 - loss: 1.9732
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2885 - loss: 1.9720
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2886 - loss: 1.9712
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2887 - loss: 1.9705
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2889 - loss: 1.9698
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2891 - loss: 1.9691
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2892 - loss: 1.9685
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2894 - loss: 1.9680
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2895 - loss: 1.9675
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2897 - loss: 1.9672
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2898 - loss: 1.9669
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2898 - loss: 1.9667
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2899 - loss: 1.9666
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2899 - loss: 1.9665
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2899 - loss: 1.9664
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2900 - loss: 1.9663
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2900 - loss: 1.9662 - val_accuracy: 0.2910 - val_loss: 1.9268

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m52s[0m 621ms/step
[1m66/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 779us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:12[0m 844ms/step
[1m 64/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 799us/step  
[1m132/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 771us/step
[1m206/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 740us/step
[1m284/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 716us/step
[1m347/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 731us/step
[1m419/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 726us/step
[1m494/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 719us/step
[1m568/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 713us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m59/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 874us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 69/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 740us/step
[1m135/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 749us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 28.73 [%]
Global F1 score (validation) = 23.62 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[1.73394665e-01 2.73510516e-01 1.34976864e-01 ... 7.81427429e-04
  1.12100288e-01 1.78803671e-02]
 [2.02889487e-01 2.33614966e-01 1.52324751e-01 ... 1.17549777e-03
  1.19575888e-01 2.01619491e-02]
 [1.90852046e-01 1.94028527e-01 1.66232735e-01 ... 1.00537867e-03
  1.78619385e-01 4.02830020e-02]
 ...
 [1.77984089e-01 2.45707810e-01 1.78475395e-01 ... 1.86881953e-04
  1.57084718e-01 2.45493557e-02]
 [1.23768196e-01 1.71817914e-01 1.10401832e-01 ... 5.36492420e-03
  8.36887136e-02 1.17951995e-02]
 [1.29886702e-01 1.77495569e-01 1.18627191e-01 ... 3.89111997e-03
  9.26769152e-02 1.09602213e-02]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 30.34 [%]
Global accuracy score (test) = 25.61 [%]
Global F1 score (train) = 25.77 [%]
Global F1 score (test) = 20.99 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.14      0.05      0.08       184
 CAMINAR CON MÓVIL O LIBRO       0.18      0.73      0.29       184
       CAMINAR USUAL SPEED       0.00      0.00      0.00       184
            CAMINAR ZIGZAG       0.00      0.00      0.00       184
          DE PIE BARRIENDO       0.25      0.61      0.35       184
   DE PIE DOBLANDO TOALLAS       0.40      0.01      0.02       184
    DE PIE MOVIENDO LIBROS       0.25      0.22      0.24       184
          DE PIE USANDO PC       0.30      0.69      0.41       184
        FASE REPOSO CON K5       0.97      0.34      0.50       184
INCREMENTAL CICLOERGOMETRO       0.61      0.26      0.36       184
           SENTADO LEYENDO       0.19      0.52      0.27       184
         SENTADO USANDO PC       0.21      0.08      0.11       184
      SENTADO VIENDO LA TV       0.00      0.00      0.00       184
   SUBIR Y BAJAR ESCALERAS       0.04      0.01      0.01       184
                    TROTAR       0.95      0.35      0.51       161

                  accuracy                           0.26      2737
                 macro avg       0.30      0.26      0.21      2737
              weighted avg       0.29      0.26      0.21      2737


Accuracy capturado en la ejecución 3: 25.61 [%]
F1-score capturado en la ejecución 3: 20.99 [%]

=== EJECUCIÓN 4 ===

--- TRAIN (ejecución 4) ---

--- TEST (ejecución 4) ---
2025-11-07 14:10:08.720260: 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 14:10:08.731609: 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 00:00:1762521008.744714 2922998 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762521008.748875 2922998 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762521008.759024 2922998 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521008.759040 2922998 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521008.759041 2922998 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521008.759042 2922998 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:10:08.762189: 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 00:00:1762521011.059222 2922998 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762521012.568596 2923133 service.cc:152] XLA service 0x720a8801e320 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762521012.568630 2923133 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:10:12.601188: 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 00:00:1762521012.747602 2923133 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762521014.170967 2923133 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47:38[0m 2s/step - accuracy: 0.0000e+00 - loss: 3.4276
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0513 - loss: 3.2904      
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0599 - loss: 3.2883
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0623 - loss: 3.2843
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0631 - loss: 3.2784
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0632 - loss: 3.2723
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0635 - loss: 3.2637
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0637 - loss: 3.2549
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0639 - loss: 3.2457
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0643 - loss: 3.2353
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0646 - loss: 3.2264
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0649 - loss: 3.2175
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0652 - loss: 3.2082
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0655 - loss: 3.1995
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0659 - loss: 3.1919
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0662 - loss: 3.1839
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0666 - loss: 3.1761
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0669 - loss: 3.1690
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0672 - loss: 3.1620
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0676 - loss: 3.1555
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0679 - loss: 3.1486
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0683 - loss: 3.1425
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0687 - loss: 3.1362
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0691 - loss: 3.1306
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0695 - loss: 3.1244
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0700 - loss: 3.1183
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0704 - loss: 3.1127
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0709 - loss: 3.1072
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0713 - loss: 3.1023
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0717 - loss: 3.0975
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0717 - loss: 3.0973 - val_accuracy: 0.1647 - val_loss: 2.6191
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3125 - loss: 2.3853
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1265 - loss: 2.7147  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1195 - loss: 2.7365
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1190 - loss: 2.7384
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1194 - loss: 2.7373
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1193 - loss: 2.7350
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1194 - loss: 2.7329
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1195 - loss: 2.7315
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1197 - loss: 2.7300
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1202 - loss: 2.7284
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1207 - loss: 2.7265
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1212 - loss: 2.7248
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1217 - loss: 2.7229
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1224 - loss: 2.7207
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1230 - loss: 2.7188
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1235 - loss: 2.7170
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1240 - loss: 2.7152
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1244 - loss: 2.7138
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1249 - loss: 2.7121
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1254 - loss: 2.7103
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1258 - loss: 2.7088
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1263 - loss: 2.7071
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1267 - loss: 2.7056
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1271 - loss: 2.7040
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1275 - loss: 2.7024
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1280 - loss: 2.7007
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1283 - loss: 2.6992
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1287 - loss: 2.6975
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1290 - loss: 2.6961
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1294 - loss: 2.6945
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1295 - loss: 2.6940 - val_accuracy: 0.1754 - val_loss: 2.4936
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.0000e+00 - loss: 2.7620
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1322 - loss: 2.5711      
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1441 - loss: 2.5663
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1462 - loss: 2.5660
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1483 - loss: 2.5625
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1497 - loss: 2.5581
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1507 - loss: 2.5535
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1516 - loss: 2.5504
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1526 - loss: 2.5473
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1535 - loss: 2.5450
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1544 - loss: 2.5425
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1552 - loss: 2.5404
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1560 - loss: 2.5384
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1566 - loss: 2.5366
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1570 - loss: 2.5354
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1575 - loss: 2.5342
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1579 - loss: 2.5330
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1584 - loss: 2.5318
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1588 - loss: 2.5306
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1592 - loss: 2.5296
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1596 - loss: 2.5285
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1600 - loss: 2.5274
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1604 - loss: 2.5264
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1608 - loss: 2.5255
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1612 - loss: 2.5244
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1615 - loss: 2.5234
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1619 - loss: 2.5224
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1622 - loss: 2.5215
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1625 - loss: 2.5205
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1627 - loss: 2.5196
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1630 - loss: 2.5189 - val_accuracy: 0.1954 - val_loss: 2.3956
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.7468
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1615 - loss: 2.4675  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1730 - loss: 2.4559
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1768 - loss: 2.4497
[1m 171/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1782 - loss: 2.4450
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1790 - loss: 2.4431
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1801 - loss: 2.4410
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1808 - loss: 2.4394
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1815 - loss: 2.4377
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1821 - loss: 2.4363
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1827 - loss: 2.4348
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1834 - loss: 2.4332
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1838 - loss: 2.4319
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1844 - loss: 2.4306
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1849 - loss: 2.4294
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1853 - loss: 2.4285
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1857 - loss: 2.4276
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1860 - loss: 2.4267
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1862 - loss: 2.4260
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1864 - loss: 2.4251
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1867 - loss: 2.4243
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1868 - loss: 2.4236
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1870 - loss: 2.4229
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1871 - loss: 2.4223
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1872 - loss: 2.4216
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1873 - loss: 2.4210
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1875 - loss: 2.4203
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1876 - loss: 2.4197
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1878 - loss: 2.4190
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1879 - loss: 2.4186 - val_accuracy: 0.2211 - val_loss: 2.3294
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.3253
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2549 - loss: 2.3304  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2254 - loss: 2.3569
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2142 - loss: 2.3692
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2102 - loss: 2.3728
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2081 - loss: 2.3742
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2060 - loss: 2.3742
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2047 - loss: 2.3731
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2039 - loss: 2.3722
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2031 - loss: 2.3715
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2024 - loss: 2.3710
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2019 - loss: 2.3700
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2016 - loss: 2.3689
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2014 - loss: 2.3678
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2013 - loss: 2.3669
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2013 - loss: 2.3660
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2012 - loss: 2.3654
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2011 - loss: 2.3647
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2010 - loss: 2.3640
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2009 - loss: 2.3635
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2008 - loss: 2.3631
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2006 - loss: 2.3627
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2005 - loss: 2.3623
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2003 - loss: 2.3620
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2002 - loss: 2.3616
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2001 - loss: 2.3611
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2001 - loss: 2.3607
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2001 - loss: 2.3603
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2001 - loss: 2.3598
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2001 - loss: 2.3593
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2001 - loss: 2.3589 - val_accuracy: 0.2259 - val_loss: 2.2766
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.2614
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2061 - loss: 2.3494  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2187 - loss: 2.3315
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2197 - loss: 2.3273
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2189 - loss: 2.3264
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2178 - loss: 2.3248
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2170 - loss: 2.3229
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2164 - loss: 2.3211
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2164 - loss: 2.3195
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2163 - loss: 2.3184
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2162 - loss: 2.3175
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2160 - loss: 2.3169
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2159 - loss: 2.3163
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2158 - loss: 2.3156
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2158 - loss: 2.3148
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2158 - loss: 2.3141
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2157 - loss: 2.3135
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2157 - loss: 2.3129
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2156 - loss: 2.3125
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2156 - loss: 2.3121
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2157 - loss: 2.3117
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2157 - loss: 2.3114
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2156 - loss: 2.3113
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2156 - loss: 2.3111
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2156 - loss: 2.3108
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2156 - loss: 2.3107
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2156 - loss: 2.3105
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2156 - loss: 2.3103
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2156 - loss: 2.3101
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2157 - loss: 2.3098
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2157 - loss: 2.3098 - val_accuracy: 0.2231 - val_loss: 2.2366
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.2748
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2036 - loss: 2.2953  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2081 - loss: 2.2965
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2090 - loss: 2.2917
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2104 - loss: 2.2862
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2118 - loss: 2.2818
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2119 - loss: 2.2809
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2121 - loss: 2.2805
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2125 - loss: 2.2795
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2129 - loss: 2.2784
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2134 - loss: 2.2775
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2138 - loss: 2.2768
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2142 - loss: 2.2760
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2145 - loss: 2.2754
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2148 - loss: 2.2750
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2151 - loss: 2.2746
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2154 - loss: 2.2742
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2157 - loss: 2.2739
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2159 - loss: 2.2735
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2162 - loss: 2.2732
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2164 - loss: 2.2729
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2166 - loss: 2.2725
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2169 - loss: 2.2719
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2171 - loss: 2.2713
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2174 - loss: 2.2708
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2176 - loss: 2.2703
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2178 - loss: 2.2698
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2180 - loss: 2.2694
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2182 - loss: 2.2689
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2184 - loss: 2.2686
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2184 - loss: 2.2685 - val_accuracy: 0.2257 - val_loss: 2.2043
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.1436
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2288 - loss: 2.2321  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2265 - loss: 2.2529
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2272 - loss: 2.2520
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2283 - loss: 2.2502
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2291 - loss: 2.2510
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2291 - loss: 2.2515
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2292 - loss: 2.2514
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2291 - loss: 2.2523
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2288 - loss: 2.2532
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2285 - loss: 2.2536
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2540
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2280 - loss: 2.2539
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2278 - loss: 2.2536
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2277 - loss: 2.2529
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2278 - loss: 2.2523
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2279 - loss: 2.2516
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2281 - loss: 2.2508
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2283 - loss: 2.2500
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2285 - loss: 2.2492
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2287 - loss: 2.2486
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2289 - loss: 2.2479
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2291 - loss: 2.2473
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2294 - loss: 2.2466
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2296 - loss: 2.2459
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2298 - loss: 2.2453
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2300 - loss: 2.2447
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2301 - loss: 2.2442
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2302 - loss: 2.2437
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2303 - loss: 2.2431
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2303 - loss: 2.2430 - val_accuracy: 0.2152 - val_loss: 2.2268
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.0887
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2586 - loss: 2.1946  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2452 - loss: 2.2018
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2400 - loss: 2.2085
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2383 - loss: 2.2108
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2381 - loss: 2.2092
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2375 - loss: 2.2090
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2367 - loss: 2.2101
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2359 - loss: 2.2114
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2352 - loss: 2.2127
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2348 - loss: 2.2133
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2344 - loss: 2.2138
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2339 - loss: 2.2145
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2334 - loss: 2.2153
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2330 - loss: 2.2158
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2328 - loss: 2.2159
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2326 - loss: 2.2160
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2325 - loss: 2.2160
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2324 - loss: 2.2158
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2323 - loss: 2.2157
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2323 - loss: 2.2153
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2324 - loss: 2.2149
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2324 - loss: 2.2144
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2324 - loss: 2.2140
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2324 - loss: 2.2134
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2325 - loss: 2.2129
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2325 - loss: 2.2124
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2325 - loss: 2.2121
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2325 - loss: 2.2117
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2324 - loss: 2.2113
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2324 - loss: 2.2112 - val_accuracy: 0.2459 - val_loss: 2.1572
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.2746
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2593 - loss: 2.1761  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2664 - loss: 2.1724
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2652 - loss: 2.1754
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2610 - loss: 2.1778
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2578 - loss: 2.1783
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2555 - loss: 2.1790
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2529 - loss: 2.1791
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2513 - loss: 2.1791
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2499 - loss: 2.1791
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2488 - loss: 2.1793
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2480 - loss: 2.1797
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2472 - loss: 2.1801
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2463 - loss: 2.1806
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2456 - loss: 2.1811
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2449 - loss: 2.1816
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2443 - loss: 2.1818
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2440 - loss: 2.1819
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2438 - loss: 2.1817
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2435 - loss: 2.1817
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2433 - loss: 2.1816
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2432 - loss: 2.1815
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2430 - loss: 2.1813
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2429 - loss: 2.1812
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2429 - loss: 2.1810
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2428 - loss: 2.1809
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2427 - loss: 2.1808
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2426 - loss: 2.1808
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2425 - loss: 2.1808
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2424 - loss: 2.1808
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2424 - loss: 2.1808 - val_accuracy: 0.2531 - val_loss: 2.1326
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 1.9917
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2720 - loss: 2.0310  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0773
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2525 - loss: 2.0979
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2517 - loss: 2.1068
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2512 - loss: 2.1124
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2507 - loss: 2.1168
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2505 - loss: 2.1203
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2503 - loss: 2.1226
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2503 - loss: 2.1243
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.1257
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.1267
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.1276
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2501 - loss: 2.1285
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2501 - loss: 2.1293
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.1301
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.1308
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2500 - loss: 2.1318
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2498 - loss: 2.1328
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2496 - loss: 2.1339
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2493 - loss: 2.1349
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2490 - loss: 2.1357
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2488 - loss: 2.1363
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2486 - loss: 2.1370
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2484 - loss: 2.1377
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2482 - loss: 2.1384
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2479 - loss: 2.1391
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2477 - loss: 2.1397
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2475 - loss: 2.1401
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2474 - loss: 2.1404 - val_accuracy: 0.2651 - val_loss: 2.1015
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.0000e+00 - loss: 2.3076
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2602 - loss: 2.1257      
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2560 - loss: 2.1375
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2509 - loss: 2.1388
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2476 - loss: 2.1399
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2456 - loss: 2.1412
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2449 - loss: 2.1418
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2446 - loss: 2.1425
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2447 - loss: 2.1428
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2448 - loss: 2.1429
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2448 - loss: 2.1425
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2449 - loss: 2.1419
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2450 - loss: 2.1412
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1405
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.1395
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2453 - loss: 2.1389
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.1382
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.1375
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1369
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2456 - loss: 2.1365
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2456 - loss: 2.1363
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1360
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1359
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1358
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1357
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1356
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1355
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1354
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1353
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1351
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2458 - loss: 2.1350 - val_accuracy: 0.2612 - val_loss: 2.0820
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.5174
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2513 - loss: 2.1734  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2483 - loss: 2.1583
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2467 - loss: 2.1522
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1492
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1465
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2463 - loss: 2.1437
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2473 - loss: 2.1412
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2479 - loss: 2.1392
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2484 - loss: 2.1378
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2488 - loss: 2.1367
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2490 - loss: 2.1356
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2494 - loss: 2.1345
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2498 - loss: 2.1335
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.1325
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2505 - loss: 2.1317
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2509 - loss: 2.1308
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2512 - loss: 2.1298
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2515 - loss: 2.1290
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2518 - loss: 2.1281
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2520 - loss: 2.1273
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2522 - loss: 2.1265
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2525 - loss: 2.1258
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2527 - loss: 2.1251
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.1246
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2530 - loss: 2.1241
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2531 - loss: 2.1237
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2533 - loss: 2.1234
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2534 - loss: 2.1230
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2535 - loss: 2.1227
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2536 - loss: 2.1225 - val_accuracy: 0.2488 - val_loss: 2.0760
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.4019
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2371 - loss: 2.1756  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2499 - loss: 2.1588
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2545 - loss: 2.1468
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2565 - loss: 2.1365
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2572 - loss: 2.1296
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2571 - loss: 2.1259
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2566 - loss: 2.1228
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2562 - loss: 2.1214
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2560 - loss: 2.1196
[1m 386/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2560 - loss: 2.1175
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.1161
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.1150
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.1143
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2562 - loss: 2.1137
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.1131
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.1126
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.1122
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2564 - loss: 2.1117
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2564 - loss: 2.1113
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.1108
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2566 - loss: 2.1103
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.1099
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.1094
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.1090
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.1087
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.1084
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.1081
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.1078
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2570 - loss: 2.1075
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2571 - loss: 2.1071 - val_accuracy: 0.2703 - val_loss: 2.0512
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.0625 - loss: 2.3173
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2195 - loss: 2.1679  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2387 - loss: 2.1372
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2478 - loss: 2.1171
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2514 - loss: 2.1075
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2523 - loss: 2.1034
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2536 - loss: 2.0993
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2546 - loss: 2.0968
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2554 - loss: 2.0952
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2557 - loss: 2.0949
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0946
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0940
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2566 - loss: 2.0932
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2570 - loss: 2.0924
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0918
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.0908
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2582 - loss: 2.0899
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2584 - loss: 2.0894
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2586 - loss: 2.0888
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2587 - loss: 2.0883
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2589 - loss: 2.0877
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2590 - loss: 2.0873
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2591 - loss: 2.0868
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2594 - loss: 2.0863
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2596 - loss: 2.0858
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2597 - loss: 2.0854
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0850
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2601 - loss: 2.0846
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0843
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0840
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2603 - loss: 2.0839 - val_accuracy: 0.2622 - val_loss: 2.0331
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.1754
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0422  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0564
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0645
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0682
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0698
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0711
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0726
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0737
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0747
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0760
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2648 - loss: 2.0772
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2643 - loss: 2.0784
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0791
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0798
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2634 - loss: 2.0805
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2632 - loss: 2.0810
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2632 - loss: 2.0812
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2632 - loss: 2.0811
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2632 - loss: 2.0808
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0805
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0802
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0797
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2634 - loss: 2.0793
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2634 - loss: 2.0788
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2635 - loss: 2.0783
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0778
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2638 - loss: 2.0773
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0769
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2640 - loss: 2.0765
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2641 - loss: 2.0764 - val_accuracy: 0.2590 - val_loss: 2.0261
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.7702
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2942 - loss: 2.0182  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2821 - loss: 2.0328
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2778 - loss: 2.0394
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2765 - loss: 2.0431
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2757 - loss: 2.0470
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2753 - loss: 2.0493
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0508
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0516
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0518
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2728 - loss: 2.0515
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2725 - loss: 2.0512
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0510
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2720 - loss: 2.0508
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0509
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0509
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0510
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0512
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0512
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0511
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0511
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0511
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0510
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0510
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0510
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0511
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0512
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0512
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0512
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0513
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2715 - loss: 2.0513 - val_accuracy: 0.2644 - val_loss: 2.0307
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 1.8549
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2494 - loss: 2.0469  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2505 - loss: 2.0506
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2523 - loss: 2.0553
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2538 - loss: 2.0572
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2553 - loss: 2.0551
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0532
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0520
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2589 - loss: 2.0512
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2596 - loss: 2.0503
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0496
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0488
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2615 - loss: 2.0478
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2620 - loss: 2.0472
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2623 - loss: 2.0469
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2627 - loss: 2.0467
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0465
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0463
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2641 - loss: 2.0460
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0457
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0453
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0449
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0445
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0442
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0438
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0434
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0431
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0428
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0425
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0422
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2673 - loss: 2.0420 - val_accuracy: 0.2770 - val_loss: 2.0093
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.8257
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2375 - loss: 2.1005  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2384 - loss: 2.0869
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2431 - loss: 2.0820
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2471 - loss: 2.0801
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2508 - loss: 2.0769
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2538 - loss: 2.0733
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0694
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2580 - loss: 2.0660
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2592 - loss: 2.0635
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2598 - loss: 2.0614
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0596
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0578
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2619 - loss: 2.0560
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2625 - loss: 2.0544
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0531
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0519
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2641 - loss: 2.0510
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2646 - loss: 2.0501
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0492
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2654 - loss: 2.0484
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0476
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0469
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0461
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0455
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2673 - loss: 2.0448
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0442
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0436
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0432
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2684 - loss: 2.0428 - val_accuracy: 0.2529 - val_loss: 2.0187
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.2991
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0583  
[1m  71/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2613 - loss: 2.0587
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2624 - loss: 2.0545
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0489
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2646 - loss: 2.0468
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0459
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0451
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0437
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2646 - loss: 2.0422
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0408
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0394
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0386
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0375
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0367
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0356
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0344
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0333
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0322
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2691 - loss: 2.0312
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2695 - loss: 2.0304
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0296
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0289
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0283
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2706 - loss: 2.0278
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0273
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0268
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0264
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0260
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2714 - loss: 2.0256
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2715 - loss: 2.0254 - val_accuracy: 0.2705 - val_loss: 2.0185
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3750 - loss: 2.5292
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2979 - loss: 1.9781  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2862 - loss: 1.9823
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2833 - loss: 1.9838
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2813 - loss: 1.9857
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2801 - loss: 1.9892
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9925
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2784 - loss: 1.9941
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2778 - loss: 1.9956
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2774 - loss: 1.9966
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2770 - loss: 1.9975
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2768 - loss: 1.9987
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2766 - loss: 2.0001
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2765 - loss: 2.0015
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2764 - loss: 2.0029
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2763 - loss: 2.0043
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2762 - loss: 2.0054
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2762 - loss: 2.0063
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2762 - loss: 2.0069
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0076
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0081
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0086
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0090
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0094
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2760 - loss: 2.0098
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2760 - loss: 2.0101
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 2.0105
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 2.0108
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 2.0110
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2758 - loss: 2.0112
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2758 - loss: 2.0112 - val_accuracy: 0.2583 - val_loss: 2.0063
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5000 - loss: 1.7772
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3143 - loss: 1.9778  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2989 - loss: 1.9810
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2968 - loss: 1.9812
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2960 - loss: 1.9822
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2944 - loss: 1.9839
[1m 226/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2928 - loss: 1.9854
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2916 - loss: 1.9869
[1m 306/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2904 - loss: 1.9890
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2895 - loss: 1.9903
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2888 - loss: 1.9914
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2882 - loss: 1.9919
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2877 - loss: 1.9923
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2873 - loss: 1.9926
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2869 - loss: 1.9928
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2867 - loss: 1.9929
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2864 - loss: 1.9931
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2862 - loss: 1.9931
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2861 - loss: 1.9932
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2859 - loss: 1.9932
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2857 - loss: 1.9934
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2855 - loss: 1.9936
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2852 - loss: 1.9938
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2850 - loss: 1.9941
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2847 - loss: 1.9945
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2845 - loss: 1.9948
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2843 - loss: 1.9951
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2841 - loss: 1.9954
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2840 - loss: 1.9957
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2838 - loss: 1.9959
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2836 - loss: 1.9962
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2836 - loss: 1.9962 - val_accuracy: 0.2673 - val_loss: 1.9954
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 2.1718
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3011 - loss: 2.0447  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2880 - loss: 2.0347
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2829 - loss: 2.0257
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2796 - loss: 2.0221
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2775 - loss: 2.0215
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2769 - loss: 2.0200
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2766 - loss: 2.0180
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2766 - loss: 2.0167
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2766 - loss: 2.0160
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2765 - loss: 2.0155
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2763 - loss: 2.0153
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2762 - loss: 2.0153
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0149
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0144
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2763 - loss: 2.0140
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2765 - loss: 2.0135
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2766 - loss: 2.0131
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2768 - loss: 2.0126
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2770 - loss: 2.0119
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2772 - loss: 2.0112
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2774 - loss: 2.0105
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 2.0099
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2777 - loss: 2.0094
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2778 - loss: 2.0088
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2780 - loss: 2.0083
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2781 - loss: 2.0079
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2783 - loss: 2.0074
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2784 - loss: 2.0070
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2785 - loss: 2.0067 - val_accuracy: 0.2668 - val_loss: 1.9928
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.6086
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3120 - loss: 1.9516  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3045 - loss: 1.9556
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3010 - loss: 1.9567
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3000 - loss: 1.9574
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3000 - loss: 1.9587
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2997 - loss: 1.9599
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2987 - loss: 1.9613
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2977 - loss: 1.9620
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2968 - loss: 1.9626
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2962 - loss: 1.9628
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2958 - loss: 1.9627
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2954 - loss: 1.9629
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2951 - loss: 1.9630
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2947 - loss: 1.9632
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2943 - loss: 1.9634
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2939 - loss: 1.9636
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2936 - loss: 1.9638
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2933 - loss: 1.9640
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2930 - loss: 1.9641
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2928 - loss: 1.9645
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2925 - loss: 1.9649
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2922 - loss: 1.9653
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2919 - loss: 1.9658
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2916 - loss: 1.9662
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2914 - loss: 1.9667
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2912 - loss: 1.9672
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2910 - loss: 1.9676
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2908 - loss: 1.9680
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2907 - loss: 1.9685
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2906 - loss: 1.9687 - val_accuracy: 0.2753 - val_loss: 1.9637
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.2216
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3063 - loss: 1.9476  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2931 - loss: 1.9706
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2888 - loss: 1.9756
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2861 - loss: 1.9826
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2847 - loss: 1.9883
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2843 - loss: 1.9915
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2838 - loss: 1.9943
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2836 - loss: 1.9956
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2832 - loss: 1.9972
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2825 - loss: 1.9987
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2820 - loss: 2.0001
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2817 - loss: 2.0007
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2816 - loss: 2.0009
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2814 - loss: 2.0010
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 2.0009
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 2.0007
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 2.0005
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 2.0003
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 2.0001
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2809 - loss: 1.9997
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 1.9993
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 1.9986
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 1.9981
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 1.9975
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 1.9970
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 1.9965
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 1.9960
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 1.9955
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9950
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2812 - loss: 1.9946 - val_accuracy: 0.2709 - val_loss: 1.9658

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 636ms/step
[1m63/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 815us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:00[0m 824ms/step
[1m 67/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 761us/step  
[1m139/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 733us/step
[1m210/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 723us/step
[1m275/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 736us/step
[1m339/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 746us/step
[1m412/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 736us/step
[1m486/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 728us/step
[1m557/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 726us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m71/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 723us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[1m 66/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 774us/step
[1m136/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 746us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 29.1 [%]
Global F1 score (validation) = 26.44 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.1725874  0.12786523 0.194632   ... 0.00508901 0.1404592  0.01716685]
 [0.14846317 0.15935723 0.22264126 ... 0.00309968 0.14156815 0.01490723]
 [0.10330679 0.13283855 0.12300053 ... 0.00694918 0.09595152 0.00807505]
 ...
 [0.15767665 0.15181062 0.25142908 ... 0.00175919 0.1524347  0.01328704]
 [0.17217515 0.15110561 0.21439883 ... 0.00237249 0.15586352 0.03088829]
 [0.06446707 0.10061654 0.08393528 ... 0.00930675 0.06493858 0.00829197]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 31.79 [%]
Global accuracy score (test) = 26.6 [%]
Global F1 score (train) = 29.32 [%]
Global F1 score (test) = 23.63 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.18      0.04      0.07       184
 CAMINAR CON MÓVIL O LIBRO       0.00      0.00      0.00       184
       CAMINAR USUAL SPEED       0.17      0.66      0.28       184
            CAMINAR ZIGZAG       0.14      0.06      0.08       184
          DE PIE BARRIENDO       0.22      0.47      0.30       184
   DE PIE DOBLANDO TOALLAS       0.24      0.14      0.18       184
    DE PIE MOVIENDO LIBROS       0.21      0.18      0.19       184
          DE PIE USANDO PC       0.27      0.72      0.39       184
        FASE REPOSO CON K5       0.68      0.62      0.65       184
INCREMENTAL CICLOERGOMETRO       0.33      0.19      0.24       184
           SENTADO LEYENDO       0.20      0.12      0.15       184
         SENTADO USANDO PC       0.11      0.04      0.06       184
      SENTADO VIENDO LA TV       0.40      0.36      0.38       184
   SUBIR Y BAJAR ESCALERAS       0.14      0.02      0.03       184
                    TROTAR       1.00      0.37      0.54       161

                  accuracy                           0.27      2737
                 macro avg       0.29      0.27      0.24      2737
              weighted avg       0.28      0.27      0.23      2737


Accuracy capturado en la ejecución 4: 26.6 [%]
F1-score capturado en la ejecución 4: 23.63 [%]

=== EJECUCIÓN 5 ===

--- TRAIN (ejecución 5) ---

--- TEST (ejecución 5) ---
2025-11-07 14:11:16.463708: 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 14:11:16.475352: 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 00:00:1762521076.489008 2926754 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762521076.493226 2926754 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762521076.503451 2926754 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521076.503471 2926754 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521076.503472 2926754 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521076.503473 2926754 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:11:16.506676: 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 00:00:1762521078.779106 2926754 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762521080.269517 2926861 service.cc:152] XLA service 0x753e8400c0d0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762521080.269545 2926861 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:11:20.305384: 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 00:00:1762521080.457695 2926861 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762521081.895743 2926861 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m48:14[0m 2s/step - accuracy: 0.0000e+00 - loss: 3.6253
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0432 - loss: 3.4685      
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0566 - loss: 3.4395
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0603 - loss: 3.4220
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0616 - loss: 3.4102
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0624 - loss: 3.3999
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0635 - loss: 3.3877
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0649 - loss: 3.3733
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0662 - loss: 3.3596
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0672 - loss: 3.3473
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0680 - loss: 3.3371
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0688 - loss: 3.3267
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0696 - loss: 3.3163
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0703 - loss: 3.3064
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0710 - loss: 3.2964
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0717 - loss: 3.2863
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0724 - loss: 3.2764
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0732 - loss: 3.2671
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0739 - loss: 3.2587
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0746 - loss: 3.2502
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0752 - loss: 3.2426
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0758 - loss: 3.2350
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0763 - loss: 3.2280
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0768 - loss: 3.2210
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0772 - loss: 3.2146
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0777 - loss: 3.2077
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0782 - loss: 3.2013
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0787 - loss: 3.1947
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0790 - loss: 3.1895
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0793 - loss: 3.1861
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0793 - loss: 3.1859 - val_accuracy: 0.1404 - val_loss: 2.6322
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.8190
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0728 - loss: 2.8458  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0825 - loss: 2.8333
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0894 - loss: 2.8180
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0940 - loss: 2.8082
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0970 - loss: 2.8017
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0987 - loss: 2.7973
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0999 - loss: 2.7948
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1011 - loss: 2.7918
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1020 - loss: 2.7888
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1028 - loss: 2.7857
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1039 - loss: 2.7827
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1049 - loss: 2.7798
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1061 - loss: 2.7766
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1072 - loss: 2.7734
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1083 - loss: 2.7703
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1091 - loss: 2.7674
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1099 - loss: 2.7649
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1105 - loss: 2.7624
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1112 - loss: 2.7600
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1118 - loss: 2.7576
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1124 - loss: 2.7553
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1129 - loss: 2.7530
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1134 - loss: 2.7508
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1139 - loss: 2.7488
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1143 - loss: 2.7467
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1148 - loss: 2.7447
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1152 - loss: 2.7427
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1157 - loss: 2.7406
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1161 - loss: 2.7388 - val_accuracy: 0.1591 - val_loss: 2.4960
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.7466
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1639 - loss: 2.5606  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1603 - loss: 2.5584
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1574 - loss: 2.5594
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1566 - loss: 2.5620
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1560 - loss: 2.5646
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1560 - loss: 2.5655
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1558 - loss: 2.5661
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1552 - loss: 2.5666
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1546 - loss: 2.5672
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1541 - loss: 2.5672
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1537 - loss: 2.5671
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1532 - loss: 2.5672
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1529 - loss: 2.5673
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1526 - loss: 2.5673
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1524 - loss: 2.5670
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1523 - loss: 2.5666
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1521 - loss: 2.5661
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1520 - loss: 2.5654
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1519 - loss: 2.5646
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1520 - loss: 2.5638
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1520 - loss: 2.5630
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1520 - loss: 2.5623
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1521 - loss: 2.5613
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1522 - loss: 2.5603
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1523 - loss: 2.5594
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1524 - loss: 2.5584
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1525 - loss: 2.5574
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1526 - loss: 2.5564
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1527 - loss: 2.5554
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1528 - loss: 2.5550 - val_accuracy: 0.1824 - val_loss: 2.4003
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.4345
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1598 - loss: 2.4660  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1661 - loss: 2.4708
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1679 - loss: 2.4715
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1692 - loss: 2.4692
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1700 - loss: 2.4668
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1707 - loss: 2.4646
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1715 - loss: 2.4627
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1723 - loss: 2.4613
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1731 - loss: 2.4599
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1736 - loss: 2.4589
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1740 - loss: 2.4576
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1742 - loss: 2.4565
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1746 - loss: 2.4549
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1749 - loss: 2.4536
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1752 - loss: 2.4524
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1754 - loss: 2.4512
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1756 - loss: 2.4501
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1757 - loss: 2.4490
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1759 - loss: 2.4478
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1761 - loss: 2.4466
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1763 - loss: 2.4455
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1764 - loss: 2.4446
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1766 - loss: 2.4438
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1767 - loss: 2.4429
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1768 - loss: 2.4419
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1769 - loss: 2.4411
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1771 - loss: 2.4401
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1772 - loss: 2.4393
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1774 - loss: 2.4384
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1775 - loss: 2.4380 - val_accuracy: 0.2168 - val_loss: 2.3084
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.2786
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2050 - loss: 2.3295  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1962 - loss: 2.3411
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1924 - loss: 2.3505
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1920 - loss: 2.3540
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1924 - loss: 2.3554
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1930 - loss: 2.3560
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1935 - loss: 2.3565
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1943 - loss: 2.3561
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1952 - loss: 2.3551
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1959 - loss: 2.3542
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1965 - loss: 2.3535
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1968 - loss: 2.3529
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1970 - loss: 2.3527
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1971 - loss: 2.3524
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1972 - loss: 2.3521
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1973 - loss: 2.3516
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1974 - loss: 2.3513
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1976 - loss: 2.3509
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1977 - loss: 2.3506
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1978 - loss: 2.3504
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1979 - loss: 2.3501
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1980 - loss: 2.3498
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1981 - loss: 2.3494
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1982 - loss: 2.3489
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1984 - loss: 2.3485
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1985 - loss: 2.3480
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1987 - loss: 2.3476
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1988 - loss: 2.3471
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1990 - loss: 2.3467
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1990 - loss: 2.3465 - val_accuracy: 0.2320 - val_loss: 2.2456
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.1847
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2067 - loss: 2.2763  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2089 - loss: 2.2918
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2121 - loss: 2.2959
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2161 - loss: 2.2968
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2177 - loss: 2.2983
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2185 - loss: 2.3000
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2185 - loss: 2.3008
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2183 - loss: 2.3018
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2182 - loss: 2.3025
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2181 - loss: 2.3030
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2181 - loss: 2.3030
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2181 - loss: 2.3028
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2181 - loss: 2.3025
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2181 - loss: 2.3020
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2181 - loss: 2.3015
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2181 - loss: 2.3010
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2180 - loss: 2.3007
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2179 - loss: 2.3005
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2178 - loss: 2.3003
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2177 - loss: 2.3000
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2177 - loss: 2.2997
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2176 - loss: 2.2995
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2176 - loss: 2.2992
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2176 - loss: 2.2989
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2175 - loss: 2.2986
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2174 - loss: 2.2982
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2174 - loss: 2.2979
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2173 - loss: 2.2976
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2172 - loss: 2.2974 - val_accuracy: 0.2418 - val_loss: 2.1942
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.0538
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2049 - loss: 2.2347  
[1m  87/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2075 - loss: 2.2575
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2071 - loss: 2.2647
[1m 169/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2075 - loss: 2.2653
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2081 - loss: 2.2650
[1m 251/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2086 - loss: 2.2656
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2089 - loss: 2.2656
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2091 - loss: 2.2657
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2095 - loss: 2.2650
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2099 - loss: 2.2641
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2103 - loss: 2.2631
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2108 - loss: 2.2623
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2113 - loss: 2.2615
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2117 - loss: 2.2609
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2122 - loss: 2.2603
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2125 - loss: 2.2597
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2130 - loss: 2.2591
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2134 - loss: 2.2584
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2137 - loss: 2.2578
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2140 - loss: 2.2573
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2142 - loss: 2.2567
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2145 - loss: 2.2561
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2148 - loss: 2.2554
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2150 - loss: 2.2549
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2153 - loss: 2.2543
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2155 - loss: 2.2537
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2157 - loss: 2.2532
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2159 - loss: 2.2527
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2160 - loss: 2.2523 - val_accuracy: 0.2481 - val_loss: 2.1627
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.1918
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1813 - loss: 2.1949  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1906 - loss: 2.2081
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1963 - loss: 2.2161
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2002 - loss: 2.2186
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2032 - loss: 2.2191
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2054 - loss: 2.2193
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2077 - loss: 2.2179
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2095 - loss: 2.2172
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2108 - loss: 2.2166
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2119 - loss: 2.2163
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2129 - loss: 2.2158
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2139 - loss: 2.2151
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2147 - loss: 2.2147
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2155 - loss: 2.2142
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2161 - loss: 2.2138
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2167 - loss: 2.2136
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2172 - loss: 2.2137
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2175 - loss: 2.2139
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2179 - loss: 2.2142
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2183 - loss: 2.2144
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2187 - loss: 2.2145
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2191 - loss: 2.2145
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2194 - loss: 2.2144
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2197 - loss: 2.2143
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2200 - loss: 2.2142
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2203 - loss: 2.2142
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2205 - loss: 2.2141
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2208 - loss: 2.2140
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2211 - loss: 2.2138
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2211 - loss: 2.2138 - val_accuracy: 0.2453 - val_loss: 2.1238
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.0625 - loss: 2.0996
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2264 - loss: 2.1067  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2283 - loss: 2.1369
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2298 - loss: 2.1546
[1m 168/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2302 - loss: 2.1638
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2308 - loss: 2.1670
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2307 - loss: 2.1712
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2303 - loss: 2.1735
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2300 - loss: 2.1756
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2298 - loss: 2.1770
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2296 - loss: 2.1784
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2296 - loss: 2.1792
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2298 - loss: 2.1797
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2301 - loss: 2.1798
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2306 - loss: 2.1799
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2309 - loss: 2.1801
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2311 - loss: 2.1802
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2315 - loss: 2.1801
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2318 - loss: 2.1798
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2320 - loss: 2.1796
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2322 - loss: 2.1794
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2323 - loss: 2.1793
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2325 - loss: 2.1791
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2327 - loss: 2.1789
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2328 - loss: 2.1788
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2329 - loss: 2.1786
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2329 - loss: 2.1785
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2330 - loss: 2.1784
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2331 - loss: 2.1782
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2331 - loss: 2.1782 - val_accuracy: 0.2442 - val_loss: 2.1106
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 1.9866
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2609 - loss: 2.1490  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2497 - loss: 2.1662
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2443 - loss: 2.1669
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2415 - loss: 2.1685
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2405 - loss: 2.1671
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2405 - loss: 2.1650
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2402 - loss: 2.1636
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2395 - loss: 2.1629
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2390 - loss: 2.1624
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2384 - loss: 2.1621
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2378 - loss: 2.1620
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2372 - loss: 2.1620
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2367 - loss: 2.1619
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2363 - loss: 2.1619
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2359 - loss: 2.1618
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2356 - loss: 2.1616
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2353 - loss: 2.1616
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2351 - loss: 2.1615
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2350 - loss: 2.1614
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2349 - loss: 2.1611
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2349 - loss: 2.1608
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2349 - loss: 2.1605
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2349 - loss: 2.1603
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2350 - loss: 2.1600
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2351 - loss: 2.1597
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2351 - loss: 2.1595
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2351 - loss: 2.1593
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2352 - loss: 2.1592
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2352 - loss: 2.1591
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2352 - loss: 2.1591 - val_accuracy: 0.2646 - val_loss: 2.0849
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.2025
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2217 - loss: 2.2418  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2338 - loss: 2.2017
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2378 - loss: 2.1814
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2390 - loss: 2.1678
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2404 - loss: 2.1609
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2410 - loss: 2.1571
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2413 - loss: 2.1549
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2414 - loss: 2.1530
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2415 - loss: 2.1513
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2415 - loss: 2.1498
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2416 - loss: 2.1480
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2417 - loss: 2.1470
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2418 - loss: 2.1461
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1452
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1443
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2420 - loss: 2.1436
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1432
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1426
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1420
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1414
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1409
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2418 - loss: 2.1405
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2418 - loss: 2.1401
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2418 - loss: 2.1398
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2418 - loss: 2.1394
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2418 - loss: 2.1390
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1386
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1383
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2419 - loss: 2.1381 - val_accuracy: 0.2710 - val_loss: 2.0474
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.8876
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2128 - loss: 2.1397  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2229 - loss: 2.1530
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2298 - loss: 2.1459
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2348 - loss: 2.1401
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2380 - loss: 2.1356
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2396 - loss: 2.1324
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2408 - loss: 2.1300
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1282
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2424 - loss: 2.1271
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2429 - loss: 2.1259
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2433 - loss: 2.1252
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2437 - loss: 2.1250
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2438 - loss: 2.1248
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2440 - loss: 2.1244
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2441 - loss: 2.1240
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2443 - loss: 2.1235
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2445 - loss: 2.1230
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2447 - loss: 2.1226
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2449 - loss: 2.1222
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1220
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1218
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2453 - loss: 2.1216
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.1215
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1214
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1212
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1210
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1208
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2456 - loss: 2.1207
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2456 - loss: 2.1205 - val_accuracy: 0.2673 - val_loss: 2.0350
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.1574
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2778 - loss: 2.0342  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2719 - loss: 2.0443
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0551
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2620 - loss: 2.0634
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0694
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2598 - loss: 2.0731
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2598 - loss: 2.0755
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0779
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2597 - loss: 2.0803
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2593 - loss: 2.0826
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2589 - loss: 2.0846
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2584 - loss: 2.0862
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0875
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.0886
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2575 - loss: 2.0893
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0900
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2570 - loss: 2.0905
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.0910
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0914
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2566 - loss: 2.0918
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.0921
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2564 - loss: 2.0923
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2564 - loss: 2.0925
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0927
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2562 - loss: 2.0929
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0931
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0932
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0933
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2561 - loss: 2.0934 - val_accuracy: 0.2544 - val_loss: 2.0439
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.2525
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2504 - loss: 2.0817  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2517 - loss: 2.0882
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2531 - loss: 2.0895
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2539 - loss: 2.0859
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2552 - loss: 2.0829
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2559 - loss: 2.0823
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0830
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0845
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.0855
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.0856
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0854
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0849
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0847
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0844
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0843
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.0844
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.0845
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2558 - loss: 2.0846
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2556 - loss: 2.0848
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2556 - loss: 2.0850
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2555 - loss: 2.0852
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2554 - loss: 2.0854
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2553 - loss: 2.0856
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2553 - loss: 2.0858
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2552 - loss: 2.0861
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2552 - loss: 2.0863
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2551 - loss: 2.0864
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2551 - loss: 2.0865
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2552 - loss: 2.0865 - val_accuracy: 0.2548 - val_loss: 2.0240
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 28ms/step - accuracy: 0.1875 - loss: 2.0752
[1m  44/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2706 - loss: 2.0270  
[1m  86/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2763 - loss: 2.0276
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2738 - loss: 2.0377
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0450
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0476
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0495
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2692 - loss: 2.0515
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2688 - loss: 2.0533
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2685 - loss: 2.0546
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2683 - loss: 2.0556
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0568
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2673 - loss: 2.0582
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0593
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0601
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0610
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0619
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0626
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0632
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0637
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0640
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0642
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0643
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0643
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0643
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0642
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0641
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0641
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0641
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2649 - loss: 2.0641 - val_accuracy: 0.2579 - val_loss: 2.0140
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.6759
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2581 - loss: 1.9836  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2607 - loss: 2.0051
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2606 - loss: 2.0199
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0266
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2605 - loss: 2.0306
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2606 - loss: 2.0347
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0379
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2600 - loss: 2.0404
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2594 - loss: 2.0424
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2588 - loss: 2.0448
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2584 - loss: 2.0466
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2583 - loss: 2.0478
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0487
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2580 - loss: 2.0496
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.0504
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2576 - loss: 2.0511
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2574 - loss: 2.0518
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0525
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.0530
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0534
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2566 - loss: 2.0539
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2566 - loss: 2.0541
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.0543
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.0543
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.0544
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2564 - loss: 2.0545
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2564 - loss: 2.0545
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0546
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2563 - loss: 2.0546 - val_accuracy: 0.2570 - val_loss: 2.0070
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.3417
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2574 - loss: 2.0313  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2619 - loss: 2.0235
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0200
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0199
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0210
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0211
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0213
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2641 - loss: 2.0226
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0235
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2635 - loss: 2.0241
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0245
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2638 - loss: 2.0251
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0257
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0262
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0266
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2647 - loss: 2.0268
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0271
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0274
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0278
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0282
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2654 - loss: 2.0285
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0288
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0289
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0290
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0291
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0293
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0296
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0299
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0301
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2658 - loss: 2.0301 - val_accuracy: 0.2516 - val_loss: 2.0098
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.1336
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2431 - loss: 2.0724  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2445 - loss: 2.0567
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2473 - loss: 2.0502
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2507 - loss: 2.0444
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2524 - loss: 2.0427
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2539 - loss: 2.0406
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2550 - loss: 2.0388
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2556 - loss: 2.0380
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2559 - loss: 2.0374
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0368
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.0362
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.0355
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0348
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.0343
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0339
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2584 - loss: 2.0334
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2587 - loss: 2.0330
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2590 - loss: 2.0327
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2593 - loss: 2.0324
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2595 - loss: 2.0323
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2598 - loss: 2.0324
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0324
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2600 - loss: 2.0324
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2600 - loss: 2.0325
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2601 - loss: 2.0327
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2601 - loss: 2.0328
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2601 - loss: 2.0329
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2601 - loss: 2.0331
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2601 - loss: 2.0332
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2601 - loss: 2.0332 - val_accuracy: 0.2640 - val_loss: 1.9707
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.8380
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3162 - loss: 1.9053  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2987 - loss: 1.9608
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2892 - loss: 1.9882
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2845 - loss: 1.9997
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2817 - loss: 2.0062
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2807 - loss: 2.0094
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2804 - loss: 2.0107
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2801 - loss: 2.0112
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 2.0110
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 2.0106
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2798 - loss: 2.0102
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 2.0104
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2794 - loss: 2.0106
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2792 - loss: 2.0110
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 2.0114
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2786 - loss: 2.0119
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2782 - loss: 2.0124
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2779 - loss: 2.0128
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 2.0132
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2773 - loss: 2.0135
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2770 - loss: 2.0138
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2767 - loss: 2.0141
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2765 - loss: 2.0143
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2763 - loss: 2.0145
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2760 - loss: 2.0149
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 2.0152
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2757 - loss: 2.0154
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2755 - loss: 2.0157
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2754 - loss: 2.0160
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2753 - loss: 2.0161 - val_accuracy: 0.2453 - val_loss: 1.9982
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.6375
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2339 - loss: 2.0695  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2470 - loss: 2.0384
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2534 - loss: 2.0323
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0287
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2589 - loss: 2.0237
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2615 - loss: 2.0198
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2628 - loss: 2.0186
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0178
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0165
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0154
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0145
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0139
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0137
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0135
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0132
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0128
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0125
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0122
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0119
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0116
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0114
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0112
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0110
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0108
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0107
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0107
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2673 - loss: 2.0108
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2673 - loss: 2.0109
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2674 - loss: 2.0110 - val_accuracy: 0.2603 - val_loss: 1.9801
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 1.8705
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2791 - loss: 1.9765  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0078
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2643 - loss: 2.0127
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0171
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0187
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0181
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0177
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0169
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0167
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0166
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0164
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0161
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0156
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2654 - loss: 2.0150
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0144
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0136
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0130
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0122
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0116
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0112
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0107
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0104
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2680 - loss: 2.0101
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0097
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2683 - loss: 2.0094
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2685 - loss: 2.0091
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0088
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0084
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2687 - loss: 2.0082 - val_accuracy: 0.2548 - val_loss: 1.9805
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.9929
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3035 - loss: 1.9651  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2925 - loss: 1.9758
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2848 - loss: 1.9866
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2807 - loss: 1.9924
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2797 - loss: 1.9947
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2801 - loss: 1.9963
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2807 - loss: 1.9968
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2805 - loss: 1.9975
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2804 - loss: 1.9974
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2803 - loss: 1.9973
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2802 - loss: 1.9970
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 1.9967
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2800 - loss: 1.9963
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2800 - loss: 1.9960
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 1.9955
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2797 - loss: 1.9952
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9950
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2794 - loss: 1.9951
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2793 - loss: 1.9950
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2792 - loss: 1.9950
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2792 - loss: 1.9950
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2791 - loss: 1.9950
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2790 - loss: 1.9950
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9951
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9951
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9951
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9951
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9951
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9952
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2789 - loss: 1.9952 - val_accuracy: 0.2666 - val_loss: 1.9720
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.2500 - loss: 2.0544
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3001 - loss: 1.9695  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2924 - loss: 1.9714
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2922 - loss: 1.9729
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2913 - loss: 1.9739
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2900 - loss: 1.9761
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2889 - loss: 1.9788
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2884 - loss: 1.9805
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2878 - loss: 1.9831
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2872 - loss: 1.9848
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2869 - loss: 1.9857
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2867 - loss: 1.9857
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2864 - loss: 1.9856
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2860 - loss: 1.9859
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2855 - loss: 1.9863
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2851 - loss: 1.9865
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2848 - loss: 1.9865
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2845 - loss: 1.9865
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2842 - loss: 1.9864
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2841 - loss: 1.9862
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2839 - loss: 1.9860
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2837 - loss: 1.9859
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2836 - loss: 1.9858
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2834 - loss: 1.9857
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2832 - loss: 1.9857
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2831 - loss: 1.9858
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2829 - loss: 1.9859
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2827 - loss: 1.9860
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2826 - loss: 1.9860
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2825 - loss: 1.9860 - val_accuracy: 0.2670 - val_loss: 1.9635
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.5000 - loss: 1.6507
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2976 - loss: 1.9062  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2826 - loss: 1.9364
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2782 - loss: 1.9480
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2767 - loss: 1.9541
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2753 - loss: 1.9589
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2751 - loss: 1.9620
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2745 - loss: 1.9658
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2743 - loss: 1.9693
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2744 - loss: 1.9718
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2743 - loss: 1.9734
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 1.9749
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2739 - loss: 1.9763
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 1.9776
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 1.9784
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 1.9793
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 1.9801
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 1.9807
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 1.9811
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 1.9816
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 1.9818
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 1.9821
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 1.9824
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 1.9826
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 1.9828
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 1.9829
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 1.9830
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2738 - loss: 1.9831
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2738 - loss: 1.9832
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2739 - loss: 1.9832
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2739 - loss: 1.9832 - val_accuracy: 0.2659 - val_loss: 1.9707
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.7996
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3293 - loss: 1.9483  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3290 - loss: 1.9614
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3222 - loss: 1.9678
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3164 - loss: 1.9724
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3121 - loss: 1.9750
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3095 - loss: 1.9758
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3074 - loss: 1.9761
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3056 - loss: 1.9760
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3037 - loss: 1.9754
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3020 - loss: 1.9751
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3002 - loss: 1.9750
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2987 - loss: 1.9751
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2973 - loss: 1.9751
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2962 - loss: 1.9753
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2951 - loss: 1.9756
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2941 - loss: 1.9757
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2932 - loss: 1.9761
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2924 - loss: 1.9764
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2917 - loss: 1.9766
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2912 - loss: 1.9767
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2907 - loss: 1.9767
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2902 - loss: 1.9768
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2897 - loss: 1.9769
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2893 - loss: 1.9771
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2888 - loss: 1.9772
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2885 - loss: 1.9773
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2882 - loss: 1.9774
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2879 - loss: 1.9774
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2877 - loss: 1.9773
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2876 - loss: 1.9773 - val_accuracy: 0.2570 - val_loss: 1.9626

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 625ms/step
[1m65/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 784us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7:56[0m 817ms/step
[1m 59/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 862us/step  
[1m135/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 750us/step
[1m205/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 739us/step
[1m274/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 736us/step
[1m345/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 731us/step
[1m419/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 722us/step
[1m491/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 719us/step
[1m555/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 727us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m66/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 775us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 74/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 687us/step
[1m140/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 721us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 27.09 [%]
Global F1 score (validation) = 24.32 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.10811511 0.13215898 0.13394183 ... 0.00949391 0.09018736 0.01078106]
 [0.15815035 0.17955604 0.202197   ... 0.0017274  0.13207726 0.019659  ]
 [0.10652633 0.10694163 0.07741003 ... 0.01518838 0.07390905 0.01176677]
 ...
 [0.12820046 0.14279364 0.22828212 ... 0.0038741  0.10805263 0.01541614]
 [0.11145395 0.1465545  0.12243874 ... 0.00855488 0.09604279 0.01138869]
 [0.14098723 0.18517442 0.20237471 ... 0.00256071 0.10155702 0.01404349]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 30.46 [%]
Global accuracy score (test) = 24.92 [%]
Global F1 score (train) = 27.86 [%]
Global F1 score (test) = 23.11 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.00      0.00      0.00       184
 CAMINAR CON MÓVIL O LIBRO       0.16      0.24      0.19       184
       CAMINAR USUAL SPEED       0.15      0.22      0.18       184
            CAMINAR ZIGZAG       0.11      0.11      0.11       184
          DE PIE BARRIENDO       0.16      0.51      0.25       184
   DE PIE DOBLANDO TOALLAS       0.29      0.28      0.29       184
    DE PIE MOVIENDO LIBROS       0.32      0.12      0.17       184
          DE PIE USANDO PC       0.30      0.70      0.42       184
        FASE REPOSO CON K5       0.71      0.50      0.59       184
INCREMENTAL CICLOERGOMETRO       0.88      0.15      0.26       184
           SENTADO LEYENDO       0.25      0.25      0.25       184
         SENTADO USANDO PC       0.27      0.08      0.12       184
      SENTADO VIENDO LA TV       0.24      0.36      0.29       184
   SUBIR Y BAJAR ESCALERAS       0.07      0.01      0.01       184
                    TROTAR       0.97      0.21      0.35       161

                  accuracy                           0.25      2737
                 macro avg       0.33      0.25      0.23      2737
              weighted avg       0.32      0.25      0.23      2737


Accuracy capturado en la ejecución 5: 24.92 [%]
F1-score capturado en la ejecución 5: 23.11 [%]

=== EJECUCIÓN 6 ===

--- TRAIN (ejecución 6) ---

--- TEST (ejecución 6) ---
2025-11-07 14:12:23.886538: 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 14:12:23.898127: 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 00:00:1762521143.911231 2930485 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762521143.915365 2930485 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762521143.925143 2930485 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521143.925160 2930485 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521143.925162 2930485 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521143.925163 2930485 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:12:23.928288: 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 00:00:1762521146.215028 2930485 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762521147.707558 2930615 service.cc:152] XLA service 0x797e5c00bf60 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762521147.707584 2930615 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:12:27.734913: 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 00:00:1762521147.885163 2930615 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762521149.301659 2930615 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47:34[0m 2s/step - accuracy: 0.1250 - loss: 2.9826
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0749 - loss: 3.2434  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0672 - loss: 3.2542
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0655 - loss: 3.2478
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0643 - loss: 3.2380
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0638 - loss: 3.2266
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0639 - loss: 3.2127
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0642 - loss: 3.1993
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0643 - loss: 3.1864
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0645 - loss: 3.1759
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0649 - loss: 3.1649
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0653 - loss: 3.1548
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0657 - loss: 3.1464
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0663 - loss: 3.1378
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0670 - loss: 3.1278
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0676 - loss: 3.1192
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0681 - loss: 3.1111
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0689 - loss: 3.1022
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0697 - loss: 3.0934
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0705 - loss: 3.0852
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0713 - loss: 3.0773
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0720 - loss: 3.0701
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0727 - loss: 3.0633
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0735 - loss: 3.0565
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0742 - loss: 3.0497
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0749 - loss: 3.0438
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0757 - loss: 3.0376
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0764 - loss: 3.0318
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0772 - loss: 3.0256
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0778 - loss: 3.0211
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0778 - loss: 3.0209 - val_accuracy: 0.1521 - val_loss: 2.5762
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.8706
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0986 - loss: 2.6918  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1087 - loss: 2.6850
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1189 - loss: 2.6735
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1239 - loss: 2.6673
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1273 - loss: 2.6634
[1m 249/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1295 - loss: 2.6598
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1307 - loss: 2.6572
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1317 - loss: 2.6553
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1324 - loss: 2.6542
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1329 - loss: 2.6534
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1335 - loss: 2.6523
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1343 - loss: 2.6511
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1351 - loss: 2.6495
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1358 - loss: 2.6479
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1365 - loss: 2.6463
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1370 - loss: 2.6449
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1374 - loss: 2.6434
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1379 - loss: 2.6419
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1385 - loss: 2.6403
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1390 - loss: 2.6388
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1394 - loss: 2.6375
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1398 - loss: 2.6363
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1401 - loss: 2.6352
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1405 - loss: 2.6338
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1409 - loss: 2.6325
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1413 - loss: 2.6311
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1417 - loss: 2.6297
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1421 - loss: 2.6283
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.1424 - loss: 2.6269
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1424 - loss: 2.6269 - val_accuracy: 0.1782 - val_loss: 2.4689
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.4081
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1853 - loss: 2.4719  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1801 - loss: 2.4746
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1796 - loss: 2.4777
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1790 - loss: 2.4800
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1789 - loss: 2.4806
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1787 - loss: 2.4810
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1785 - loss: 2.4814
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1784 - loss: 2.4819
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1783 - loss: 2.4824
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1782 - loss: 2.4829
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1783 - loss: 2.4831
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1784 - loss: 2.4831
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1785 - loss: 2.4832
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1787 - loss: 2.4830
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1789 - loss: 2.4828
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1791 - loss: 2.4825
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1793 - loss: 2.4822
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1794 - loss: 2.4820
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1796 - loss: 2.4817
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1798 - loss: 2.4813
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1800 - loss: 2.4809
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1801 - loss: 2.4804
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1803 - loss: 2.4799
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1805 - loss: 2.4795
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1806 - loss: 2.4790
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1808 - loss: 2.4785
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1810 - loss: 2.4780
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1812 - loss: 2.4775
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1814 - loss: 2.4767
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1814 - loss: 2.4766 - val_accuracy: 0.2248 - val_loss: 2.3717
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.2170
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2224 - loss: 2.3561  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2102 - loss: 2.3697
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2062 - loss: 2.3737
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2035 - loss: 2.3784
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2018 - loss: 2.3811
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2009 - loss: 2.3829
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1996 - loss: 2.3849
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1986 - loss: 2.3868
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1977 - loss: 2.3886
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1969 - loss: 2.3899
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1962 - loss: 2.3910
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1956 - loss: 2.3918
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1953 - loss: 2.3921
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1952 - loss: 2.3923
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1951 - loss: 2.3923
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1950 - loss: 2.3925
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1950 - loss: 2.3925
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1950 - loss: 2.3925
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1951 - loss: 2.3924
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1952 - loss: 2.3922
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1953 - loss: 2.3919
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1955 - loss: 2.3915
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1956 - loss: 2.3911
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1958 - loss: 2.3907
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1959 - loss: 2.3902
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1960 - loss: 2.3898
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1962 - loss: 2.3893
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1963 - loss: 2.3889
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1964 - loss: 2.3886 - val_accuracy: 0.2266 - val_loss: 2.2873
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.4878
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2153 - loss: 2.3163  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2115 - loss: 2.3307
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2111 - loss: 2.3340
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2120 - loss: 2.3335
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2128 - loss: 2.3307
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2129 - loss: 2.3295
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2132 - loss: 2.3291
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2134 - loss: 2.3283
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2135 - loss: 2.3276
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2138 - loss: 2.3270
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2141 - loss: 2.3266
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2143 - loss: 2.3264
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2145 - loss: 2.3264
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2147 - loss: 2.3264
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2147 - loss: 2.3265
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2147 - loss: 2.3263
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2147 - loss: 2.3263
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2146 - loss: 2.3262
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2145 - loss: 2.3260
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2145 - loss: 2.3257
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2145 - loss: 2.3255
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2144 - loss: 2.3252
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2144 - loss: 2.3249
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2143 - loss: 2.3246
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2143 - loss: 2.3243
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2144 - loss: 2.3240
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2144 - loss: 2.3237
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2145 - loss: 2.3234
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2145 - loss: 2.3230
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2145 - loss: 2.3230 - val_accuracy: 0.2313 - val_loss: 2.2560
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.2534
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2085 - loss: 2.2899  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2106 - loss: 2.2972
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2111 - loss: 2.2957
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2125 - loss: 2.2941
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2133 - loss: 2.2936
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2132 - loss: 2.2935
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2133 - loss: 2.2935
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2133 - loss: 2.2932
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2133 - loss: 2.2925
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2135 - loss: 2.2919
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2137 - loss: 2.2910
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2139 - loss: 2.2900
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2140 - loss: 2.2890
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2142 - loss: 2.2882
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2145 - loss: 2.2873
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2147 - loss: 2.2866
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2149 - loss: 2.2860
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2151 - loss: 2.2854
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2154 - loss: 2.2847
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2156 - loss: 2.2841
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2159 - loss: 2.2833
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2163 - loss: 2.2825
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2166 - loss: 2.2816
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2169 - loss: 2.2808
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2173 - loss: 2.2800
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2176 - loss: 2.2792
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2179 - loss: 2.2785
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2181 - loss: 2.2778
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2183 - loss: 2.2772 - val_accuracy: 0.2424 - val_loss: 2.2087
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 19ms/step - accuracy: 0.4375 - loss: 1.9809
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2700 - loss: 2.1817  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2513 - loss: 2.1940
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2424 - loss: 2.2030
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2362 - loss: 2.2135
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2323 - loss: 2.2207
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2296 - loss: 2.2252
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2281 - loss: 2.2277
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2270 - loss: 2.2290
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2266 - loss: 2.2296
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2263 - loss: 2.2303
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2262 - loss: 2.2303
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2261 - loss: 2.2303
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2261 - loss: 2.2302
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2261 - loss: 2.2301
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2262 - loss: 2.2299
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2262 - loss: 2.2297
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2262 - loss: 2.2294
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2263 - loss: 2.2293
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2264 - loss: 2.2290
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2265 - loss: 2.2288
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2266 - loss: 2.2287
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2267 - loss: 2.2286
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2267 - loss: 2.2285
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2267 - loss: 2.2284
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2268 - loss: 2.2283
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2268 - loss: 2.2281
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2269 - loss: 2.2280
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2270 - loss: 2.2278
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2270 - loss: 2.2278 - val_accuracy: 0.2265 - val_loss: 2.1727
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.1441
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2042 - loss: 2.2158  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2102 - loss: 2.2208
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2144 - loss: 2.2237
[1m 169/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2176 - loss: 2.2218
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2196 - loss: 2.2195
[1m 253/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2210 - loss: 2.2174
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2218 - loss: 2.2167
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2227 - loss: 2.2152
[1m 378/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2238 - loss: 2.2134
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2248 - loss: 2.2122
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2255 - loss: 2.2115
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2263 - loss: 2.2106
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2269 - loss: 2.2096
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2272 - loss: 2.2090
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2275 - loss: 2.2084
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2278 - loss: 2.2077
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2281 - loss: 2.2071
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2283 - loss: 2.2066
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2285 - loss: 2.2060
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2288 - loss: 2.2055
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2290 - loss: 2.2051
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2292 - loss: 2.2046
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2294 - loss: 2.2042
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2296 - loss: 2.2039
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2298 - loss: 2.2036
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2300 - loss: 2.2033
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2302 - loss: 2.2030
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2304 - loss: 2.2027
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2305 - loss: 2.2026 - val_accuracy: 0.2457 - val_loss: 2.1189
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.3364
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2242 - loss: 2.2298  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2271 - loss: 2.2105
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2298 - loss: 2.1975
[1m 169/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2313 - loss: 2.1929
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2333 - loss: 2.1889
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2346 - loss: 2.1856
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2355 - loss: 2.1825
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2362 - loss: 2.1804
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2366 - loss: 2.1789
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2369 - loss: 2.1779
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2371 - loss: 2.1769
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2373 - loss: 2.1762
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2377 - loss: 2.1753
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2380 - loss: 2.1747
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2384 - loss: 2.1740
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2387 - loss: 2.1734
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2390 - loss: 2.1729
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2393 - loss: 2.1724
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2395 - loss: 2.1719
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2396 - loss: 2.1715
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2398 - loss: 2.1711
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2400 - loss: 2.1708
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2401 - loss: 2.1706
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2403 - loss: 2.1704
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2404 - loss: 2.1702
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2405 - loss: 2.1700
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2406 - loss: 2.1699
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2406 - loss: 2.1699
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2406 - loss: 2.1698 - val_accuracy: 0.2475 - val_loss: 2.1078
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.0625 - loss: 2.4901
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2252 - loss: 2.2153  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2390 - loss: 2.1770
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2426 - loss: 2.1665
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2428 - loss: 2.1639
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2423 - loss: 2.1624
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2420 - loss: 2.1605
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2421 - loss: 2.1584
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2421 - loss: 2.1573
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2420 - loss: 2.1570
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2420 - loss: 2.1569
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2420 - loss: 2.1567
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1566
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2420 - loss: 2.1565
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2421 - loss: 2.1562
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2424 - loss: 2.1557
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2426 - loss: 2.1554
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2428 - loss: 2.1553
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2429 - loss: 2.1551
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2432 - loss: 2.1549
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2434 - loss: 2.1547
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2436 - loss: 2.1545
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2438 - loss: 2.1543
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2439 - loss: 2.1540
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2442 - loss: 2.1537
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2444 - loss: 2.1533
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2446 - loss: 2.1529
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2448 - loss: 2.1525
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2450 - loss: 2.1521
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2452 - loss: 2.1517 - val_accuracy: 0.2601 - val_loss: 2.0792
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.8634
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2516 - loss: 2.0972  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2566 - loss: 2.1040
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2588 - loss: 2.1092
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2615 - loss: 2.1145
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2628 - loss: 2.1191
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2634 - loss: 2.1232
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2635 - loss: 2.1251
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2632 - loss: 2.1267
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2628 - loss: 2.1279
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2625 - loss: 2.1286
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2619 - loss: 2.1293
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2613 - loss: 2.1299
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2607 - loss: 2.1303
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2602 - loss: 2.1307
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2597 - loss: 2.1312
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2592 - loss: 2.1316
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2589 - loss: 2.1319
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2585 - loss: 2.1323
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.1326
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.1327
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2574 - loss: 2.1327
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2572 - loss: 2.1326
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2570 - loss: 2.1324
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.1321
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.1318
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.1314
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2564 - loss: 2.1312
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2563 - loss: 2.1309 - val_accuracy: 0.2562 - val_loss: 2.0615
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.0623
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0563  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0634
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2643 - loss: 2.0705
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0745
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2617 - loss: 2.0793
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0838
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2607 - loss: 2.0859
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0883
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2594 - loss: 2.0903
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2586 - loss: 2.0924
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.0942
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0959
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0971
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0983
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.0994
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2555 - loss: 2.1002
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2552 - loss: 2.1007
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2551 - loss: 2.1012
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2549 - loss: 2.1016
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.1021
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2547 - loss: 2.1026
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2545 - loss: 2.1030
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2544 - loss: 2.1033
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1035
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2542 - loss: 2.1037
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2541 - loss: 2.1038
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2541 - loss: 2.1039
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2541 - loss: 2.1039 - val_accuracy: 0.2505 - val_loss: 2.0374
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.2500 - loss: 2.1560
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2406 - loss: 2.1393  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2471 - loss: 2.1287
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2512 - loss: 2.1191
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2526 - loss: 2.1158
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2540 - loss: 2.1132
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2551 - loss: 2.1129
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2558 - loss: 2.1124
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2567 - loss: 2.1119
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.1107
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2586 - loss: 2.1092
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2591 - loss: 2.1079
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2596 - loss: 2.1065
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2598 - loss: 2.1057
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2598 - loss: 2.1048
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2598 - loss: 2.1044
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2597 - loss: 2.1040
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2596 - loss: 2.1036
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2595 - loss: 2.1033
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2595 - loss: 2.1028
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2595 - loss: 2.1024
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2595 - loss: 2.1020
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2595 - loss: 2.1015
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2595 - loss: 2.1011
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2596 - loss: 2.1008
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2596 - loss: 2.1006
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2596 - loss: 2.1003
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2596 - loss: 2.1000
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2596 - loss: 2.0997
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2597 - loss: 2.0994
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2597 - loss: 2.0994 - val_accuracy: 0.2551 - val_loss: 2.0532
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.5232
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2458 - loss: 2.1507  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2488 - loss: 2.1317
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2520 - loss: 2.1226
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2546 - loss: 2.1169
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2563 - loss: 2.1114
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2573 - loss: 2.1081
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2578 - loss: 2.1050
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2581 - loss: 2.1022
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2582 - loss: 2.0992
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0968
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2580 - loss: 2.0949
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0930
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2583 - loss: 2.0912
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2583 - loss: 2.0901
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2583 - loss: 2.0892
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2584 - loss: 2.0885
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2584 - loss: 2.0878
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2585 - loss: 2.0872
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2586 - loss: 2.0867
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2587 - loss: 2.0862
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2588 - loss: 2.0858
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2589 - loss: 2.0853
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2591 - loss: 2.0848
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2593 - loss: 2.0842
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2594 - loss: 2.0838
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2595 - loss: 2.0833
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2596 - loss: 2.0829
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2597 - loss: 2.0826
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2598 - loss: 2.0823 - val_accuracy: 0.2675 - val_loss: 2.0144
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 1.9809
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2668 - loss: 1.9893  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0109
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0255
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0340
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2619 - loss: 2.0382
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2629 - loss: 2.0421
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0451
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2643 - loss: 2.0474
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2648 - loss: 2.0492
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0507
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0521
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0530
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0537
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0545
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0551
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0556
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0559
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0560
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0561
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0561
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0560
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0559
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2673 - loss: 2.0557
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0555
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0554
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0552
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0551
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0551
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2678 - loss: 2.0550 - val_accuracy: 0.2738 - val_loss: 2.0043
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.1875 - loss: 1.8753
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2538 - loss: 2.0674  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2580 - loss: 2.0590
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2578 - loss: 2.0553
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2589 - loss: 2.0511
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0483
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0465
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2617 - loss: 2.0455
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2623 - loss: 2.0445
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0442
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2638 - loss: 2.0436
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0425
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0417
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0411
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0404
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0399
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0397
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0395
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0393
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0390
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2673 - loss: 2.0389
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0389
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0389
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0389
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2678 - loss: 2.0389
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0389
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2680 - loss: 2.0389
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0389
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0389
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0389
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2682 - loss: 2.0389 - val_accuracy: 0.2718 - val_loss: 2.0041
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.7903
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2897 - loss: 2.0211  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2866 - loss: 2.0240
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2859 - loss: 2.0253
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2855 - loss: 2.0267
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2853 - loss: 2.0267
[1m 251/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2854 - loss: 2.0257
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2853 - loss: 2.0244
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2854 - loss: 2.0230
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2854 - loss: 2.0222
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2853 - loss: 2.0217
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2851 - loss: 2.0215
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2849 - loss: 2.0214
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2847 - loss: 2.0213
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2845 - loss: 2.0213
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2842 - loss: 2.0215
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2839 - loss: 2.0218
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2836 - loss: 2.0219
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2833 - loss: 2.0220
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2832 - loss: 2.0220
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2829 - loss: 2.0221
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2827 - loss: 2.0222
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2825 - loss: 2.0224
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2822 - loss: 2.0226
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2820 - loss: 2.0228
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2818 - loss: 2.0229
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2815 - loss: 2.0230
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2813 - loss: 2.0230
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 2.0230
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2810 - loss: 2.0230 - val_accuracy: 0.2710 - val_loss: 1.9825
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.4375 - loss: 1.7492
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2865 - loss: 1.9961  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0043
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2705 - loss: 2.0134
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0207
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2695 - loss: 2.0272
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2689 - loss: 2.0319
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2684 - loss: 2.0353
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0368
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2689 - loss: 2.0377
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0380
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0379
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0376
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0372
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2712 - loss: 2.0369
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0364
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0360
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0355
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0353
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0350
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0347
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0344
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0340
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0337
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0332
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0329
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0326
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0322
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0318
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2718 - loss: 2.0313 - val_accuracy: 0.2849 - val_loss: 1.9855
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3750 - loss: 1.8383
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3412 - loss: 1.9410  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3144 - loss: 1.9737
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3048 - loss: 1.9861
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2991 - loss: 1.9948
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2962 - loss: 1.9982
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2945 - loss: 2.0000
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2937 - loss: 2.0005
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2932 - loss: 2.0014
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2924 - loss: 2.0026
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2916 - loss: 2.0029
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2910 - loss: 2.0027
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2904 - loss: 2.0026
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2898 - loss: 2.0027
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2894 - loss: 2.0027
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2888 - loss: 2.0027
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2883 - loss: 2.0027
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2879 - loss: 2.0026
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2875 - loss: 2.0025
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2871 - loss: 2.0025
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2866 - loss: 2.0026
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2862 - loss: 2.0027
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2858 - loss: 2.0028
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2855 - loss: 2.0029
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2852 - loss: 2.0030
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2849 - loss: 2.0030
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2847 - loss: 2.0031
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2845 - loss: 2.0031
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2843 - loss: 2.0032
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2843 - loss: 2.0032 - val_accuracy: 0.2675 - val_loss: 1.9781
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.1875 - loss: 2.1908
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2429 - loss: 2.0535  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2523 - loss: 2.0337
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2592 - loss: 2.0233
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2632 - loss: 2.0188
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0154
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0146
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2673 - loss: 2.0144
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0148
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2678 - loss: 2.0148
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0145
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0141
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2692 - loss: 2.0135
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0126
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0120
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0114
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0107
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2714 - loss: 2.0101
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0097
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0093
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2723 - loss: 2.0089
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2725 - loss: 2.0084
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2728 - loss: 2.0080
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2730 - loss: 2.0075
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0072
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2735 - loss: 2.0068
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 2.0066
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2739 - loss: 2.0064
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2741 - loss: 2.0062
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2742 - loss: 2.0061 - val_accuracy: 0.2718 - val_loss: 1.9796
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.3125 - loss: 2.0156
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2982 - loss: 1.9816  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2840 - loss: 2.0021
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2791 - loss: 2.0051
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2783 - loss: 2.0056
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2788 - loss: 2.0056
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2791 - loss: 2.0062
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2788 - loss: 2.0074
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2785 - loss: 2.0089
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2782 - loss: 2.0103
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2782 - loss: 2.0108
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2782 - loss: 2.0108
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2782 - loss: 2.0108
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2784 - loss: 2.0103
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2786 - loss: 2.0098
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2788 - loss: 2.0092
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2791 - loss: 2.0083
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2793 - loss: 2.0075
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 2.0065
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 2.0055
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2802 - loss: 2.0046
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 2.0038
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 2.0031
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2807 - loss: 2.0024
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2808 - loss: 2.0018
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2809 - loss: 2.0012
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 2.0006
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 2.0000
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9995
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2813 - loss: 1.9991 - val_accuracy: 0.2814 - val_loss: 1.9643
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.4375 - loss: 1.9139
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2788 - loss: 2.0279  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2788 - loss: 2.0163
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2822 - loss: 2.0017
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2822 - loss: 1.9918
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2811 - loss: 1.9881
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2806 - loss: 1.9856
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2800 - loss: 1.9845
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2797 - loss: 1.9836
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2798 - loss: 1.9824
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 1.9807
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 1.9792
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2809 - loss: 1.9780
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 1.9777
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2814 - loss: 1.9777
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2815 - loss: 1.9778
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2817 - loss: 1.9778
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2818 - loss: 1.9779
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2819 - loss: 1.9780
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2820 - loss: 1.9783
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2822 - loss: 1.9785
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2823 - loss: 1.9786
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2824 - loss: 1.9789
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2825 - loss: 1.9791
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2825 - loss: 1.9793
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2826 - loss: 1.9795
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2826 - loss: 1.9797
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2827 - loss: 1.9798
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2827 - loss: 1.9799
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.2827 - loss: 1.9801
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2827 - loss: 1.9801 - val_accuracy: 0.2596 - val_loss: 1.9831
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 1.8717
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0220  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0153
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2680 - loss: 2.0098
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0035
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0001
[1m 249/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2693 - loss: 1.9972
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2703 - loss: 1.9938
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2713 - loss: 1.9912
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2722 - loss: 1.9890
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2730 - loss: 1.9875
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 1.9864
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 1.9857
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2750 - loss: 1.9848
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2756 - loss: 1.9839
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 1.9832
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2766 - loss: 1.9824
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2772 - loss: 1.9818
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2777 - loss: 1.9814
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2782 - loss: 1.9810
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2787 - loss: 1.9806
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2791 - loss: 1.9802
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 1.9798
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 1.9794
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2802 - loss: 1.9791
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 1.9787
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2808 - loss: 1.9785
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 1.9783
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 1.9782
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2812 - loss: 1.9781 - val_accuracy: 0.2609 - val_loss: 1.9806
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 1.9513
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2667 - loss: 1.9402  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2838 - loss: 1.9191
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2905 - loss: 1.9148
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2925 - loss: 1.9205
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2932 - loss: 1.9243
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2933 - loss: 1.9280
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2936 - loss: 1.9314
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2937 - loss: 1.9339
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2940 - loss: 1.9356
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2942 - loss: 1.9369
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2944 - loss: 1.9385
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2944 - loss: 1.9396
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2944 - loss: 1.9407
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2945 - loss: 1.9418
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2946 - loss: 1.9424
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2947 - loss: 1.9434
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2948 - loss: 1.9443
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2948 - loss: 1.9452
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2948 - loss: 1.9461
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2948 - loss: 1.9467
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2949 - loss: 1.9473
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2949 - loss: 1.9479
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2948 - loss: 1.9486
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2947 - loss: 1.9492
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2946 - loss: 1.9497
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2944 - loss: 1.9502
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2944 - loss: 1.9507
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2943 - loss: 1.9510
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2943 - loss: 1.9513 - val_accuracy: 0.2696 - val_loss: 1.9656
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 1.9973
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3183 - loss: 1.8688  
[1m  69/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3119 - loss: 1.8856
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3099 - loss: 1.9028
[1m 149/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3092 - loss: 1.9135
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3084 - loss: 1.9173
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3076 - loss: 1.9197
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3065 - loss: 1.9231
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3050 - loss: 1.9260
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3038 - loss: 1.9281
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3026 - loss: 1.9299
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3016 - loss: 1.9313
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3007 - loss: 1.9327
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2998 - loss: 1.9343
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2990 - loss: 1.9355
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2984 - loss: 1.9366
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2977 - loss: 1.9379
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2971 - loss: 1.9390
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2967 - loss: 1.9396
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2962 - loss: 1.9403
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2957 - loss: 1.9411
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2953 - loss: 1.9417
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2949 - loss: 1.9422
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2946 - loss: 1.9426
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2942 - loss: 1.9430
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2940 - loss: 1.9433
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2937 - loss: 1.9437
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2934 - loss: 1.9441
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2932 - loss: 1.9444
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2929 - loss: 1.9447
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2929 - loss: 1.9448 - val_accuracy: 0.2698 - val_loss: 1.9766

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 609ms/step
[1m70/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 725us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:00[0m 825ms/step
[1m 68/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 748us/step  
[1m126/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 804us/step
[1m193/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 788us/step
[1m263/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 770us/step
[1m334/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 757us/step
[1m407/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 744us/step
[1m460/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 767us/step
[1m518/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 779us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m64/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 794us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[1m 69/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 743us/step
[1m139/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 730us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 25.7 [%]
Global F1 score (validation) = 23.42 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.13523445 0.16736065 0.12622993 ... 0.0031919  0.12979352 0.01636348]
 [0.13494466 0.23380737 0.15888505 ... 0.00100718 0.17341493 0.02725961]
 [0.10649718 0.1503569  0.11968276 ... 0.00573067 0.10119355 0.01375163]
 ...
 [0.14864828 0.1974837  0.18475431 ... 0.00125412 0.17393476 0.02659237]
 [0.17653266 0.181064   0.16399603 ... 0.00177747 0.17697735 0.0316839 ]
 [0.0472532  0.05648268 0.04931312 ... 0.01076282 0.04230367 0.00560883]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 30.61 [%]
Global accuracy score (test) = 23.86 [%]
Global F1 score (train) = 27.88 [%]
Global F1 score (test) = 20.91 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.00      0.00      0.00       184
 CAMINAR CON MÓVIL O LIBRO       0.13      0.32      0.19       184
       CAMINAR USUAL SPEED       0.17      0.07      0.10       184
            CAMINAR ZIGZAG       0.10      0.14      0.12       184
          DE PIE BARRIENDO       0.15      0.46      0.23       184
   DE PIE DOBLANDO TOALLAS       0.16      0.11      0.13       184
    DE PIE MOVIENDO LIBROS       0.14      0.10      0.11       184
          DE PIE USANDO PC       0.26      0.91      0.41       184
        FASE REPOSO CON K5       0.86      0.62      0.73       184
INCREMENTAL CICLOERGOMETRO       1.00      0.02      0.03       184
           SENTADO LEYENDO       0.27      0.20      0.23       184
         SENTADO USANDO PC       0.25      0.01      0.02       184
      SENTADO VIENDO LA TV       0.31      0.26      0.28       184
   SUBIR Y BAJAR ESCALERAS       0.29      0.02      0.04       184
                    TROTAR       0.98      0.35      0.51       161

                  accuracy                           0.24      2737
                 macro avg       0.34      0.24      0.21      2737
              weighted avg       0.33      0.24      0.21      2737


Accuracy capturado en la ejecución 6: 23.86 [%]
F1-score capturado en la ejecución 6: 20.91 [%]

=== EJECUCIÓN 7 ===

--- TRAIN (ejecución 7) ---

--- TEST (ejecución 7) ---
2025-11-07 14:13:30.686250: 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 14:13:30.697607: 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 00:00:1762521210.710619 2934214 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762521210.714758 2934214 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762521210.724445 2934214 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521210.724461 2934214 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521210.724463 2934214 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521210.724464 2934214 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:13:30.727588: 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 00:00:1762521213.015402 2934214 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762521214.520104 2934345 service.cc:152] XLA service 0x7ac82c00c460 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762521214.520129 2934345 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:13:34.547439: 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 00:00:1762521214.697111 2934345 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762521216.124192 2934345 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47:38[0m 2s/step - accuracy: 0.1250 - loss: 3.0609
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0944 - loss: 3.3075  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0875 - loss: 3.2898
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0843 - loss: 3.2712
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0829 - loss: 3.2578
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0821 - loss: 3.2485
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0813 - loss: 3.2412
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0815 - loss: 3.2331
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0818 - loss: 3.2259
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0822 - loss: 3.2190
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0825 - loss: 3.2118
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0830 - loss: 3.2053
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0835 - loss: 3.1984
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0840 - loss: 3.1921
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0844 - loss: 3.1861
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0848 - loss: 3.1802
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0852 - loss: 3.1742
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0856 - loss: 3.1681
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0859 - loss: 3.1625
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0862 - loss: 3.1562
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0864 - loss: 3.1507
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0867 - loss: 3.1447
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0870 - loss: 3.1399
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0873 - loss: 3.1339
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0876 - loss: 3.1285
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0878 - loss: 3.1235
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0880 - loss: 3.1184
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0883 - loss: 3.1131
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0885 - loss: 3.1082
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0886 - loss: 3.1049
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0887 - loss: 3.1048 - val_accuracy: 0.1377 - val_loss: 2.6434
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.7613
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1198 - loss: 2.7240  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1246 - loss: 2.7177
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1280 - loss: 2.7129
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1287 - loss: 2.7111
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1284 - loss: 2.7092
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1281 - loss: 2.7074
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1278 - loss: 2.7059
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1276 - loss: 2.7042
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1272 - loss: 2.7029
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1271 - loss: 2.7016
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1270 - loss: 2.7003
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1271 - loss: 2.6990
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1272 - loss: 2.6977
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1275 - loss: 2.6963
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1278 - loss: 2.6948
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1281 - loss: 2.6930
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1284 - loss: 2.6911
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1287 - loss: 2.6893
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1290 - loss: 2.6875
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1293 - loss: 2.6856
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1296 - loss: 2.6837
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1300 - loss: 2.6818
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1303 - loss: 2.6799
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1307 - loss: 2.6779
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1310 - loss: 2.6762
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1313 - loss: 2.6743
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1317 - loss: 2.6725
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1320 - loss: 2.6708
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1321 - loss: 2.6702 - val_accuracy: 0.1676 - val_loss: 2.4923
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.4295
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1493 - loss: 2.5552  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1507 - loss: 2.5545
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1565 - loss: 2.5489
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1596 - loss: 2.5470
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1612 - loss: 2.5456
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1618 - loss: 2.5446
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1626 - loss: 2.5427
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1633 - loss: 2.5407
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1637 - loss: 2.5393
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1641 - loss: 2.5379
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1645 - loss: 2.5363
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1648 - loss: 2.5346
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1652 - loss: 2.5328
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1654 - loss: 2.5313
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1654 - loss: 2.5299
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1655 - loss: 2.5286
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1657 - loss: 2.5274
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1658 - loss: 2.5260
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1661 - loss: 2.5246
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1664 - loss: 2.5233
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1667 - loss: 2.5218
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1670 - loss: 2.5203
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1674 - loss: 2.5189
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1677 - loss: 2.5176
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1679 - loss: 2.5163
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1682 - loss: 2.5151
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1684 - loss: 2.5138
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1687 - loss: 2.5126
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1690 - loss: 2.5114
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1690 - loss: 2.5113 - val_accuracy: 0.2183 - val_loss: 2.3885
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.3900
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2193 - loss: 2.3999  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2048 - loss: 2.4154
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1990 - loss: 2.4251
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1941 - loss: 2.4315
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1914 - loss: 2.4344
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1896 - loss: 2.4358
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1889 - loss: 2.4351
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1885 - loss: 2.4344
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1882 - loss: 2.4338
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1879 - loss: 2.4331
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1876 - loss: 2.4323
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1875 - loss: 2.4315
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1873 - loss: 2.4309
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1872 - loss: 2.4301
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1871 - loss: 2.4295
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1871 - loss: 2.4287
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1872 - loss: 2.4279
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1874 - loss: 2.4271
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1876 - loss: 2.4262
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1880 - loss: 2.4253
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1883 - loss: 2.4242
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1887 - loss: 2.4232
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1890 - loss: 2.4224
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1894 - loss: 2.4215
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1897 - loss: 2.4206
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1900 - loss: 2.4197
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1903 - loss: 2.4187
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1906 - loss: 2.4178
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1909 - loss: 2.4170
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1909 - loss: 2.4169 - val_accuracy: 0.2170 - val_loss: 2.3215
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.7989
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2113 - loss: 2.4179  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2141 - loss: 2.3898
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2146 - loss: 2.3761
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2145 - loss: 2.3669
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2145 - loss: 2.3624
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2139 - loss: 2.3595
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2132 - loss: 2.3575
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2127 - loss: 2.3561
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2123 - loss: 2.3550
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2119 - loss: 2.3540
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2117 - loss: 2.3533
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2116 - loss: 2.3526
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2116 - loss: 2.3521
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2116 - loss: 2.3515
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2117 - loss: 2.3508
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2117 - loss: 2.3502
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2118 - loss: 2.3495
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2119 - loss: 2.3488
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2120 - loss: 2.3483
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2121 - loss: 2.3480
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2122 - loss: 2.3476
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2122 - loss: 2.3473
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2123 - loss: 2.3470
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2123 - loss: 2.3467
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2124 - loss: 2.3463
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2125 - loss: 2.3460
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2126 - loss: 2.3456
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2127 - loss: 2.3452
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2127 - loss: 2.3450 - val_accuracy: 0.2294 - val_loss: 2.2785
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.2582
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2233 - loss: 2.2827  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2242 - loss: 2.2891
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2246 - loss: 2.2917
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2233 - loss: 2.2964
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2228 - loss: 2.2982
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2223 - loss: 2.2989
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2217 - loss: 2.2996
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2214 - loss: 2.2999
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2213 - loss: 2.3001
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2213 - loss: 2.3002
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2211 - loss: 2.3007
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2209 - loss: 2.3010
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2208 - loss: 2.3011
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2208 - loss: 2.3009
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2207 - loss: 2.3008
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2207 - loss: 2.3006
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2206 - loss: 2.3001
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2207 - loss: 2.2997
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2207 - loss: 2.2992
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2207 - loss: 2.2988
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2208 - loss: 2.2982
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2209 - loss: 2.2976
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2210 - loss: 2.2971
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2211 - loss: 2.2966
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2212 - loss: 2.2961
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2213 - loss: 2.2957
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2214 - loss: 2.2952
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2216 - loss: 2.2947
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2217 - loss: 2.2943
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2217 - loss: 2.2940 - val_accuracy: 0.2374 - val_loss: 2.2320
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.4214
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2106 - loss: 2.2859  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2192 - loss: 2.2693
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2218 - loss: 2.2609
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2237 - loss: 2.2574
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2251 - loss: 2.2584
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2260 - loss: 2.2581
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2270 - loss: 2.2574
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2279 - loss: 2.2570
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2285 - loss: 2.2565
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2288 - loss: 2.2567
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2290 - loss: 2.2570
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2291 - loss: 2.2571
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2291 - loss: 2.2573
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2293 - loss: 2.2574
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2294 - loss: 2.2574
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2297 - loss: 2.2575
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2298 - loss: 2.2575
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2300 - loss: 2.2575
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2301 - loss: 2.2575
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2302 - loss: 2.2574
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2304 - loss: 2.2573
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2304 - loss: 2.2572
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2305 - loss: 2.2571
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2305 - loss: 2.2570
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2305 - loss: 2.2569
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2305 - loss: 2.2567
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2306 - loss: 2.2565
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2306 - loss: 2.2563
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2306 - loss: 2.2561
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2306 - loss: 2.2560 - val_accuracy: 0.2444 - val_loss: 2.1974
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.2551
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2145 - loss: 2.2114  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2209 - loss: 2.2107
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2263 - loss: 2.2103
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2111
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2295 - loss: 2.2116
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2303 - loss: 2.2130
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2313 - loss: 2.2135
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2313 - loss: 2.2139
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2309 - loss: 2.2144
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2308 - loss: 2.2143
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2308 - loss: 2.2144
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2308 - loss: 2.2144
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2308 - loss: 2.2144
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2307 - loss: 2.2146
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2307 - loss: 2.2148
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2307 - loss: 2.2149
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2308 - loss: 2.2150
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2309 - loss: 2.2148
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2311 - loss: 2.2146
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2312 - loss: 2.2144
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2314 - loss: 2.2142
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2315 - loss: 2.2141
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2316 - loss: 2.2140
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2317 - loss: 2.2139
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2318 - loss: 2.2139
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2319 - loss: 2.2138
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2320 - loss: 2.2136
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2321 - loss: 2.2134
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2322 - loss: 2.2133
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2323 - loss: 2.2132 - val_accuracy: 0.2353 - val_loss: 2.1673
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 1.9643
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2220 - loss: 2.1857  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2190 - loss: 2.2018
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2174 - loss: 2.2083
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2178 - loss: 2.2107
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2191 - loss: 2.2090
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2203 - loss: 2.2079
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2218 - loss: 2.2072
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2233 - loss: 2.2062
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2248 - loss: 2.2054
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2257 - loss: 2.2050
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2264 - loss: 2.2047
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2273 - loss: 2.2042
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2033
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2290 - loss: 2.2025
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2297 - loss: 2.2017
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2305 - loss: 2.2009
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2312 - loss: 2.2001
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2318 - loss: 2.1996
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2322 - loss: 2.1992
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2327 - loss: 2.1988
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2332 - loss: 2.1983
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2337 - loss: 2.1979
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2341 - loss: 2.1974
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2345 - loss: 2.1971
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2348 - loss: 2.1967
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2351 - loss: 2.1963
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2354 - loss: 2.1959
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2357 - loss: 2.1955
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2358 - loss: 2.1954 - val_accuracy: 0.2279 - val_loss: 2.1433
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 2.3203
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2516 - loss: 2.2217  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2519 - loss: 2.2114
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2515 - loss: 2.2076
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2534 - loss: 2.2010
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2542 - loss: 2.1975
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2540 - loss: 2.1952
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2537 - loss: 2.1931
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2528 - loss: 2.1917
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2522 - loss: 2.1900
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2518 - loss: 2.1881
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2515 - loss: 2.1867
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2514 - loss: 2.1857
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.1846
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.1834
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2512 - loss: 2.1825
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2511 - loss: 2.1815
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2510 - loss: 2.1805
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2510 - loss: 2.1795
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2509 - loss: 2.1786
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2507 - loss: 2.1778
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2506 - loss: 2.1771
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2505 - loss: 2.1763
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2504 - loss: 2.1756
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2504 - loss: 2.1750
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2503 - loss: 2.1743
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.1737
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2501 - loss: 2.1731
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2501 - loss: 2.1725
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2500 - loss: 2.1720
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2500 - loss: 2.1718 - val_accuracy: 0.2274 - val_loss: 2.1187
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.2267
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2409 - loss: 2.1618  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2397 - loss: 2.1624
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2414 - loss: 2.1558
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2431 - loss: 2.1508
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2437 - loss: 2.1466
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2442 - loss: 2.1439
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2446 - loss: 2.1410
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2450 - loss: 2.1391
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2456 - loss: 2.1376
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2463 - loss: 2.1363
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2469 - loss: 2.1355
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2474 - loss: 2.1351
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2479 - loss: 2.1350
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2482 - loss: 2.1351
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2485 - loss: 2.1353
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2488 - loss: 2.1354
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2490 - loss: 2.1356
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2493 - loss: 2.1357
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2495 - loss: 2.1357
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2497 - loss: 2.1357
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2499 - loss: 2.1357
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2501 - loss: 2.1357
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2503 - loss: 2.1357
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2505 - loss: 2.1356
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2507 - loss: 2.1356
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2509 - loss: 2.1355
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2510 - loss: 2.1355
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2511 - loss: 2.1354
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2512 - loss: 2.1354 - val_accuracy: 0.2603 - val_loss: 2.0928
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.0181
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2783 - loss: 2.1067  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2665 - loss: 2.1259
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2638 - loss: 2.1262
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2628 - loss: 2.1269
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2621 - loss: 2.1268
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2616 - loss: 2.1271
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2608 - loss: 2.1283
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2600 - loss: 2.1290
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2594 - loss: 2.1291
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2585 - loss: 2.1295
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.1298
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2571 - loss: 2.1300
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.1299
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2562 - loss: 2.1300
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2557 - loss: 2.1302
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2553 - loss: 2.1304
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.1305
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2545 - loss: 2.1305
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1303
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2542 - loss: 2.1301
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2541 - loss: 2.1299
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2540 - loss: 2.1297
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2538 - loss: 2.1296
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2536 - loss: 2.1295
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2535 - loss: 2.1294
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2534 - loss: 2.1292
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2534 - loss: 2.1290
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2533 - loss: 2.1289
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2533 - loss: 2.1287 - val_accuracy: 0.2318 - val_loss: 2.0978
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.1926
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2365 - loss: 2.0843  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2428 - loss: 2.0923
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2451 - loss: 2.0915
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2476 - loss: 2.0891
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2490 - loss: 2.0868
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2502 - loss: 2.0865
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2516 - loss: 2.0866
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2526 - loss: 2.0869
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2533 - loss: 2.0879
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2538 - loss: 2.0887
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2541 - loss: 2.0893
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.0900
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2544 - loss: 2.0908
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2545 - loss: 2.0915
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2545 - loss: 2.0922
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2545 - loss: 2.0929
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2546 - loss: 2.0934
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2547 - loss: 2.0939
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0944
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0948
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0952
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0956
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0958
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2549 - loss: 2.0960
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2550 - loss: 2.0962
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2550 - loss: 2.0964
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2551 - loss: 2.0965
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2551 - loss: 2.0966
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2551 - loss: 2.0968 - val_accuracy: 0.2437 - val_loss: 2.0492
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.1037
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2462 - loss: 2.1228  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1086
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2556 - loss: 2.1074
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2570 - loss: 2.1058
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2588 - loss: 2.1025
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2606 - loss: 2.0990
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2620 - loss: 2.0959
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0935
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0923
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2634 - loss: 2.0913
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2632 - loss: 2.0908
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0905
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2629 - loss: 2.0902
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2627 - loss: 2.0897
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2624 - loss: 2.0889
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2622 - loss: 2.0885
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2619 - loss: 2.0882
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2617 - loss: 2.0880
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2614 - loss: 2.0877
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0875
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0872
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2607 - loss: 2.0869
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2605 - loss: 2.0866
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0863
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0860
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0858
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2601 - loss: 2.0857
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2600 - loss: 2.0857
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0857
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2599 - loss: 2.0857 - val_accuracy: 0.2416 - val_loss: 2.0566
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.0327
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2621 - loss: 2.0382  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2587 - loss: 2.0464
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0409
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2622 - loss: 2.0401
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2623 - loss: 2.0409
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2614 - loss: 2.0429
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2606 - loss: 2.0447
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0467
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0484
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0498
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0512
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0526
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0537
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0550
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0560
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0569
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0577
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0583
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0589
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2605 - loss: 2.0593
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2606 - loss: 2.0599
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2608 - loss: 2.0603
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2608 - loss: 2.0607
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0610
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0613
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0615
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2612 - loss: 2.0617
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2612 - loss: 2.0619
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2613 - loss: 2.0620 - val_accuracy: 0.2479 - val_loss: 2.0396
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.3125 - loss: 1.7069
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2748 - loss: 1.9853  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0107
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0256
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2654 - loss: 2.0341
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0389
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0417
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0429
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2647 - loss: 2.0447
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0463
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2641 - loss: 2.0478
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0490
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0499
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2632 - loss: 2.0510
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0520
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0526
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0530
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2632 - loss: 2.0532
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0533
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2635 - loss: 2.0534
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0534
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2638 - loss: 2.0535
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2640 - loss: 2.0535
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2641 - loss: 2.0536
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0537
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0538
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0539
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2646 - loss: 2.0541
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2646 - loss: 2.0542
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2647 - loss: 2.0543
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2648 - loss: 2.0543 - val_accuracy: 0.2488 - val_loss: 2.0405
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.8771
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0401  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2590 - loss: 2.0433
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0475
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0487
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0503
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0531
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0545
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2575 - loss: 2.0553
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2576 - loss: 2.0557
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.0557
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2582 - loss: 2.0554
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2585 - loss: 2.0555
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2589 - loss: 2.0554
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2594 - loss: 2.0550
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2597 - loss: 2.0546
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2600 - loss: 2.0542
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0538
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2606 - loss: 2.0534
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0529
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2612 - loss: 2.0524
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2615 - loss: 2.0521
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2617 - loss: 2.0518
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2618 - loss: 2.0516
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2620 - loss: 2.0514
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2620 - loss: 2.0513
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2621 - loss: 2.0513
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2622 - loss: 2.0513
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2622 - loss: 2.0514
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2622 - loss: 2.0515
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2622 - loss: 2.0515 - val_accuracy: 0.2481 - val_loss: 2.0246
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1875 - loss: 2.2274
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0820  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2727 - loss: 2.0518
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2741 - loss: 2.0456
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2760 - loss: 2.0423
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2772 - loss: 2.0392
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2774 - loss: 2.0373
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2769 - loss: 2.0366
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2763 - loss: 2.0360
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2759 - loss: 2.0358
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2756 - loss: 2.0357
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2755 - loss: 2.0354
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2754 - loss: 2.0351
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2754 - loss: 2.0349
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0351
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0354
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0355
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0354
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0353
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0352
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0352
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0354
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2742 - loss: 2.0356
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2741 - loss: 2.0358
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2739 - loss: 2.0360
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2738 - loss: 2.0363
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0365
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2735 - loss: 2.0367
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2734 - loss: 2.0368
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2733 - loss: 2.0368
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2733 - loss: 2.0368 - val_accuracy: 0.2644 - val_loss: 2.0149
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3750 - loss: 2.0828
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2683 - loss: 2.1049  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2795 - loss: 2.0773
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2821 - loss: 2.0621
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2823 - loss: 2.0570
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2822 - loss: 2.0535
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2821 - loss: 2.0509
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2814 - loss: 2.0490
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2808 - loss: 2.0474
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2800 - loss: 2.0461
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2793 - loss: 2.0451
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2788 - loss: 2.0440
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2783 - loss: 2.0432
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2779 - loss: 2.0424
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 2.0415
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2772 - loss: 2.0407
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2770 - loss: 2.0400
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2767 - loss: 2.0395
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2765 - loss: 2.0390
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2764 - loss: 2.0386
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2762 - loss: 2.0380
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0376
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2760 - loss: 2.0371
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2760 - loss: 2.0368
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 2.0366
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2758 - loss: 2.0363
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2758 - loss: 2.0360
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2757 - loss: 2.0358
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2757 - loss: 2.0356
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2756 - loss: 2.0354
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2756 - loss: 2.0353 - val_accuracy: 0.2566 - val_loss: 1.9982
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.5000 - loss: 1.7028
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3388 - loss: 1.9382  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3209 - loss: 1.9732
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3108 - loss: 1.9887
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3057 - loss: 1.9962
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3021 - loss: 2.0014
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2986 - loss: 2.0061
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2952 - loss: 2.0098
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2924 - loss: 2.0117
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2902 - loss: 2.0132
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2886 - loss: 2.0143
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2870 - loss: 2.0155
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2858 - loss: 2.0163
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2847 - loss: 2.0170
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2838 - loss: 2.0176
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2830 - loss: 2.0183
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2823 - loss: 2.0189
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2818 - loss: 2.0193
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2813 - loss: 2.0196
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2809 - loss: 2.0198
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2807 - loss: 2.0199
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 2.0198
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2803 - loss: 2.0198
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 2.0198
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 2.0198
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2798 - loss: 2.0199
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 2.0200
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2794 - loss: 2.0200
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2793 - loss: 2.0200
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2792 - loss: 2.0199
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2792 - loss: 2.0199 - val_accuracy: 0.2540 - val_loss: 1.9912
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.7488
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2462 - loss: 2.0760  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2580 - loss: 2.0776
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0744
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2646 - loss: 2.0683
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0616
[1m 227/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0574
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2683 - loss: 2.0528
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0492
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2689 - loss: 2.0456
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2695 - loss: 2.0420
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0390
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0367
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0343
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0326
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2723 - loss: 2.0311
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2729 - loss: 2.0296
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2735 - loss: 2.0281
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0267
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0256
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0248
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2751 - loss: 2.0239
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2754 - loss: 2.0231
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2756 - loss: 2.0225
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2758 - loss: 2.0220
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0215
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2763 - loss: 2.0210
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2764 - loss: 2.0205
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2766 - loss: 2.0201
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2768 - loss: 2.0196
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2769 - loss: 2.0193 - val_accuracy: 0.2729 - val_loss: 1.9760
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.1340
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2795 - loss: 2.0507  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2886 - loss: 2.0220
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2897 - loss: 2.0131
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2893 - loss: 2.0076
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2881 - loss: 2.0054
[1m 249/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2877 - loss: 2.0034
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2880 - loss: 2.0016
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2884 - loss: 2.0001
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2888 - loss: 1.9991
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2888 - loss: 1.9985
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2886 - loss: 1.9984
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2883 - loss: 1.9985
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2881 - loss: 1.9986
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2879 - loss: 1.9985
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2879 - loss: 1.9982
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2878 - loss: 1.9978
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2878 - loss: 1.9975
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2878 - loss: 1.9973
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2878 - loss: 1.9970
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2879 - loss: 1.9968
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2879 - loss: 1.9967
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2878 - loss: 1.9965
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2878 - loss: 1.9964
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2878 - loss: 1.9963
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2878 - loss: 1.9962
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2877 - loss: 1.9961
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2876 - loss: 1.9961
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2875 - loss: 1.9961
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2874 - loss: 1.9961 - val_accuracy: 0.2709 - val_loss: 1.9715
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.2503
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3469 - loss: 1.9743  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3338 - loss: 1.9828
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3241 - loss: 1.9871
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3165 - loss: 1.9889
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3104 - loss: 1.9919
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3065 - loss: 1.9955
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3036 - loss: 1.9976
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3011 - loss: 1.9991
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2994 - loss: 1.9994
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2977 - loss: 1.9997
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2962 - loss: 2.0000
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2951 - loss: 2.0004
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2943 - loss: 2.0004
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2935 - loss: 2.0003
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2928 - loss: 2.0001
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2923 - loss: 2.0000
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2918 - loss: 2.0001
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2913 - loss: 2.0001
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2908 - loss: 2.0001
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2905 - loss: 2.0000
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2902 - loss: 1.9998
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2899 - loss: 1.9996
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2898 - loss: 1.9995
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2896 - loss: 1.9993
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2893 - loss: 1.9992
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2891 - loss: 1.9991
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2889 - loss: 1.9989
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2888 - loss: 1.9986
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2887 - loss: 1.9985
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2887 - loss: 1.9984 - val_accuracy: 0.2790 - val_loss: 1.9735
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.6250 - loss: 1.5204
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3713 - loss: 1.8704  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3480 - loss: 1.8971
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3342 - loss: 1.9196
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3257 - loss: 1.9347
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3195 - loss: 1.9432
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3144 - loss: 1.9498
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3106 - loss: 1.9550
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3076 - loss: 1.9587
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3053 - loss: 1.9617
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3037 - loss: 1.9635
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3025 - loss: 1.9647
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3015 - loss: 1.9654
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3006 - loss: 1.9661
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2999 - loss: 1.9667
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2992 - loss: 1.9673
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2986 - loss: 1.9679
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2979 - loss: 1.9686
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2973 - loss: 1.9693
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2967 - loss: 1.9701
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2962 - loss: 1.9707
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2957 - loss: 1.9712
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2952 - loss: 1.9718
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2947 - loss: 1.9724
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2943 - loss: 1.9729
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2939 - loss: 1.9734
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2936 - loss: 1.9740
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2933 - loss: 1.9744
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2931 - loss: 1.9747
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2928 - loss: 1.9751
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2928 - loss: 1.9751 - val_accuracy: 0.2546 - val_loss: 2.0027
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 2.0165
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2299 - loss: 2.0443  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2488 - loss: 2.0202
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2569 - loss: 2.0071
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2604 - loss: 1.9994
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2621 - loss: 1.9960
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2643 - loss: 1.9929
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2660 - loss: 1.9904
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2676 - loss: 1.9885
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2689 - loss: 1.9871
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 1.9852
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 1.9834
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2725 - loss: 1.9820
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2735 - loss: 1.9808
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 1.9797
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2753 - loss: 1.9789
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 1.9781
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2765 - loss: 1.9775
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2769 - loss: 1.9769
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2773 - loss: 1.9766
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 1.9763
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2779 - loss: 1.9762
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2781 - loss: 1.9761
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2784 - loss: 1.9759
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2786 - loss: 1.9759
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2788 - loss: 1.9759
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2791 - loss: 1.9759
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2793 - loss: 1.9759
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 1.9760
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2797 - loss: 1.9760
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2797 - loss: 1.9760 - val_accuracy: 0.2668 - val_loss: 1.9844

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 642ms/step
[1m61/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 842us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:21[0m 861ms/step
[1m 69/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 741us/step  
[1m144/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 707us/step
[1m214/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 712us/step
[1m282/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 720us/step
[1m349/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 726us/step
[1m423/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 717us/step
[1m496/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 713us/step
[1m562/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 718us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m64/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 798us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 66/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 775us/step
[1m138/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 734us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 26.98 [%]
Global F1 score (validation) = 23.53 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.06069656 0.06558673 0.05206281 ... 0.01238751 0.04757709 0.00768565]
 [0.13226517 0.1599915  0.11688887 ... 0.00447617 0.13238235 0.0130777 ]
 [0.11998855 0.16906029 0.09674133 ... 0.00485489 0.13333887 0.01253779]
 ...
 [0.13231933 0.13341485 0.08381958 ... 0.00531636 0.13455099 0.01573481]
 [0.2056413  0.21441607 0.11697605 ... 0.00035449 0.1494188  0.04800899]
 [0.16595212 0.19356428 0.10334803 ... 0.00276173 0.15812995 0.01539991]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 30.88 [%]
Global accuracy score (test) = 25.94 [%]
Global F1 score (train) = 28.02 [%]
Global F1 score (test) = 23.73 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.07      0.03      0.04       184
 CAMINAR CON MÓVIL O LIBRO       0.20      0.42      0.27       184
       CAMINAR USUAL SPEED       0.00      0.00      0.00       184
            CAMINAR ZIGZAG       0.15      0.24      0.18       184
          DE PIE BARRIENDO       0.16      0.43      0.24       184
   DE PIE DOBLANDO TOALLAS       0.24      0.15      0.19       184
    DE PIE MOVIENDO LIBROS       0.19      0.19      0.19       184
          DE PIE USANDO PC       0.29      0.76      0.42       184
        FASE REPOSO CON K5       0.87      0.62      0.73       184
INCREMENTAL CICLOERGOMETRO       0.33      0.17      0.23       184
           SENTADO LEYENDO       0.25      0.09      0.13       184
         SENTADO USANDO PC       0.20      0.09      0.12       184
      SENTADO VIENDO LA TV       0.29      0.38      0.33       184
   SUBIR Y BAJAR ESCALERAS       0.20      0.05      0.09       184
                    TROTAR       0.98      0.26      0.41       161

                  accuracy                           0.26      2737
                 macro avg       0.29      0.26      0.24      2737
              weighted avg       0.29      0.26      0.24      2737


Accuracy capturado en la ejecución 7: 25.94 [%]
F1-score capturado en la ejecución 7: 23.73 [%]

=== EJECUCIÓN 8 ===

--- TRAIN (ejecución 8) ---

--- TEST (ejecución 8) ---
2025-11-07 14:14:38.086921: 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 14:14:38.098444: 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 00:00:1762521278.111713 2937980 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762521278.115748 2937980 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762521278.125684 2937980 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521278.125702 2937980 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521278.125703 2937980 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521278.125705 2937980 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:14:38.128857: 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 00:00:1762521280.412341 2937980 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762521281.928603 2938098 service.cc:152] XLA service 0x739e8400cec0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762521281.928629 2938098 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:14:41.955454: 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 00:00:1762521282.101531 2938098 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762521283.560526 2938098 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m48:45[0m 3s/step - accuracy: 0.0000e+00 - loss: 3.5327
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0561 - loss: 3.3198      
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0589 - loss: 3.3177
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0616 - loss: 3.3063
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0636 - loss: 3.2951
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0650 - loss: 3.2854
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0663 - loss: 3.2762
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0678 - loss: 3.2665
[1m 306/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0694 - loss: 3.2556
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0712 - loss: 3.2423
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0725 - loss: 3.2317
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0738 - loss: 3.2206
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0750 - loss: 3.2093
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0761 - loss: 3.1982
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0769 - loss: 3.1893
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0778 - loss: 3.1803
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0786 - loss: 3.1721
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0792 - loss: 3.1642
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0799 - loss: 3.1564
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0805 - loss: 3.1490
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0810 - loss: 3.1429
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0815 - loss: 3.1365
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0819 - loss: 3.1301
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0824 - loss: 3.1237
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0828 - loss: 3.1179
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0833 - loss: 3.1117
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0837 - loss: 3.1063
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0841 - loss: 3.1010
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0845 - loss: 3.0962
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0850 - loss: 3.0905
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0854 - loss: 3.0862
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0854 - loss: 3.0861 - val_accuracy: 0.1325 - val_loss: 2.5817
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.0625 - loss: 2.7646
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1279 - loss: 2.6802  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1277 - loss: 2.6899
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1263 - loss: 2.6991
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1258 - loss: 2.7024
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1260 - loss: 2.7045
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1263 - loss: 2.7054
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1262 - loss: 2.7049
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1258 - loss: 2.7046
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1256 - loss: 2.7044
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1253 - loss: 2.7046
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1253 - loss: 2.7045
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1254 - loss: 2.7040
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1255 - loss: 2.7035
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1257 - loss: 2.7028
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1260 - loss: 2.7018
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1264 - loss: 2.7004
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1267 - loss: 2.6993
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1270 - loss: 2.6980
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1274 - loss: 2.6967
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1278 - loss: 2.6952
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1281 - loss: 2.6939
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1286 - loss: 2.6923
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1290 - loss: 2.6911
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1294 - loss: 2.6896
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1298 - loss: 2.6883
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1301 - loss: 2.6870
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1305 - loss: 2.6857
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1308 - loss: 2.6844
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1312 - loss: 2.6831
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1313 - loss: 2.6825 - val_accuracy: 0.2091 - val_loss: 2.4751
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.2647
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1630 - loss: 2.5373  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1605 - loss: 2.5648
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1597 - loss: 2.5668
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1597 - loss: 2.5629
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1596 - loss: 2.5617
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1596 - loss: 2.5616
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1600 - loss: 2.5606
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1604 - loss: 2.5595
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1605 - loss: 2.5586
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1605 - loss: 2.5578
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1605 - loss: 2.5568
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1605 - loss: 2.5559
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1606 - loss: 2.5551
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1609 - loss: 2.5541
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1613 - loss: 2.5531
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1617 - loss: 2.5519
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1620 - loss: 2.5508
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1624 - loss: 2.5497
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1627 - loss: 2.5486
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1630 - loss: 2.5476
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1633 - loss: 2.5466
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1636 - loss: 2.5456
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1639 - loss: 2.5447
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1642 - loss: 2.5436
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1644 - loss: 2.5426
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1647 - loss: 2.5417
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1649 - loss: 2.5407
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1652 - loss: 2.5396
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1655 - loss: 2.5387
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1656 - loss: 2.5384 - val_accuracy: 0.2081 - val_loss: 2.3751
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.4080
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1914 - loss: 2.4690  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1883 - loss: 2.4688
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1872 - loss: 2.4654
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1864 - loss: 2.4642
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1854 - loss: 2.4636
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1847 - loss: 2.4620
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1847 - loss: 2.4601
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1849 - loss: 2.4582
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1851 - loss: 2.4568
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1853 - loss: 2.4555
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1857 - loss: 2.4542
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1860 - loss: 2.4531
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1863 - loss: 2.4519
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1864 - loss: 2.4509
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1865 - loss: 2.4501
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1866 - loss: 2.4494
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1868 - loss: 2.4486
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1871 - loss: 2.4478
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1873 - loss: 2.4469
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1875 - loss: 2.4460
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1877 - loss: 2.4451
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1879 - loss: 2.4443
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1881 - loss: 2.4435
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1882 - loss: 2.4426
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1884 - loss: 2.4418
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1886 - loss: 2.4410
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1887 - loss: 2.4402
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1889 - loss: 2.4394
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1890 - loss: 2.4389 - val_accuracy: 0.2115 - val_loss: 2.3111
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.2148
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2115 - loss: 2.3676  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2073 - loss: 2.3674
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2030 - loss: 2.3676
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2015 - loss: 2.3675
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1995 - loss: 2.3691
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1982 - loss: 2.3703
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1980 - loss: 2.3698
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1984 - loss: 2.3687
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1992 - loss: 2.3674
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2001 - loss: 2.3659
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2007 - loss: 2.3645
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2013 - loss: 2.3634
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2018 - loss: 2.3624
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2023 - loss: 2.3615
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2027 - loss: 2.3608
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2030 - loss: 2.3603
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2032 - loss: 2.3599
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2034 - loss: 2.3596
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2037 - loss: 2.3593
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2039 - loss: 2.3589
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2040 - loss: 2.3587
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2042 - loss: 2.3584
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2043 - loss: 2.3580
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2045 - loss: 2.3576
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2047 - loss: 2.3572
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2049 - loss: 2.3568
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2050 - loss: 2.3563
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2052 - loss: 2.3558
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2054 - loss: 2.3554
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2055 - loss: 2.3549 - val_accuracy: 0.2313 - val_loss: 2.2506
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.1469
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2203 - loss: 2.2626  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2145 - loss: 2.2805
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2115 - loss: 2.2861
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2102 - loss: 2.2898
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2096 - loss: 2.2923
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2092 - loss: 2.2946
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2089 - loss: 2.2966
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2089 - loss: 2.2980
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2088 - loss: 2.2988
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2088 - loss: 2.2989
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2089 - loss: 2.2990
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2088 - loss: 2.2991
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2088 - loss: 2.2991
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2089 - loss: 2.2989
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2091 - loss: 2.2987
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2093 - loss: 2.2984
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2096 - loss: 2.2981
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2099 - loss: 2.2977
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2103 - loss: 2.2973
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2107 - loss: 2.2970
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2110 - loss: 2.2966
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2113 - loss: 2.2963
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2116 - loss: 2.2960
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2119 - loss: 2.2958
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2122 - loss: 2.2955
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2125 - loss: 2.2952
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2127 - loss: 2.2950
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2129 - loss: 2.2947
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2131 - loss: 2.2945
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2132 - loss: 2.2944 - val_accuracy: 0.2313 - val_loss: 2.1836
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3125 - loss: 2.2295
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2684 - loss: 2.2160  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2506 - loss: 2.2410
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2439 - loss: 2.2544
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2401 - loss: 2.2602
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2372 - loss: 2.2630
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2349 - loss: 2.2647
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2331 - loss: 2.2656
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2320 - loss: 2.2652
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2313 - loss: 2.2644
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2308 - loss: 2.2633
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2303 - loss: 2.2620
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2300 - loss: 2.2607
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2298 - loss: 2.2594
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2295 - loss: 2.2583
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2293 - loss: 2.2574
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2292 - loss: 2.2566
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2291 - loss: 2.2558
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2290 - loss: 2.2551
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2289 - loss: 2.2544
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2288 - loss: 2.2539
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2287 - loss: 2.2533
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2286 - loss: 2.2529
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2285 - loss: 2.2524
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2284 - loss: 2.2519
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2283 - loss: 2.2515
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2512
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2280 - loss: 2.2507
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2279 - loss: 2.2503
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2278 - loss: 2.2498
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2277 - loss: 2.2496 - val_accuracy: 0.2302 - val_loss: 2.1386
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.9489
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2380 - loss: 2.1717  
[1m  71/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2298 - loss: 2.1975
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2298 - loss: 2.2022
[1m 148/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2053
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2269 - loss: 2.2076
[1m 227/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2260 - loss: 2.2099
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2252 - loss: 2.2123
[1m 305/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2246 - loss: 2.2138
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2242 - loss: 2.2151
[1m 386/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2237 - loss: 2.2160
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2235 - loss: 2.2165
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2233 - loss: 2.2168
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2233 - loss: 2.2171
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2236 - loss: 2.2170
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2239 - loss: 2.2168
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2241 - loss: 2.2166
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2243 - loss: 2.2165
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2245 - loss: 2.2163
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2248 - loss: 2.2161
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2252 - loss: 2.2158
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2255 - loss: 2.2154
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2258 - loss: 2.2150
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2260 - loss: 2.2148
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2263 - loss: 2.2146
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2265 - loss: 2.2144
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2267 - loss: 2.2141
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2268 - loss: 2.2138
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2270 - loss: 2.2135
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2272 - loss: 2.2132
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2273 - loss: 2.2129
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2273 - loss: 2.2128 - val_accuracy: 0.2444 - val_loss: 2.1220
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.0000e+00 - loss: 2.1137
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2245 - loss: 2.1356      
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2314 - loss: 2.1559
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2350 - loss: 2.1629
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2369 - loss: 2.1643
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2382 - loss: 2.1650
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2398 - loss: 2.1661
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2412 - loss: 2.1664
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2420 - loss: 2.1670
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2424 - loss: 2.1675
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2423 - loss: 2.1684
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2423 - loss: 2.1693
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2422 - loss: 2.1701
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2422 - loss: 2.1709
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2422 - loss: 2.1716
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2421 - loss: 2.1723
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2422 - loss: 2.1729
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2421 - loss: 2.1735
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2422 - loss: 2.1740
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2421 - loss: 2.1744
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2421 - loss: 2.1748
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2420 - loss: 2.1751
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2421 - loss: 2.1754
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2421 - loss: 2.1756
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2421 - loss: 2.1759
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2420 - loss: 2.1761
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2420 - loss: 2.1764
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2420 - loss: 2.1766
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1768
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1769
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2418 - loss: 2.1769 - val_accuracy: 0.2444 - val_loss: 2.0890
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.1624
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2319 - loss: 2.1487  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2318 - loss: 2.1470
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2318 - loss: 2.1519
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2327 - loss: 2.1539
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2329 - loss: 2.1547
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2330 - loss: 2.1541
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2335 - loss: 2.1538
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2340 - loss: 2.1528
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2345 - loss: 2.1521
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2350 - loss: 2.1514
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2356 - loss: 2.1506
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2361 - loss: 2.1503
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2363 - loss: 2.1502
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2364 - loss: 2.1504
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2365 - loss: 2.1506
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2366 - loss: 2.1509
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2369 - loss: 2.1508
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2372 - loss: 2.1508
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2375 - loss: 2.1507
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2377 - loss: 2.1505
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2379 - loss: 2.1504
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2381 - loss: 2.1503
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2383 - loss: 2.1503
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2384 - loss: 2.1502
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2386 - loss: 2.1502
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2388 - loss: 2.1502
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2390 - loss: 2.1501
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2391 - loss: 2.1501
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2392 - loss: 2.1501
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2392 - loss: 2.1502 - val_accuracy: 0.2470 - val_loss: 2.0948
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 29ms/step - accuracy: 0.1250 - loss: 2.3633
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2041 - loss: 2.1686  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2171 - loss: 2.1637
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2257 - loss: 2.1525
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2331 - loss: 2.1437
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2376 - loss: 2.1390
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2416 - loss: 2.1340
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2447 - loss: 2.1300
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2468 - loss: 2.1279
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2482 - loss: 2.1264
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2493 - loss: 2.1248
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2504 - loss: 2.1237
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2511 - loss: 2.1230
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2516 - loss: 2.1225
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2521 - loss: 2.1221
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2525 - loss: 2.1217
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.1215
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2529 - loss: 2.1215
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2529 - loss: 2.1216
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2530 - loss: 2.1217
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2530 - loss: 2.1218
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2531 - loss: 2.1219
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2531 - loss: 2.1221
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2531 - loss: 2.1222
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2531 - loss: 2.1224
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2530 - loss: 2.1226
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2529 - loss: 2.1229
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2529 - loss: 2.1231
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.1232
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.1233
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2527 - loss: 2.1233 - val_accuracy: 0.2346 - val_loss: 2.0704
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.2293
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2576 - loss: 2.1301  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2588 - loss: 2.1292
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2604 - loss: 2.1243
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2603 - loss: 2.1255
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2598 - loss: 2.1273
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2594 - loss: 2.1287
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2592 - loss: 2.1291
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2588 - loss: 2.1292
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2586 - loss: 2.1288
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2585 - loss: 2.1281
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2586 - loss: 2.1272
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2586 - loss: 2.1264
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2586 - loss: 2.1256
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2586 - loss: 2.1250
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2587 - loss: 2.1243
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2588 - loss: 2.1236
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2590 - loss: 2.1229
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2591 - loss: 2.1223
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2592 - loss: 2.1217
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2593 - loss: 2.1213
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2592 - loss: 2.1209
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2592 - loss: 2.1205
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2591 - loss: 2.1202
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2591 - loss: 2.1198
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2590 - loss: 2.1194
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2588 - loss: 2.1191
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2587 - loss: 2.1189
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2585 - loss: 2.1188
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2584 - loss: 2.1186
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2583 - loss: 2.1185 - val_accuracy: 0.2427 - val_loss: 2.0527
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.2864
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2422 - loss: 2.0991  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2514 - loss: 2.0940
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2520 - loss: 2.0892
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2528 - loss: 2.0886
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2540 - loss: 2.0883
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2547 - loss: 2.0878
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2550 - loss: 2.0883
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2554 - loss: 2.0880
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2558 - loss: 2.0878
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2562 - loss: 2.0877
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0879
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0880
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2564 - loss: 2.0880
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.0881
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0882
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0884
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0885
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2570 - loss: 2.0884
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0884
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0883
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2574 - loss: 2.0883
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2575 - loss: 2.0883
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2576 - loss: 2.0883
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.0883
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.0883
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2580 - loss: 2.0883
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0883
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0885
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2582 - loss: 2.0886 - val_accuracy: 0.2557 - val_loss: 2.0228
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.9872
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2785 - loss: 2.0270  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0574
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2615 - loss: 2.0681
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2601 - loss: 2.0741
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2598 - loss: 2.0778
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0796
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0803
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2614 - loss: 2.0810
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2615 - loss: 2.0813
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2614 - loss: 2.0813
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2617 - loss: 2.0812
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2618 - loss: 2.0813
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2617 - loss: 2.0816
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2615 - loss: 2.0820
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0823
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2607 - loss: 2.0828
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0833
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2600 - loss: 2.0837
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2597 - loss: 2.0840
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2595 - loss: 2.0843
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2592 - loss: 2.0846
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2590 - loss: 2.0849
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2587 - loss: 2.0853
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2585 - loss: 2.0857
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2584 - loss: 2.0859
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2582 - loss: 2.0862
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2582 - loss: 2.0864
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0866
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2581 - loss: 2.0867 - val_accuracy: 0.2592 - val_loss: 2.0161
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.1060
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2801 - loss: 2.0938  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2764 - loss: 2.0818
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0800
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2720 - loss: 2.0808
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0824
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2680 - loss: 2.0828
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0826
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0827
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0828
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0829
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0827
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2627 - loss: 2.0823
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2624 - loss: 2.0817
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2622 - loss: 2.0812
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2618 - loss: 2.0807
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2616 - loss: 2.0804
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2612 - loss: 2.0803
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0803
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2607 - loss: 2.0802
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0801
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0801
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2601 - loss: 2.0801
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0801
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0800
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0799
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0797
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2598 - loss: 2.0796
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2598 - loss: 2.0795
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2598 - loss: 2.0794
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2598 - loss: 2.0793 - val_accuracy: 0.2548 - val_loss: 2.0224
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.3750 - loss: 2.0347
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2844 - loss: 2.0495  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0669
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0707
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2641 - loss: 2.0721
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2640 - loss: 2.0722
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2638 - loss: 2.0721
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0712
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0700
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2646 - loss: 2.0692
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0687
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0680
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0674
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2654 - loss: 2.0667
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0659
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0650
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0642
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0634
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0628
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0623
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0620
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0617
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0614
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0612
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0611
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0611
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0611
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0611
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0611
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0611
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2665 - loss: 2.0612 - val_accuracy: 0.2599 - val_loss: 1.9812
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.4375 - loss: 2.0398
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3017 - loss: 2.0545  
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2857 - loss: 2.0502
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2782 - loss: 2.0484
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0456
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0472
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0482
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2725 - loss: 2.0491
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2719 - loss: 2.0494
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0491
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0489
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0483
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0480
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2705 - loss: 2.0477
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0473
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0467
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2697 - loss: 2.0464
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0462
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2690 - loss: 2.0461
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0460
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2684 - loss: 2.0461
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0461
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2678 - loss: 2.0462
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0461
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0460
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0459
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0458
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0458
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0457
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0456
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2668 - loss: 2.0456 - val_accuracy: 0.2807 - val_loss: 2.0079
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.9114
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0415  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0326
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0321
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0319
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0315
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2626 - loss: 2.0305
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2626 - loss: 2.0293
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0279
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2634 - loss: 2.0270
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2638 - loss: 2.0265
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0262
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2647 - loss: 2.0259
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0257
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0260
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0263
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0264
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0266
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0268
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0269
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0270
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0272
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0273
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0275
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0275
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0276
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0277
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0278
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0281
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0283
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2670 - loss: 2.0285 - val_accuracy: 0.2757 - val_loss: 1.9895
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.0017
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2311 - loss: 2.1166  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2415 - loss: 2.0900
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2513 - loss: 2.0745
[1m 170/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2554 - loss: 2.0648
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2574 - loss: 2.0596
[1m 251/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2590 - loss: 2.0551
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2600 - loss: 2.0512
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2608 - loss: 2.0490
[1m 377/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2614 - loss: 2.0473
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2620 - loss: 2.0458
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2627 - loss: 2.0443
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0428
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0415
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0405
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0398
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2646 - loss: 2.0391
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2648 - loss: 2.0385
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0379
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0374
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0371
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0369
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0366
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0363
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0361
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0359
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2654 - loss: 2.0357
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0355
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0353
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0350
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2658 - loss: 2.0350 - val_accuracy: 0.2685 - val_loss: 1.9847
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.1384
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2199 - loss: 2.0317  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2401 - loss: 2.0023
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2456 - loss: 2.0018
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2478 - loss: 2.0062
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2500 - loss: 2.0086
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2525 - loss: 2.0085
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2549 - loss: 2.0077
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0073
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0076
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2580 - loss: 2.0078
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2590 - loss: 2.0084
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2597 - loss: 2.0089
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0094
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2607 - loss: 2.0099
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0102
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2615 - loss: 2.0106
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2619 - loss: 2.0109
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2623 - loss: 2.0111
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2627 - loss: 2.0113
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0115
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0117
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0119
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0122
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2641 - loss: 2.0124
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0125
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2647 - loss: 2.0126
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0126
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0127
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0128
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2657 - loss: 2.0128 - val_accuracy: 0.2825 - val_loss: 1.9708
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.8556
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2794 - loss: 2.0033  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2794 - loss: 2.0006
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2798 - loss: 1.9966
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9956
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2810 - loss: 1.9955
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2807 - loss: 1.9954
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2804 - loss: 1.9953
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2801 - loss: 1.9953
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2798 - loss: 1.9958
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 1.9967
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2794 - loss: 1.9972
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2792 - loss: 1.9979
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2791 - loss: 1.9986
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2790 - loss: 1.9993
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9998
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2787 - loss: 2.0002
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2786 - loss: 2.0005
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2786 - loss: 2.0005
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2786 - loss: 2.0006
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2786 - loss: 2.0009
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2785 - loss: 2.0011
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2784 - loss: 2.0012
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2784 - loss: 2.0014
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2783 - loss: 2.0015
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2783 - loss: 2.0016
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2782 - loss: 2.0018
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2781 - loss: 2.0020
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2780 - loss: 2.0022
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2779 - loss: 2.0024
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2779 - loss: 2.0026 - val_accuracy: 0.2890 - val_loss: 1.9676
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.0822
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2345 - loss: 2.0858  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2494 - loss: 2.0553
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2549 - loss: 2.0368
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2582 - loss: 2.0256
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2607 - loss: 2.0182
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2625 - loss: 2.0138
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0098
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0063
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0045
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2678 - loss: 2.0034
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0029
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2684 - loss: 2.0026
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0021
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2690 - loss: 2.0015
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0011
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 2.0008
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0004
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0003
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2705 - loss: 2.0001
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 1.9998
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 1.9996
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2714 - loss: 1.9995
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 1.9994
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2718 - loss: 1.9992
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2720 - loss: 1.9991
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2722 - loss: 1.9990
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2725 - loss: 1.9989
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2726 - loss: 1.9987
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2728 - loss: 1.9986
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2729 - loss: 1.9986 - val_accuracy: 0.2810 - val_loss: 1.9716
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.1875 - loss: 1.9950
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3071 - loss: 1.9163  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3093 - loss: 1.9295
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3059 - loss: 1.9367
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3020 - loss: 1.9445
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3003 - loss: 1.9492
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2994 - loss: 1.9515
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2981 - loss: 1.9541
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2967 - loss: 1.9566
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2956 - loss: 1.9587
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2944 - loss: 1.9607
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2933 - loss: 1.9627
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2924 - loss: 1.9646
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2917 - loss: 1.9659
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2909 - loss: 1.9674
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2900 - loss: 1.9688
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2893 - loss: 1.9700
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2885 - loss: 1.9714
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2878 - loss: 1.9725
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2873 - loss: 1.9734
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2868 - loss: 1.9740
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2864 - loss: 1.9746
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2860 - loss: 1.9751
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2857 - loss: 1.9754
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2855 - loss: 1.9758
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2852 - loss: 1.9762
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2850 - loss: 1.9766
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2847 - loss: 1.9770
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2845 - loss: 1.9773
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2843 - loss: 1.9776
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2842 - loss: 1.9777 - val_accuracy: 0.2683 - val_loss: 1.9511
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.7704
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2560 - loss: 1.9967  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2608 - loss: 2.0030
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2634 - loss: 1.9996
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2643 - loss: 1.9985
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2659 - loss: 1.9977
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2679 - loss: 1.9972
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2694 - loss: 1.9959
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2709 - loss: 1.9941
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2723 - loss: 1.9925
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2733 - loss: 1.9916
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 1.9908
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2753 - loss: 1.9899
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 1.9893
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2763 - loss: 1.9891
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2766 - loss: 1.9890
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2768 - loss: 1.9889
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2769 - loss: 1.9890
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2770 - loss: 1.9891
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2772 - loss: 1.9893
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2774 - loss: 1.9894
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 1.9895
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2777 - loss: 1.9896
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 1.9899
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2777 - loss: 1.9899
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2777 - loss: 1.9898
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2777 - loss: 1.9897
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2778 - loss: 1.9896
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2778 - loss: 1.9896
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2778 - loss: 1.9895
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2778 - loss: 1.9895 - val_accuracy: 0.2772 - val_loss: 1.9339
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 2.2969
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3114 - loss: 1.9456  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2966 - loss: 1.9506
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2905 - loss: 1.9536
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2881 - loss: 1.9578
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2870 - loss: 1.9601
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2858 - loss: 1.9634
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2849 - loss: 1.9660
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2849 - loss: 1.9677
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2851 - loss: 1.9686
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2853 - loss: 1.9696
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2855 - loss: 1.9704
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2855 - loss: 1.9712
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2854 - loss: 1.9717
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2854 - loss: 1.9721
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2853 - loss: 1.9726
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2852 - loss: 1.9728
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2851 - loss: 1.9729
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2850 - loss: 1.9729
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2848 - loss: 1.9730
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2847 - loss: 1.9730
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2846 - loss: 1.9730
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2845 - loss: 1.9730
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2844 - loss: 1.9730
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2843 - loss: 1.9729
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2843 - loss: 1.9727
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2842 - loss: 1.9726
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2841 - loss: 1.9725
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2841 - loss: 1.9724
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2840 - loss: 1.9723
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2840 - loss: 1.9723 - val_accuracy: 0.2707 - val_loss: 1.9545

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 633ms/step
[1m69/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 750us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7:58[0m 821ms/step
[1m 68/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 755us/step  
[1m141/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 719us/step
[1m210/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 722us/step
[1m278/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 725us/step
[1m343/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 734us/step
[1m413/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 732us/step
[1m479/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 736us/step
[1m551/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 732us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m64/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 795us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 73/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 703us/step
[1m141/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 722us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 26.68 [%]
Global F1 score (validation) = 24.23 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.16328897 0.20674764 0.17721759 ... 0.00203954 0.10533839 0.01644297]
 [0.1604295  0.19222507 0.2031182  ... 0.00158421 0.1210826  0.01741193]
 [0.21047525 0.20432788 0.18384351 ... 0.00092602 0.12143259 0.02488292]
 ...
 [0.1437708  0.17568195 0.15724625 ... 0.00284864 0.14111735 0.02277333]
 [0.15486512 0.18993925 0.1522279  ... 0.00263204 0.12728982 0.0201969 ]
 [0.10250928 0.17427954 0.08745578 ... 0.01020587 0.08101545 0.01389404]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 29.95 [%]
Global accuracy score (test) = 23.64 [%]
Global F1 score (train) = 27.45 [%]
Global F1 score (test) = 21.15 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.10      0.02      0.03       184
 CAMINAR CON MÓVIL O LIBRO       0.16      0.46      0.24       184
       CAMINAR USUAL SPEED       0.14      0.09      0.11       184
            CAMINAR ZIGZAG       0.05      0.03      0.04       184
          DE PIE BARRIENDO       0.17      0.49      0.25       184
   DE PIE DOBLANDO TOALLAS       0.23      0.09      0.13       184
    DE PIE MOVIENDO LIBROS       0.27      0.17      0.21       184
          DE PIE USANDO PC       0.23      0.79      0.36       184
        FASE REPOSO CON K5       0.78      0.62      0.69       184
INCREMENTAL CICLOERGOMETRO       0.53      0.14      0.22       184
           SENTADO LEYENDO       0.16      0.14      0.15       184
         SENTADO USANDO PC       0.11      0.08      0.09       184
      SENTADO VIENDO LA TV       0.38      0.12      0.19       184
   SUBIR Y BAJAR ESCALERAS       0.00      0.00      0.00       184
                    TROTAR       0.98      0.30      0.46       161

                  accuracy                           0.24      2737
                 macro avg       0.29      0.24      0.21      2737
              weighted avg       0.28      0.24      0.21      2737


Accuracy capturado en la ejecución 8: 23.64 [%]
F1-score capturado en la ejecución 8: 21.15 [%]

=== EJECUCIÓN 9 ===

--- TRAIN (ejecución 9) ---

--- TEST (ejecución 9) ---
2025-11-07 14:15:45.957834: 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 14:15:45.969294: 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 00:00:1762521345.982695 2941728 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762521345.986880 2941728 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762521345.996704 2941728 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521345.996731 2941728 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521345.996733 2941728 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521345.996734 2941728 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:15:45.999850: 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 00:00:1762521348.290132 2941728 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762521349.793314 2941858 service.cc:152] XLA service 0x7c2ac800b170 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762521349.793363 2941858 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:15:49.828274: 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 00:00:1762521349.981771 2941858 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762521351.405073 2941858 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m48:03[0m 2s/step - accuracy: 0.1250 - loss: 3.1008
[1m  32/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0703 - loss: 3.1501  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0674 - loss: 3.1580
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0689 - loss: 3.1522
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0710 - loss: 3.1464
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0723 - loss: 3.1403
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0739 - loss: 3.1326
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0751 - loss: 3.1258
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0764 - loss: 3.1179
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0776 - loss: 3.1101
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0787 - loss: 3.1038
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0795 - loss: 3.0988
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0801 - loss: 3.0940
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0809 - loss: 3.0891
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0815 - loss: 3.0841
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0820 - loss: 3.0797
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0825 - loss: 3.0754
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0830 - loss: 3.0712
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0834 - loss: 3.0670
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0839 - loss: 3.0629
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0843 - loss: 3.0584
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0847 - loss: 3.0541
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0851 - loss: 3.0498
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0855 - loss: 3.0456
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0858 - loss: 3.0417
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0862 - loss: 3.0380
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0865 - loss: 3.0336
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0869 - loss: 3.0296
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0872 - loss: 3.0258
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0874 - loss: 3.0237
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0874 - loss: 3.0236 - val_accuracy: 0.1545 - val_loss: 2.6069
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.6680
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1408 - loss: 2.7013  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1356 - loss: 2.7128
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1326 - loss: 2.7168
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1314 - loss: 2.7212
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1306 - loss: 2.7224
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1301 - loss: 2.7229
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1301 - loss: 2.7219
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1301 - loss: 2.7209
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1302 - loss: 2.7200
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1304 - loss: 2.7186
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1307 - loss: 2.7171
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1310 - loss: 2.7155
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1313 - loss: 2.7139
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1316 - loss: 2.7121
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1320 - loss: 2.7104
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1324 - loss: 2.7089
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1329 - loss: 2.7073
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1333 - loss: 2.7056
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1337 - loss: 2.7042
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1341 - loss: 2.7026
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1345 - loss: 2.7009
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1349 - loss: 2.6993
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1354 - loss: 2.6975
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1359 - loss: 2.6956
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1363 - loss: 2.6941
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1367 - loss: 2.6923
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1371 - loss: 2.6907
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1374 - loss: 2.6892
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1378 - loss: 2.6878 - val_accuracy: 0.1874 - val_loss: 2.4664
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.8166
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1611 - loss: 2.5617  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1728 - loss: 2.5420
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1746 - loss: 2.5340
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1740 - loss: 2.5334
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1735 - loss: 2.5328
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1732 - loss: 2.5325
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1728 - loss: 2.5329
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1727 - loss: 2.5326
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1730 - loss: 2.5313
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1733 - loss: 2.5300
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1734 - loss: 2.5290
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1736 - loss: 2.5281
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1738 - loss: 2.5272
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1740 - loss: 2.5261
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1742 - loss: 2.5250
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1744 - loss: 2.5239
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1745 - loss: 2.5229
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1747 - loss: 2.5219
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1748 - loss: 2.5210
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1749 - loss: 2.5201
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1751 - loss: 2.5193
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1752 - loss: 2.5184
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1754 - loss: 2.5176
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1755 - loss: 2.5168
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1757 - loss: 2.5160
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1759 - loss: 2.5151
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1761 - loss: 2.5143
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1763 - loss: 2.5133
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1764 - loss: 2.5128 - val_accuracy: 0.2059 - val_loss: 2.3673
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.4124
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1904 - loss: 2.4209  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1929 - loss: 2.4258
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1932 - loss: 2.4279
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1934 - loss: 2.4311
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1931 - loss: 2.4320
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1929 - loss: 2.4321
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1922 - loss: 2.4327
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1913 - loss: 2.4329
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1906 - loss: 2.4331
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1900 - loss: 2.4330
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1897 - loss: 2.4326
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1893 - loss: 2.4321
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1890 - loss: 2.4318
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1887 - loss: 2.4314
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1887 - loss: 2.4306
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1887 - loss: 2.4299
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1887 - loss: 2.4292
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1889 - loss: 2.4282
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1890 - loss: 2.4271
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1892 - loss: 2.4261
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1892 - loss: 2.4252
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1893 - loss: 2.4243
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1894 - loss: 2.4235
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1895 - loss: 2.4225
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1897 - loss: 2.4215
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1898 - loss: 2.4206
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1900 - loss: 2.4197
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1901 - loss: 2.4190
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1903 - loss: 2.4182
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1903 - loss: 2.4180 - val_accuracy: 0.2126 - val_loss: 2.2868
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.3636
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2123 - loss: 2.3422  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2101 - loss: 2.3514
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2058 - loss: 2.3532
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2049 - loss: 2.3529
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2047 - loss: 2.3525
[1m 251/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2048 - loss: 2.3520
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2046 - loss: 2.3512
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2047 - loss: 2.3503
[1m 381/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2044 - loss: 2.3496
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2042 - loss: 2.3490
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2038 - loss: 2.3486
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2035 - loss: 2.3481
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2033 - loss: 2.3477
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2029 - loss: 2.3473
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2027 - loss: 2.3471
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2025 - loss: 2.3468
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2024 - loss: 2.3463
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2025 - loss: 2.3458
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2026 - loss: 2.3453
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2027 - loss: 2.3448
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2028 - loss: 2.3444
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2029 - loss: 2.3439
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2031 - loss: 2.3433
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2033 - loss: 2.3428
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2034 - loss: 2.3422
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2036 - loss: 2.3418
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2037 - loss: 2.3414
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2039 - loss: 2.3408
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2039 - loss: 2.3407 - val_accuracy: 0.2389 - val_loss: 2.2296
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.2894
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2189 - loss: 2.3200  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2167 - loss: 2.3175
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2161 - loss: 2.3135
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2170 - loss: 2.3098
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2172 - loss: 2.3076
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2174 - loss: 2.3061
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2171 - loss: 2.3055
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2165 - loss: 2.3050
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2158 - loss: 2.3046
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2152 - loss: 2.3041
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2149 - loss: 2.3033
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2145 - loss: 2.3024
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2144 - loss: 2.3012
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2144 - loss: 2.2999
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2144 - loss: 2.2987
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2145 - loss: 2.2975
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2146 - loss: 2.2963
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2146 - loss: 2.2952
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2147 - loss: 2.2942
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2147 - loss: 2.2935
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2148 - loss: 2.2926
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2149 - loss: 2.2919
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2150 - loss: 2.2911
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2151 - loss: 2.2904
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2152 - loss: 2.2896
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2153 - loss: 2.2889
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2154 - loss: 2.2882
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2155 - loss: 2.2876
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2157 - loss: 2.2870 - val_accuracy: 0.2438 - val_loss: 2.1822
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.9264
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2404 - loss: 2.1761  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2315 - loss: 2.2106
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2286 - loss: 2.2222
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2281 - loss: 2.2274
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2285 - loss: 2.2304
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2285 - loss: 2.2329
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2286 - loss: 2.2338
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2293 - loss: 2.2338
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2300 - loss: 2.2335
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2305 - loss: 2.2331
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2310 - loss: 2.2325
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2314 - loss: 2.2320
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2317 - loss: 2.2317
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2320 - loss: 2.2314
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2322 - loss: 2.2313
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2323 - loss: 2.2312
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2323 - loss: 2.2311
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2323 - loss: 2.2311
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2322 - loss: 2.2311
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2320 - loss: 2.2310
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2320 - loss: 2.2310
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2318 - loss: 2.2308
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2317 - loss: 2.2308
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2314 - loss: 2.2308
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2313 - loss: 2.2308
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2312 - loss: 2.2307
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2311 - loss: 2.2306
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2309 - loss: 2.2306
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2309 - loss: 2.2305 - val_accuracy: 0.2431 - val_loss: 2.1559
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0134
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2479 - loss: 2.1762  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2439 - loss: 2.1973
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2424 - loss: 2.2033
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2405 - loss: 2.2056
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2392 - loss: 2.2072
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2379 - loss: 2.2092
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2370 - loss: 2.2103
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2362 - loss: 2.2113
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2355 - loss: 2.2127
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2349 - loss: 2.2137
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2344 - loss: 2.2144
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2339 - loss: 2.2150
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2336 - loss: 2.2156
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2333 - loss: 2.2160
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2330 - loss: 2.2162
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2328 - loss: 2.2162
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2325 - loss: 2.2160
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2324 - loss: 2.2157
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2323 - loss: 2.2153
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2322 - loss: 2.2150
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2322 - loss: 2.2148
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2320 - loss: 2.2145
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2320 - loss: 2.2141
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2320 - loss: 2.2137
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2319 - loss: 2.2133
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2319 - loss: 2.2128
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2319 - loss: 2.2123
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2319 - loss: 2.2119
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2318 - loss: 2.2115
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2318 - loss: 2.2114 - val_accuracy: 0.2529 - val_loss: 2.1178
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.1029
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2021 - loss: 2.2183  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2127 - loss: 2.2094
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2179 - loss: 2.2006
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2219 - loss: 2.1938
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2243 - loss: 2.1919
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2263 - loss: 2.1907
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2281 - loss: 2.1882
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2295 - loss: 2.1866
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2306 - loss: 2.1855
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2315 - loss: 2.1847
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2321 - loss: 2.1844
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2327 - loss: 2.1840
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2331 - loss: 2.1835
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2337 - loss: 2.1829
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2342 - loss: 2.1824
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2346 - loss: 2.1818
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2349 - loss: 2.1813
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2350 - loss: 2.1808
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2352 - loss: 2.1803
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2354 - loss: 2.1798
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2355 - loss: 2.1794
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2356 - loss: 2.1791
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2357 - loss: 2.1789
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2358 - loss: 2.1785
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2358 - loss: 2.1782
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2359 - loss: 2.1778
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2360 - loss: 2.1774
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2360 - loss: 2.1771
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2361 - loss: 2.1767
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2361 - loss: 2.1767 - val_accuracy: 0.2629 - val_loss: 2.0776
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.1822
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2327 - loss: 2.1773  
[1m  87/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2422 - loss: 2.1547
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2467 - loss: 2.1462
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2467 - loss: 2.1436
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2459 - loss: 2.1417
[1m 249/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2446 - loss: 2.1413
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2440 - loss: 2.1415
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2437 - loss: 2.1415
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2436 - loss: 2.1412
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2433 - loss: 2.1414
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2432 - loss: 2.1416
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2434 - loss: 2.1415
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2438 - loss: 2.1411
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2442 - loss: 2.1409
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2444 - loss: 2.1409
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2445 - loss: 2.1409
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2446 - loss: 2.1410
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2446 - loss: 2.1413
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2446 - loss: 2.1416
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2446 - loss: 2.1417
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2446 - loss: 2.1419
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2447 - loss: 2.1421
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2447 - loss: 2.1422
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2447 - loss: 2.1423
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2448 - loss: 2.1422
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2448 - loss: 2.1421
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2448 - loss: 2.1421
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2448 - loss: 2.1421
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2448 - loss: 2.1422 - val_accuracy: 0.2503 - val_loss: 2.0718
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.2868
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2485 - loss: 2.1262  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2431 - loss: 2.1420
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2426 - loss: 2.1457
[1m 170/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2426 - loss: 2.1464
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2434 - loss: 2.1461
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2445 - loss: 2.1447
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2450 - loss: 2.1440
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1434
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1431
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2450 - loss: 2.1427
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2449 - loss: 2.1425
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2450 - loss: 2.1422
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1416
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1412
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2453 - loss: 2.1405
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1398
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2456 - loss: 2.1391
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2458 - loss: 2.1384
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2460 - loss: 2.1378
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2462 - loss: 2.1373
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2464 - loss: 2.1369
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2465 - loss: 2.1365
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2467 - loss: 2.1361
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2468 - loss: 2.1357
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2469 - loss: 2.1355
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2470 - loss: 2.1351
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2471 - loss: 2.1348
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2472 - loss: 2.1345
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2473 - loss: 2.1342
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2473 - loss: 2.1342 - val_accuracy: 0.2549 - val_loss: 2.0358
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.0738
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2695 - loss: 2.0991  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2607 - loss: 2.0962
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2570 - loss: 2.1004
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2533 - loss: 2.1034
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2506 - loss: 2.1051
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2488 - loss: 2.1058
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2474 - loss: 2.1073
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2465 - loss: 2.1086
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2460 - loss: 2.1093
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2458 - loss: 2.1097
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2458 - loss: 2.1098
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1100
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1101
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2456 - loss: 2.1101
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2459 - loss: 2.1099
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2462 - loss: 2.1094
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2464 - loss: 2.1090
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2468 - loss: 2.1086
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2472 - loss: 2.1084
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2475 - loss: 2.1082
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2477 - loss: 2.1080
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2480 - loss: 2.1078
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2481 - loss: 2.1076
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2482 - loss: 2.1075
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2483 - loss: 2.1074
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2484 - loss: 2.1073
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2485 - loss: 2.1072
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2486 - loss: 2.1071
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2487 - loss: 2.1070 - val_accuracy: 0.2653 - val_loss: 2.0445
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3125 - loss: 2.6127
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2637 - loss: 2.1270  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2550 - loss: 2.1171
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2532 - loss: 2.1081
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2537 - loss: 2.1024
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2537 - loss: 2.0997
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2537 - loss: 2.0985
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2538 - loss: 2.0971
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2541 - loss: 2.0964
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2541 - loss: 2.0959
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2541 - loss: 2.0955
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2541 - loss: 2.0952
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2541 - loss: 2.0952
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2542 - loss: 2.0952
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.0951
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2545 - loss: 2.0951
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0950
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2549 - loss: 2.0949
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2550 - loss: 2.0949
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2551 - loss: 2.0950
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2551 - loss: 2.0950
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2551 - loss: 2.0948
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2552 - loss: 2.0946
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2553 - loss: 2.0944
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2554 - loss: 2.0941
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2556 - loss: 2.0938
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2557 - loss: 2.0937
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2557 - loss: 2.0935
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2558 - loss: 2.0934
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2558 - loss: 2.0933 - val_accuracy: 0.2683 - val_loss: 2.0143
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 1.9375
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2705 - loss: 2.1015  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2672 - loss: 2.1023
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2646 - loss: 2.1043
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2614 - loss: 2.1010
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2589 - loss: 2.0985
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2580 - loss: 2.0964
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2579 - loss: 2.0943
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2576 - loss: 2.0921
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0904
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.0890
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0878
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0867
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0858
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.0852
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2570 - loss: 2.0846
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0840
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0836
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0832
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0827
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2574 - loss: 2.0824
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2575 - loss: 2.0820
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.0818
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.0815
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.0813
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2580 - loss: 2.0811
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0809
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0808
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2582 - loss: 2.0808
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2582 - loss: 2.0807 - val_accuracy: 0.2683 - val_loss: 2.0244
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.2500 - loss: 2.1143
[1m  44/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2209 - loss: 2.1006  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2397 - loss: 2.0881
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2453 - loss: 2.0871
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2478 - loss: 2.0848
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2496 - loss: 2.0846
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2503 - loss: 2.0856
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2510 - loss: 2.0857
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2518 - loss: 2.0851
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2523 - loss: 2.0846
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2527 - loss: 2.0842
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2530 - loss: 2.0840
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2534 - loss: 2.0838
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2537 - loss: 2.0837
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2540 - loss: 2.0835
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.0833
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2546 - loss: 2.0831
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2549 - loss: 2.0829
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2552 - loss: 2.0827
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2555 - loss: 2.0824
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2558 - loss: 2.0819
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2562 - loss: 2.0813
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.0808
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0804
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2570 - loss: 2.0799
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0794
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2574 - loss: 2.0790
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2576 - loss: 2.0786
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.0781
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2578 - loss: 2.0780 - val_accuracy: 0.2625 - val_loss: 1.9984
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.0499
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2841 - loss: 2.0446  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2785 - loss: 2.0478
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2806 - loss: 2.0434
[1m 169/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2808 - loss: 2.0403
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2791 - loss: 2.0412
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2776 - loss: 2.0418
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2765 - loss: 2.0425
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2755 - loss: 2.0431
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0439
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0449
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0458
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0463
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2734 - loss: 2.0466
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0470
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2729 - loss: 2.0475
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2726 - loss: 2.0479
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2724 - loss: 2.0482
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2723 - loss: 2.0483
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2720 - loss: 2.0485
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0485
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0486
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0486
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2714 - loss: 2.0487
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0487
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2712 - loss: 2.0488
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0489
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0490
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0492
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2707 - loss: 2.0493 - val_accuracy: 0.2601 - val_loss: 2.0035
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.2500 - loss: 2.0162
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2495 - loss: 2.0249  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2487 - loss: 2.0221
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2486 - loss: 2.0242
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2514 - loss: 2.0240
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2543 - loss: 2.0224
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0216
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2583 - loss: 2.0222
[1m 333/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2590 - loss: 2.0234
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2593 - loss: 2.0240
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2598 - loss: 2.0244
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0249
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2606 - loss: 2.0257
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0268
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2613 - loss: 2.0277
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2616 - loss: 2.0283
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2619 - loss: 2.0288
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2622 - loss: 2.0291
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2624 - loss: 2.0295
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2626 - loss: 2.0299
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2628 - loss: 2.0303
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2629 - loss: 2.0307
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0310
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2632 - loss: 2.0312
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2634 - loss: 2.0313
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0315
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2638 - loss: 2.0317
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0319
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2640 - loss: 2.0320
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2641 - loss: 2.0321 - val_accuracy: 0.2635 - val_loss: 2.0138
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.2500 - loss: 1.9518
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0980  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0695
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0573
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0495
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0451
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0420
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0397
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2695 - loss: 2.0385
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0378
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0372
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0366
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0363
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0360
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0358
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0355
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0353
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0351
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0352
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0353
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2654 - loss: 2.0354
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2654 - loss: 2.0354
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0353
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0352
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0352
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0352
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0351
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0349
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0347
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2661 - loss: 2.0347 - val_accuracy: 0.2605 - val_loss: 1.9861
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.8586
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2975 - loss: 2.0093  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2885 - loss: 2.0153
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2841 - loss: 2.0174
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2838 - loss: 2.0195
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2838 - loss: 2.0194
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2836 - loss: 2.0194
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2835 - loss: 2.0199
[1m 333/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2826 - loss: 2.0210
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2816 - loss: 2.0220
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 2.0231
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 2.0239
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2787 - loss: 2.0247
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2778 - loss: 2.0251
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2769 - loss: 2.0258
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2762 - loss: 2.0262
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2755 - loss: 2.0264
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2751 - loss: 2.0266
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0267
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0267
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2742 - loss: 2.0266
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0265
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2738 - loss: 2.0262
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2738 - loss: 2.0259
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 2.0256
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0254
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0253
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0251
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0249
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0247
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2736 - loss: 2.0247 - val_accuracy: 0.2605 - val_loss: 1.9887
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3750 - loss: 1.8784
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2756 - loss: 2.0198  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2769 - loss: 2.0157
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2741 - loss: 2.0185
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2725 - loss: 2.0227
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2724 - loss: 2.0238
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2724 - loss: 2.0237
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0232
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0224
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0220
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0223
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0223
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2706 - loss: 2.0221
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0220
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0216
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2701 - loss: 2.0212
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0206
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0199
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2705 - loss: 2.0193
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0188
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0184
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0181
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0179
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0177
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0177
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0176
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2712 - loss: 2.0176
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2712 - loss: 2.0175
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2712 - loss: 2.0176
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2712 - loss: 2.0176 - val_accuracy: 0.2648 - val_loss: 1.9707
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.0006
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2919 - loss: 1.9406  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2854 - loss: 1.9594
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2807 - loss: 1.9730
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2776 - loss: 1.9829
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2765 - loss: 1.9881
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2758 - loss: 1.9921
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2759 - loss: 1.9949
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2764 - loss: 1.9972
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2766 - loss: 1.9992
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2765 - loss: 2.0011
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0032
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2758 - loss: 2.0050
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2757 - loss: 2.0061
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2755 - loss: 2.0072
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2753 - loss: 2.0082
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2753 - loss: 2.0088
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0094
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0097
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0099
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0100
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0100
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0098
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0096
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0094
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0093
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2753 - loss: 2.0092
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2753 - loss: 2.0092
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2753 - loss: 2.0091
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2753 - loss: 2.0091 - val_accuracy: 0.2675 - val_loss: 1.9737
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.1519
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2579 - loss: 2.0650  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0467
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2755 - loss: 2.0323
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2782 - loss: 2.0239
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2791 - loss: 2.0201
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2796 - loss: 2.0167
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2801 - loss: 2.0136
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2803 - loss: 2.0114
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2805 - loss: 2.0094
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2807 - loss: 2.0069
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 2.0045
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 2.0026
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 2.0010
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2809 - loss: 2.0000
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2808 - loss: 1.9991
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 1.9983
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 1.9975
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2803 - loss: 1.9966
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2802 - loss: 1.9959
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2800 - loss: 1.9952
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 1.9945
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2798 - loss: 1.9940
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2797 - loss: 1.9935
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9931
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 1.9928
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 1.9925
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2794 - loss: 1.9923
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2793 - loss: 1.9921
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2791 - loss: 1.9920
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2791 - loss: 1.9919 - val_accuracy: 0.2594 - val_loss: 1.9773
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.9508
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2927 - loss: 1.9751  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2903 - loss: 1.9614
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2871 - loss: 1.9635
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2847 - loss: 1.9676
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2818 - loss: 1.9703
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2799 - loss: 1.9748
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2786 - loss: 1.9784
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2777 - loss: 1.9803
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2774 - loss: 1.9811
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2773 - loss: 1.9813
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2774 - loss: 1.9811
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 1.9809
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 1.9809
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 1.9811
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 1.9813
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 1.9815
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 1.9819
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 1.9823
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 1.9824
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 1.9827
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 1.9829
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 1.9830
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 1.9831
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 1.9833
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 1.9835
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2777 - loss: 1.9837
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2777 - loss: 1.9839
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2777 - loss: 1.9842
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2777 - loss: 1.9843 - val_accuracy: 0.2816 - val_loss: 1.9583
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.6920
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2575 - loss: 1.9942  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2629 - loss: 1.9993
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2657 - loss: 1.9973
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2676 - loss: 1.9958
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2691 - loss: 1.9957
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2697 - loss: 1.9967
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2708 - loss: 1.9964
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2716 - loss: 1.9963
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2721 - loss: 1.9962
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2728 - loss: 1.9958
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2735 - loss: 1.9953
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 1.9951
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 1.9948
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 1.9943
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2757 - loss: 1.9938
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 1.9931
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2764 - loss: 1.9928
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2767 - loss: 1.9926
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2769 - loss: 1.9924
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2770 - loss: 1.9922
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2772 - loss: 1.9921
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2774 - loss: 1.9919
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 1.9915
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 1.9912
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2777 - loss: 1.9908
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2778 - loss: 1.9903
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2779 - loss: 1.9900
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2780 - loss: 1.9896
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2780 - loss: 1.9893 - val_accuracy: 0.2731 - val_loss: 1.9603
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 1.8923
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2424 - loss: 2.0045  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2542 - loss: 1.9935
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2615 - loss: 1.9855
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2659 - loss: 1.9833
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2685 - loss: 1.9818
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2697 - loss: 1.9816
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2706 - loss: 1.9821
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2711 - loss: 1.9820
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 1.9816
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2718 - loss: 1.9814
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2720 - loss: 1.9813
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2722 - loss: 1.9814
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2724 - loss: 1.9814
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2727 - loss: 1.9812
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2730 - loss: 1.9811
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2734 - loss: 1.9810
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2739 - loss: 1.9807
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2743 - loss: 1.9805
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2746 - loss: 1.9803
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 1.9803
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2750 - loss: 1.9802
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 1.9802
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2755 - loss: 1.9801
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2756 - loss: 1.9801
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2757 - loss: 1.9801
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2758 - loss: 1.9803
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2758 - loss: 1.9804
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 1.9805
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2759 - loss: 1.9805 - val_accuracy: 0.2683 - val_loss: 1.9610

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 624ms/step
[1m59/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 864us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:15[0m 850ms/step
[1m 68/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 748us/step  
[1m142/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 711us/step
[1m199/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 763us/step
[1m272/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 743us/step
[1m347/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 728us/step
[1m410/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 738us/step
[1m476/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 742us/step
[1m538/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 750us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m67/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 764us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 71/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 720us/step
[1m136/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 748us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 27.07 [%]
Global F1 score (validation) = 22.93 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.14238843 0.22580296 0.16605915 ... 0.00128755 0.1245904  0.02335734]
 [0.18328214 0.193694   0.15535387 ... 0.00156946 0.13768396 0.0211149 ]
 [0.15569481 0.21397358 0.14600936 ... 0.00180846 0.14495897 0.02130549]
 ...
 [0.15343131 0.17041045 0.13865258 ... 0.00344337 0.13842073 0.01207179]
 [0.18100259 0.22097111 0.19593143 ... 0.00058214 0.1275709  0.04779001]
 [0.11038793 0.1134273  0.09771077 ... 0.01381426 0.09902214 0.01189239]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 30.13 [%]
Global accuracy score (test) = 24.66 [%]
Global F1 score (train) = 27.08 [%]
Global F1 score (test) = 22.04 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.10      0.05      0.07       184
 CAMINAR CON MÓVIL O LIBRO       0.17      0.59      0.26       184
       CAMINAR USUAL SPEED       0.04      0.01      0.02       184
            CAMINAR ZIGZAG       0.09      0.09      0.09       184
          DE PIE BARRIENDO       0.27      0.48      0.35       184
   DE PIE DOBLANDO TOALLAS       0.25      0.14      0.18       184
    DE PIE MOVIENDO LIBROS       0.13      0.05      0.07       184
          DE PIE USANDO PC       0.22      0.71      0.33       184
        FASE REPOSO CON K5       0.95      0.51      0.66       184
INCREMENTAL CICLOERGOMETRO       0.54      0.12      0.20       184
           SENTADO LEYENDO       0.17      0.18      0.18       184
         SENTADO USANDO PC       0.00      0.00      0.00       184
      SENTADO VIENDO LA TV       0.32      0.41      0.36       184
   SUBIR Y BAJAR ESCALERAS       0.16      0.02      0.04       184
                    TROTAR       0.96      0.34      0.50       161

                  accuracy                           0.25      2737
                 macro avg       0.29      0.25      0.22      2737
              weighted avg       0.29      0.25      0.22      2737


Accuracy capturado en la ejecución 9: 24.66 [%]
F1-score capturado en la ejecución 9: 22.04 [%]

=== EJECUCIÓN 10 ===

--- TRAIN (ejecución 10) ---

--- TEST (ejecución 10) ---
2025-11-07 14:16:52.897788: 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 14:16:52.908764: 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 00:00:1762521412.922169 2945462 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762521412.926317 2945462 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762521412.936502 2945462 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521412.936519 2945462 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521412.936520 2945462 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521412.936521 2945462 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:16:52.939460: 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 00:00:1762521415.207375 2945462 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762521416.684984 2945594 service.cc:152] XLA service 0x7d4cc000bbc0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762521416.685009 2945594 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:16:56.712055: 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 00:00:1762521416.862409 2945594 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762521418.275914 2945594 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47:18[0m 2s/step - accuracy: 0.0625 - loss: 3.0648
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0690 - loss: 3.1842  
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0717 - loss: 3.1713
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0738 - loss: 3.1644
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0753 - loss: 3.1569
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0772 - loss: 3.1463
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0790 - loss: 3.1362
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0799 - loss: 3.1274
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0807 - loss: 3.1193
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0815 - loss: 3.1124
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0822 - loss: 3.1048
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0829 - loss: 3.0973
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0835 - loss: 3.0907
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0841 - loss: 3.0839
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0847 - loss: 3.0774
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0853 - loss: 3.0714
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0859 - loss: 3.0654
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0864 - loss: 3.0596
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0868 - loss: 3.0541
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0872 - loss: 3.0490
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0875 - loss: 3.0445
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0879 - loss: 3.0396
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0882 - loss: 3.0347
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0885 - loss: 3.0300
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0889 - loss: 3.0255
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0892 - loss: 3.0215
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0895 - loss: 3.0171
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0898 - loss: 3.0128
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0902 - loss: 3.0089
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0906 - loss: 3.0046
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0907 - loss: 3.0030
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0907 - loss: 3.0029 - val_accuracy: 0.1299 - val_loss: 2.6292
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.6111
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1328 - loss: 2.7409  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1280 - loss: 2.7280
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1281 - loss: 2.7194
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1275 - loss: 2.7187
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1275 - loss: 2.7176
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1275 - loss: 2.7167
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1269 - loss: 2.7170
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1265 - loss: 2.7167
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1263 - loss: 2.7160
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1263 - loss: 2.7148
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1261 - loss: 2.7137
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1259 - loss: 2.7123
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1258 - loss: 2.7108
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1257 - loss: 2.7092
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1256 - loss: 2.7080
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1256 - loss: 2.7067
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1255 - loss: 2.7055
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1255 - loss: 2.7043
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1255 - loss: 2.7032
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1255 - loss: 2.7021
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1255 - loss: 2.7010
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1256 - loss: 2.7000
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1257 - loss: 2.6989
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1258 - loss: 2.6978
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1259 - loss: 2.6965
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1261 - loss: 2.6951
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1262 - loss: 2.6939
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1264 - loss: 2.6925
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1266 - loss: 2.6911
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1267 - loss: 2.6905 - val_accuracy: 0.1336 - val_loss: 2.5367
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.4685
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1839 - loss: 2.5753  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1685 - loss: 2.5856
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1621 - loss: 2.5877
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1586 - loss: 2.5873
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1570 - loss: 2.5861
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1564 - loss: 2.5846
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1557 - loss: 2.5832
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1553 - loss: 2.5816
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1549 - loss: 2.5806
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1543 - loss: 2.5798
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1539 - loss: 2.5792
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1534 - loss: 2.5784
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1531 - loss: 2.5777
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1528 - loss: 2.5772
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1527 - loss: 2.5763
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1525 - loss: 2.5756
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1525 - loss: 2.5748
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1527 - loss: 2.5739
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1528 - loss: 2.5729
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1529 - loss: 2.5719
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1531 - loss: 2.5709
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1532 - loss: 2.5699
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1534 - loss: 2.5689
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1536 - loss: 2.5680
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1537 - loss: 2.5672
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1539 - loss: 2.5663
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1541 - loss: 2.5655
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1542 - loss: 2.5647
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1544 - loss: 2.5638
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1544 - loss: 2.5637 - val_accuracy: 0.1636 - val_loss: 2.4700
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.1250 - loss: 2.4945
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1855 - loss: 2.4337  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1864 - loss: 2.4446
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1858 - loss: 2.4512
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1858 - loss: 2.4522
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1864 - loss: 2.4523
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1865 - loss: 2.4521
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1860 - loss: 2.4527
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1853 - loss: 2.4535
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1846 - loss: 2.4543
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1841 - loss: 2.4548
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1839 - loss: 2.4550
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1838 - loss: 2.4553
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1836 - loss: 2.4557
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1836 - loss: 2.4560
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1836 - loss: 2.4562
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1837 - loss: 2.4563
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1837 - loss: 2.4563
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1836 - loss: 2.4562
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1836 - loss: 2.4560
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1837 - loss: 2.4558
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1837 - loss: 2.4555
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1837 - loss: 2.4554
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1837 - loss: 2.4551
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1837 - loss: 2.4549
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1838 - loss: 2.4547
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1839 - loss: 2.4544
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1839 - loss: 2.4541
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1840 - loss: 2.4537
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1840 - loss: 2.4535 - val_accuracy: 0.1935 - val_loss: 2.3760
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.5921
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1514 - loss: 2.4654  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1695 - loss: 2.4488
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1766 - loss: 2.4406
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1803 - loss: 2.4352
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1832 - loss: 2.4303
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1867 - loss: 2.4239
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1886 - loss: 2.4206
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1902 - loss: 2.4175
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1916 - loss: 2.4147
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1928 - loss: 2.4123
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1938 - loss: 2.4100
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1946 - loss: 2.4079
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1954 - loss: 2.4057
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1961 - loss: 2.4037
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1967 - loss: 2.4018
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1973 - loss: 2.3999
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1978 - loss: 2.3983
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1983 - loss: 2.3967
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1987 - loss: 2.3953
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1991 - loss: 2.3939
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1994 - loss: 2.3927
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1997 - loss: 2.3915
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2000 - loss: 2.3906
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2003 - loss: 2.3895
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2006 - loss: 2.3885
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2009 - loss: 2.3876
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2011 - loss: 2.3867
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2014 - loss: 2.3859
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2016 - loss: 2.3852 - val_accuracy: 0.2035 - val_loss: 2.2939
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.0496
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2376 - loss: 2.3381  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2257 - loss: 2.3493
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2231 - loss: 2.3513
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2230 - loss: 2.3499
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2225 - loss: 2.3473
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2219 - loss: 2.3457
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2213 - loss: 2.3442
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2207 - loss: 2.3432
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2204 - loss: 2.3417
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2201 - loss: 2.3400
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2199 - loss: 2.3384
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2197 - loss: 2.3370
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2197 - loss: 2.3355
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2197 - loss: 2.3341
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2198 - loss: 2.3327
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2198 - loss: 2.3313
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2197 - loss: 2.3301
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2197 - loss: 2.3290
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2197 - loss: 2.3277
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2197 - loss: 2.3265
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2198 - loss: 2.3252
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2199 - loss: 2.3240
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2200 - loss: 2.3229
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2200 - loss: 2.3220
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2200 - loss: 2.3211
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2201 - loss: 2.3202
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2201 - loss: 2.3194
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2201 - loss: 2.3186
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2202 - loss: 2.3178
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2202 - loss: 2.3177 - val_accuracy: 0.2246 - val_loss: 2.2194
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.1250 - loss: 2.3911
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2234 - loss: 2.3052  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2251 - loss: 2.2938
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2268 - loss: 2.2838
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2273 - loss: 2.2784
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2277 - loss: 2.2733
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2280 - loss: 2.2704
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2283 - loss: 2.2683
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2285 - loss: 2.2668
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2286 - loss: 2.2655
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2286 - loss: 2.2650
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2285 - loss: 2.2651
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2284 - loss: 2.2653
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2284 - loss: 2.2653
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2285 - loss: 2.2652
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2286 - loss: 2.2649
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2287 - loss: 2.2648
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2288 - loss: 2.2646
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2288 - loss: 2.2643
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2288 - loss: 2.2640
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2289 - loss: 2.2636
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2289 - loss: 2.2632
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2290 - loss: 2.2626
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2291 - loss: 2.2620
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2293 - loss: 2.2614
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2294 - loss: 2.2609
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2295 - loss: 2.2605
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2296 - loss: 2.2600
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2297 - loss: 2.2596
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2298 - loss: 2.2593 - val_accuracy: 0.2290 - val_loss: 2.1828
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.3797
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1952 - loss: 2.3071  
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2052 - loss: 2.2783
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2140 - loss: 2.2583
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2180 - loss: 2.2510
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2208 - loss: 2.2448
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2227 - loss: 2.2408
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2240 - loss: 2.2380
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2255 - loss: 2.2358
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2268 - loss: 2.2339
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2278 - loss: 2.2318
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2287 - loss: 2.2301
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2293 - loss: 2.2290
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2298 - loss: 2.2282
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2302 - loss: 2.2277
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2308 - loss: 2.2269
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2314 - loss: 2.2261
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2318 - loss: 2.2253
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2320 - loss: 2.2246
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2322 - loss: 2.2240
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2324 - loss: 2.2235
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2326 - loss: 2.2229
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2327 - loss: 2.2224
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2328 - loss: 2.2219
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2329 - loss: 2.2215
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2330 - loss: 2.2211
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2331 - loss: 2.2207
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2332 - loss: 2.2203
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2333 - loss: 2.2200
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2333 - loss: 2.2195
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2334 - loss: 2.2195 - val_accuracy: 0.2364 - val_loss: 2.1410
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.1875 - loss: 2.1774
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2092 - loss: 2.2376  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2170 - loss: 2.2285
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2199 - loss: 2.2229
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2223 - loss: 2.2172
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2242 - loss: 2.2141
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2264 - loss: 2.2116
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2284 - loss: 2.2091
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2298 - loss: 2.2067
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2310 - loss: 2.2044
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2320 - loss: 2.2023
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2329 - loss: 2.2008
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2340 - loss: 2.1989
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2349 - loss: 2.1974
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2357 - loss: 2.1960
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2362 - loss: 2.1950
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2367 - loss: 2.1942
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2370 - loss: 2.1935
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2372 - loss: 2.1930
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2375 - loss: 2.1922
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2378 - loss: 2.1915
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2382 - loss: 2.1907
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2385 - loss: 2.1899
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2388 - loss: 2.1893
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2391 - loss: 2.1887
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2394 - loss: 2.1882
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2396 - loss: 2.1878
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2398 - loss: 2.1873
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2400 - loss: 2.1868
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2402 - loss: 2.1863 - val_accuracy: 0.2424 - val_loss: 2.0980
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.1341
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2847 - loss: 2.1462  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2744 - loss: 2.1493
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2673 - loss: 2.1551
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2628 - loss: 2.1569
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2609 - loss: 2.1560
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2593 - loss: 2.1553
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2586 - loss: 2.1537
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2577 - loss: 2.1532
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2569 - loss: 2.1530
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2562 - loss: 2.1526
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2557 - loss: 2.1524
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2550 - loss: 2.1522
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2546 - loss: 2.1520
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2542 - loss: 2.1516
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2540 - loss: 2.1513
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2537 - loss: 2.1511
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2535 - loss: 2.1509
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2534 - loss: 2.1507
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2532 - loss: 2.1505
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2531 - loss: 2.1504
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2530 - loss: 2.1502
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2530 - loss: 2.1501
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2530 - loss: 2.1500
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2529 - loss: 2.1499
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2529 - loss: 2.1497
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2529 - loss: 2.1495
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.1493
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.1491
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2528 - loss: 2.1490 - val_accuracy: 0.2468 - val_loss: 2.0653
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.2809
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2834 - loss: 2.1350  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2773 - loss: 2.1263
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2765 - loss: 2.1196
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2745 - loss: 2.1175
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2714 - loss: 2.1197
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2689 - loss: 2.1237
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2676 - loss: 2.1264
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2668 - loss: 2.1282
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2659 - loss: 2.1300
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.1308
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2648 - loss: 2.1313
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2643 - loss: 2.1314
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2639 - loss: 2.1313
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2636 - loss: 2.1311
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2634 - loss: 2.1308
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2631 - loss: 2.1306
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2628 - loss: 2.1304
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2626 - loss: 2.1301
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2623 - loss: 2.1298
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2621 - loss: 2.1295
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2619 - loss: 2.1292
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2618 - loss: 2.1289
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2616 - loss: 2.1286
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2614 - loss: 2.1284
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2613 - loss: 2.1281
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2612 - loss: 2.1277
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2610 - loss: 2.1274
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2609 - loss: 2.1272
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2607 - loss: 2.1270
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2606 - loss: 2.1269 - val_accuracy: 0.2551 - val_loss: 2.0438
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.2027
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2407 - loss: 2.2282  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2613 - loss: 2.1763
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2652 - loss: 2.1569
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2665 - loss: 2.1464
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2671 - loss: 2.1381
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2669 - loss: 2.1316
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2666 - loss: 2.1275
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2665 - loss: 2.1242
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2665 - loss: 2.1212
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.1190
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.1171
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2660 - loss: 2.1155
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.1141
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.1132
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.1124
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.1115
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.1107
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.1101
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.1096
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2654 - loss: 2.1091
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.1086
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2651 - loss: 2.1081
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.1078
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2649 - loss: 2.1075
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2648 - loss: 2.1072
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2647 - loss: 2.1069
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.1066
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2644 - loss: 2.1063
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2644 - loss: 2.1061
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2643 - loss: 2.1060 - val_accuracy: 0.2685 - val_loss: 2.0402
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.2193
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0620  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0731
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0755
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2720 - loss: 2.0744
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2727 - loss: 2.0727
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2734 - loss: 2.0708
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0692
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0680
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2735 - loss: 2.0680
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0682
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2730 - loss: 2.0684
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2726 - loss: 2.0687
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2725 - loss: 2.0691
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2726 - loss: 2.0694
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2726 - loss: 2.0695
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2726 - loss: 2.0694
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2726 - loss: 2.0692
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2724 - loss: 2.0694
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0696
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2720 - loss: 2.0699
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0702
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0705
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0708
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0710
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2712 - loss: 2.0713
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0715
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0717
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0718
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2707 - loss: 2.0719 - val_accuracy: 0.2675 - val_loss: 2.0089
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3750 - loss: 1.9200
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2803 - loss: 2.0587  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2790 - loss: 2.0500
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2775 - loss: 2.0477
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2753 - loss: 2.0485
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2741 - loss: 2.0489
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0486
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2725 - loss: 2.0491
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0504
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0517
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2705 - loss: 2.0529
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0538
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0551
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2689 - loss: 2.0559
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2685 - loss: 2.0568
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0579
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0588
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0596
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0602
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0608
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0613
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0618
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0623
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0625
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0627
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0628
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0629
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0630
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0629
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2662 - loss: 2.0629 - val_accuracy: 0.2723 - val_loss: 2.0233
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.9478
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2611 - loss: 2.1065  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2505 - loss: 2.1050
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2496 - loss: 2.0968
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2500 - loss: 2.0906
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2508 - loss: 2.0848
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2517 - loss: 2.0808
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2525 - loss: 2.0779
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2534 - loss: 2.0758
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2543 - loss: 2.0737
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2551 - loss: 2.0723
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2557 - loss: 2.0711
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2562 - loss: 2.0698
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.0692
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0690
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0687
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2574 - loss: 2.0684
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2576 - loss: 2.0681
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.0676
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0672
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2583 - loss: 2.0668
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2585 - loss: 2.0664
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2587 - loss: 2.0659
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2588 - loss: 2.0654
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2590 - loss: 2.0648
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2592 - loss: 2.0641
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2594 - loss: 2.0635
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2597 - loss: 2.0629
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0623
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2600 - loss: 2.0620 - val_accuracy: 0.2679 - val_loss: 2.0069
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 1.9349
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2985 - loss: 1.9185  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2968 - loss: 1.9577
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2927 - loss: 1.9834
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2900 - loss: 1.9954
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2886 - loss: 2.0022
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2868 - loss: 2.0073
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2855 - loss: 2.0102
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2844 - loss: 2.0129
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2838 - loss: 2.0149
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2832 - loss: 2.0165
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2826 - loss: 2.0181
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2820 - loss: 2.0190
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2816 - loss: 2.0195
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 2.0201
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 2.0210
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2800 - loss: 2.0220
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 2.0229
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2792 - loss: 2.0237
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 2.0245
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2786 - loss: 2.0253
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2784 - loss: 2.0258
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2783 - loss: 2.0263
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2781 - loss: 2.0268
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2779 - loss: 2.0272
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2777 - loss: 2.0276
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 2.0280
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2774 - loss: 2.0283
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2772 - loss: 2.0287
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2770 - loss: 2.0292 - val_accuracy: 0.2740 - val_loss: 1.9921
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0850
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2580 - loss: 2.0677  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2638 - loss: 2.0676
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0667
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2673 - loss: 2.0629
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0605
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2692 - loss: 2.0581
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0562
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0539
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2712 - loss: 2.0517
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0502
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0482
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2726 - loss: 2.0463
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2727 - loss: 2.0449
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2729 - loss: 2.0438
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0424
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2733 - loss: 2.0413
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2735 - loss: 2.0403
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 2.0396
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2739 - loss: 2.0387
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0381
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2742 - loss: 2.0374
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2743 - loss: 2.0369
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0364
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2746 - loss: 2.0359
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0354
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0349
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0344
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0341
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2749 - loss: 2.0338 - val_accuracy: 0.2799 - val_loss: 1.9737
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.4375 - loss: 2.0472
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2252 - loss: 2.1166  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2354 - loss: 2.0957
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2450 - loss: 2.0803
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2499 - loss: 2.0721
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2532 - loss: 2.0681
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2555 - loss: 2.0639
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2575 - loss: 2.0602
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2593 - loss: 2.0569
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2607 - loss: 2.0541
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2619 - loss: 2.0510
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2628 - loss: 2.0489
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0468
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0451
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0432
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0417
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0402
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0389
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0376
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0364
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0352
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2691 - loss: 2.0343
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 2.0335
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0327
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0320
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2706 - loss: 2.0314
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0307
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0300
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0294
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2714 - loss: 2.0288
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2715 - loss: 2.0286 - val_accuracy: 0.2797 - val_loss: 1.9771
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.3125 - loss: 1.9604
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2693 - loss: 1.9980  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0025
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2777 - loss: 2.0023
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2777 - loss: 2.0034
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2773 - loss: 2.0054
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2765 - loss: 2.0078
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2760 - loss: 2.0091
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2756 - loss: 2.0098
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2751 - loss: 2.0102
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0102
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0101
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0099
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0095
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0088
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0083
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2753 - loss: 2.0078
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2754 - loss: 2.0073
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2755 - loss: 2.0069
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2756 - loss: 2.0066
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2758 - loss: 2.0062
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2760 - loss: 2.0059
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2762 - loss: 2.0055
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2764 - loss: 2.0050
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2766 - loss: 2.0047
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2767 - loss: 2.0045
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2769 - loss: 2.0043
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2769 - loss: 2.0042
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2770 - loss: 2.0042
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2770 - loss: 2.0042 - val_accuracy: 0.2653 - val_loss: 1.9752
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.3125 - loss: 1.7335
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9611  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2733 - loss: 1.9817
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2728 - loss: 1.9935
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2735 - loss: 1.9977
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0004
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2760 - loss: 2.0016
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2771 - loss: 2.0011
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2784 - loss: 2.0000
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2797 - loss: 1.9994
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2808 - loss: 1.9990
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2816 - loss: 1.9988
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2823 - loss: 1.9989
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2827 - loss: 1.9990
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2831 - loss: 1.9990
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2834 - loss: 1.9990
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2836 - loss: 1.9988
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2837 - loss: 1.9987
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2837 - loss: 1.9987
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2837 - loss: 1.9986
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2837 - loss: 1.9985
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2837 - loss: 1.9984
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2837 - loss: 1.9983
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2837 - loss: 1.9982
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2837 - loss: 1.9981
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2836 - loss: 1.9981
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2836 - loss: 1.9980
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2835 - loss: 1.9979
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2834 - loss: 1.9977
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2833 - loss: 1.9976
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2832 - loss: 1.9975 - val_accuracy: 0.2714 - val_loss: 1.9754
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.2500 - loss: 1.7968
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2937 - loss: 1.9395  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2937 - loss: 1.9566
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2929 - loss: 1.9648
[1m 146/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2921 - loss: 1.9673
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2922 - loss: 1.9671
[1m 223/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2916 - loss: 1.9679
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2907 - loss: 1.9691
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2900 - loss: 1.9697
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2891 - loss: 1.9711
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2882 - loss: 1.9726
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2877 - loss: 1.9735
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2875 - loss: 1.9742
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2874 - loss: 1.9747
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2871 - loss: 1.9754
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2867 - loss: 1.9760
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2863 - loss: 1.9765
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2861 - loss: 1.9770
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2859 - loss: 1.9774
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2856 - loss: 1.9779
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2855 - loss: 1.9783
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2854 - loss: 1.9786
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2854 - loss: 1.9789
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2853 - loss: 1.9790
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2853 - loss: 1.9792
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2852 - loss: 1.9793
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2851 - loss: 1.9794
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2850 - loss: 1.9795
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2850 - loss: 1.9797
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2849 - loss: 1.9797
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2849 - loss: 1.9798
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2849 - loss: 1.9798 - val_accuracy: 0.2853 - val_loss: 1.9492
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.1875 - loss: 2.0038
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2828 - loss: 2.0064  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2929 - loss: 1.9902
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2930 - loss: 1.9855
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2908 - loss: 1.9881
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2906 - loss: 1.9868
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2900 - loss: 1.9858
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2897 - loss: 1.9849
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2893 - loss: 1.9840
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2888 - loss: 1.9842
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2883 - loss: 1.9840
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2879 - loss: 1.9837
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2876 - loss: 1.9835
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2872 - loss: 1.9834
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2867 - loss: 1.9832
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2863 - loss: 1.9831
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2860 - loss: 1.9829
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2858 - loss: 1.9830
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2857 - loss: 1.9830
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2857 - loss: 1.9827
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2858 - loss: 1.9824
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2858 - loss: 1.9821
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2858 - loss: 1.9819
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2858 - loss: 1.9816
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2858 - loss: 1.9813
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2858 - loss: 1.9810
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2858 - loss: 1.9808
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2858 - loss: 1.9805
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2858 - loss: 1.9803
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2858 - loss: 1.9800
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2858 - loss: 1.9800 - val_accuracy: 0.2740 - val_loss: 1.9685
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.3563
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2503 - loss: 2.0238  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2635 - loss: 2.0022
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2677 - loss: 1.9967
[1m 168/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2707 - loss: 1.9925
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2727 - loss: 1.9899
[1m 249/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2744 - loss: 1.9881
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2756 - loss: 1.9874
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2765 - loss: 1.9867
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2771 - loss: 1.9863
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 1.9859
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2780 - loss: 1.9851
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2782 - loss: 1.9846
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2784 - loss: 1.9845
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2787 - loss: 1.9842
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9838
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2792 - loss: 1.9835
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2794 - loss: 1.9831
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2797 - loss: 1.9825
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 1.9818
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2803 - loss: 1.9812
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 1.9806
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2809 - loss: 1.9800
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 1.9794
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2814 - loss: 1.9788
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2815 - loss: 1.9784
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2816 - loss: 1.9780
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2817 - loss: 1.9777
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2817 - loss: 1.9774
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2818 - loss: 1.9771 - val_accuracy: 0.2772 - val_loss: 1.9542
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.3750 - loss: 2.0406
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2751 - loss: 1.9542  
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2743 - loss: 1.9564
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2758 - loss: 1.9564
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2769 - loss: 1.9557
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2774 - loss: 1.9544
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2779 - loss: 1.9541
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2788 - loss: 1.9544
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2794 - loss: 1.9554
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9571
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 1.9580
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2802 - loss: 1.9584
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2803 - loss: 1.9590
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 1.9594
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2807 - loss: 1.9597
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2809 - loss: 1.9596
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 1.9595
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2813 - loss: 1.9595
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2815 - loss: 1.9595
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2816 - loss: 1.9595
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2818 - loss: 1.9595
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2819 - loss: 1.9596
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2820 - loss: 1.9596
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2822 - loss: 1.9597
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2823 - loss: 1.9597
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2824 - loss: 1.9597
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2825 - loss: 1.9597
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2826 - loss: 1.9596
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2827 - loss: 1.9596
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2828 - loss: 1.9597
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2828 - loss: 1.9597 - val_accuracy: 0.2857 - val_loss: 1.9585
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.9960
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3037 - loss: 1.9529  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3006 - loss: 1.9494
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2989 - loss: 1.9517
[1m 168/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2963 - loss: 1.9537
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2942 - loss: 1.9559
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2929 - loss: 1.9575
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2919 - loss: 1.9575
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2909 - loss: 1.9575
[1m 386/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2902 - loss: 1.9579
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2898 - loss: 1.9581
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2895 - loss: 1.9582
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2892 - loss: 1.9582
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2889 - loss: 1.9581
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2886 - loss: 1.9578
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2883 - loss: 1.9577
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2880 - loss: 1.9574
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2877 - loss: 1.9571
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2876 - loss: 1.9569
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2874 - loss: 1.9567
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2873 - loss: 1.9566
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2873 - loss: 1.9565
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2872 - loss: 1.9565
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2872 - loss: 1.9565
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2871 - loss: 1.9564
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2871 - loss: 1.9563
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2871 - loss: 1.9563
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2870 - loss: 1.9562
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2870 - loss: 1.9562
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2870 - loss: 1.9562 - val_accuracy: 0.2853 - val_loss: 1.9274

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m52s[0m 615ms/step
[1m63/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 820us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7:49[0m 806ms/step
[1m 69/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 745us/step  
[1m141/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 720us/step
[1m216/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 704us/step
[1m280/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 723us/step
[1m352/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 717us/step
[1m418/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 725us/step
[1m490/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 721us/step
[1m557/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 725us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m66/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 774us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 70/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 725us/step
[1m143/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 706us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 26.83 [%]
Global F1 score (validation) = 23.68 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.10610296 0.18734898 0.13018936 ... 0.00821643 0.07305232 0.0135637 ]
 [0.1436002  0.2377594  0.19704139 ... 0.0010037  0.14031008 0.03794422]
 [0.13829209 0.20545319 0.18485895 ... 0.00348984 0.12012259 0.02205125]
 ...
 [0.15150101 0.18082254 0.1855773  ... 0.00025521 0.14977506 0.07294292]
 [0.16842891 0.19981863 0.19514582 ... 0.00082249 0.17601581 0.04280831]
 [0.09562762 0.12707771 0.10227757 ... 0.01278231 0.0552335  0.0085791 ]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 31.62 [%]
Global accuracy score (test) = 25.21 [%]
Global F1 score (train) = 28.96 [%]
Global F1 score (test) = 22.08 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.00      0.00      0.00       184
 CAMINAR CON MÓVIL O LIBRO       0.16      0.58      0.25       184
       CAMINAR USUAL SPEED       0.08      0.05      0.06       184
            CAMINAR ZIGZAG       0.00      0.00      0.00       184
          DE PIE BARRIENDO       0.18      0.52      0.26       184
   DE PIE DOBLANDO TOALLAS       0.20      0.14      0.17       184
    DE PIE MOVIENDO LIBROS       0.21      0.20      0.21       184
          DE PIE USANDO PC       0.32      0.77      0.45       184
        FASE REPOSO CON K5       0.91      0.54      0.68       184
INCREMENTAL CICLOERGOMETRO       0.50      0.10      0.17       184
           SENTADO LEYENDO       0.26      0.25      0.25       184
         SENTADO USANDO PC       0.12      0.03      0.05       184
      SENTADO VIENDO LA TV       0.28      0.27      0.28       184
   SUBIR Y BAJAR ESCALERAS       0.00      0.00      0.00       184
                    TROTAR       0.85      0.33      0.48       161

                  accuracy                           0.25      2737
                 macro avg       0.27      0.25      0.22      2737
              weighted avg       0.27      0.25      0.22      2737


Accuracy capturado en la ejecución 10: 25.21 [%]
F1-score capturado en la ejecución 10: 22.08 [%]

=== EJECUCIÓN 11 ===

--- TRAIN (ejecución 11) ---

--- TEST (ejecución 11) ---
2025-11-07 14:18:00.174759: 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 14:18:00.186070: 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 00:00:1762521480.199258 2949210 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762521480.203183 2949210 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762521480.213190 2949210 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521480.213207 2949210 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521480.213208 2949210 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521480.213209 2949210 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:18:00.216368: 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 00:00:1762521482.489518 2949210 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762521484.003050 2949326 service.cc:152] XLA service 0x72856400bc50 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762521484.003076 2949326 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:18:04.029764: 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 00:00:1762521484.175066 2949326 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762521485.561408 2949326 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47:08[0m 2s/step - accuracy: 0.0625 - loss: 2.9728
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0699 - loss: 3.1270  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0726 - loss: 3.1189
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0733 - loss: 3.1187
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0739 - loss: 3.1156
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0739 - loss: 3.1115
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0747 - loss: 3.1044
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0760 - loss: 3.0967
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0771 - loss: 3.0893
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0782 - loss: 3.0820
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0793 - loss: 3.0748
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0802 - loss: 3.0677
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0811 - loss: 3.0613
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0821 - loss: 3.0545
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0829 - loss: 3.0482
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0837 - loss: 3.0415
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0844 - loss: 3.0353
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0852 - loss: 3.0287
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0860 - loss: 3.0226
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0867 - loss: 3.0171
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0875 - loss: 3.0113
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0882 - loss: 3.0058
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0888 - loss: 3.0011
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0894 - loss: 2.9963
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0899 - loss: 2.9918
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0905 - loss: 2.9872
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0909 - loss: 2.9833
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0915 - loss: 2.9789
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0920 - loss: 2.9748
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0924 - loss: 2.9711
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0925 - loss: 2.9710 - val_accuracy: 0.1761 - val_loss: 2.5278
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.5323
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1735 - loss: 2.6220  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1610 - loss: 2.6532
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1531 - loss: 2.6614
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1473 - loss: 2.6655
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1449 - loss: 2.6656
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1434 - loss: 2.6643
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1422 - loss: 2.6638
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1410 - loss: 2.6639
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1401 - loss: 2.6638
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1395 - loss: 2.6629
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1391 - loss: 2.6617
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1389 - loss: 2.6605
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1388 - loss: 2.6594
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1387 - loss: 2.6583
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1387 - loss: 2.6573
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1386 - loss: 2.6567
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1386 - loss: 2.6560
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1387 - loss: 2.6553
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1387 - loss: 2.6546
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1388 - loss: 2.6537
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1390 - loss: 2.6528
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1391 - loss: 2.6518
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1393 - loss: 2.6508
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1395 - loss: 2.6499
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1396 - loss: 2.6491
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1398 - loss: 2.6482
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1400 - loss: 2.6473
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1402 - loss: 2.6464
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1404 - loss: 2.6455 - val_accuracy: 0.1944 - val_loss: 2.4481
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.3503
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1705 - loss: 2.5501  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1701 - loss: 2.5630
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1699 - loss: 2.5651
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1681 - loss: 2.5651
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1672 - loss: 2.5638
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1665 - loss: 2.5634
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1662 - loss: 2.5633
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1660 - loss: 2.5629
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1658 - loss: 2.5621
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1656 - loss: 2.5612
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1656 - loss: 2.5601
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1657 - loss: 2.5588
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1660 - loss: 2.5574
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1662 - loss: 2.5561
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1664 - loss: 2.5548
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1667 - loss: 2.5534
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1670 - loss: 2.5521
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1673 - loss: 2.5509
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1675 - loss: 2.5497
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1677 - loss: 2.5486
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1678 - loss: 2.5477
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1680 - loss: 2.5466
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1681 - loss: 2.5455
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1683 - loss: 2.5443
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1684 - loss: 2.5432
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1685 - loss: 2.5420
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1686 - loss: 2.5410
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1686 - loss: 2.5401
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1687 - loss: 2.5392 - val_accuracy: 0.2002 - val_loss: 2.4062
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.5872
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1789 - loss: 2.4895  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1786 - loss: 2.4815
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1801 - loss: 2.4738
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1814 - loss: 2.4690
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1828 - loss: 2.4657
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1837 - loss: 2.4631
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1839 - loss: 2.4618
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1839 - loss: 2.4610
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1837 - loss: 2.4603
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1834 - loss: 2.4599
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1833 - loss: 2.4592
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1833 - loss: 2.4583
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1834 - loss: 2.4573
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1835 - loss: 2.4564
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1835 - loss: 2.4556
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1835 - loss: 2.4549
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1835 - loss: 2.4542
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1836 - loss: 2.4536
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1836 - loss: 2.4530
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1836 - loss: 2.4525
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1837 - loss: 2.4517
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1838 - loss: 2.4511
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1839 - loss: 2.4504
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1841 - loss: 2.4497
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1843 - loss: 2.4489
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1845 - loss: 2.4481
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1847 - loss: 2.4473
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1848 - loss: 2.4465
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1850 - loss: 2.4459
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1851 - loss: 2.4453 - val_accuracy: 0.2222 - val_loss: 2.3192
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.1786
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1680 - loss: 2.4260  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1714 - loss: 2.4276
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1759 - loss: 2.4239
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1802 - loss: 2.4162
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1843 - loss: 2.4095
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1866 - loss: 2.4065
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1880 - loss: 2.4047
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1894 - loss: 2.4023
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1904 - loss: 2.4006
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1911 - loss: 2.3993
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1918 - loss: 2.3978
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1923 - loss: 2.3965
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1928 - loss: 2.3953
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1932 - loss: 2.3941
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1935 - loss: 2.3930
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1939 - loss: 2.3919
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1942 - loss: 2.3909
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1944 - loss: 2.3901
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1946 - loss: 2.3893
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1948 - loss: 2.3884
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1951 - loss: 2.3876
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1953 - loss: 2.3868
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1954 - loss: 2.3860
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1956 - loss: 2.3851
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1958 - loss: 2.3842
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1960 - loss: 2.3833
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1962 - loss: 2.3823
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1964 - loss: 2.3814
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1966 - loss: 2.3803
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1967 - loss: 2.3798 - val_accuracy: 0.2118 - val_loss: 2.2944
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.0000e+00 - loss: 2.8582
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1881 - loss: 2.3689      
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1999 - loss: 2.3343
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2042 - loss: 2.3208
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2052 - loss: 2.3187
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2052 - loss: 2.3178
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2054 - loss: 2.3177
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2058 - loss: 2.3174
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2063 - loss: 2.3170
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2066 - loss: 2.3168
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2070 - loss: 2.3163
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2072 - loss: 2.3163
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2076 - loss: 2.3162
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2079 - loss: 2.3160
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2082 - loss: 2.3155
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2086 - loss: 2.3151
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2089 - loss: 2.3146
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2093 - loss: 2.3139
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2097 - loss: 2.3134
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2101 - loss: 2.3129
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2103 - loss: 2.3124
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2106 - loss: 2.3118
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2108 - loss: 2.3112
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2111 - loss: 2.3105
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2114 - loss: 2.3098
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2116 - loss: 2.3091
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2119 - loss: 2.3084
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2121 - loss: 2.3077
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2124 - loss: 2.3070
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2126 - loss: 2.3065 - val_accuracy: 0.2366 - val_loss: 2.2139
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.2498
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2430 - loss: 2.2210  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2438 - loss: 2.2203
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2387 - loss: 2.2273
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2366 - loss: 2.2305
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2352 - loss: 2.2329
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2342 - loss: 2.2343
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2332 - loss: 2.2360
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2323 - loss: 2.2378
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2319 - loss: 2.2391
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2314 - loss: 2.2404
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2308 - loss: 2.2419
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2304 - loss: 2.2433
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2299 - loss: 2.2449
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2296 - loss: 2.2462
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2294 - loss: 2.2471
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2293 - loss: 2.2477
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2292 - loss: 2.2482
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2291 - loss: 2.2486
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2291 - loss: 2.2488
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2290 - loss: 2.2489
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2290 - loss: 2.2491
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2290 - loss: 2.2492
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2289 - loss: 2.2493
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2289 - loss: 2.2494
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2288 - loss: 2.2495
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2288 - loss: 2.2496
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2288 - loss: 2.2497
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2288 - loss: 2.2498
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2287 - loss: 2.2498
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2287 - loss: 2.2498 - val_accuracy: 0.2344 - val_loss: 2.1792
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.1875 - loss: 2.1525
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1990 - loss: 2.2038  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2119 - loss: 2.2046
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2174 - loss: 2.2081
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2200 - loss: 2.2116
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2221 - loss: 2.2131
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2236 - loss: 2.2140
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2245 - loss: 2.2155
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2251 - loss: 2.2165
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2258 - loss: 2.2170
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2264 - loss: 2.2175
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2270 - loss: 2.2179
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2275 - loss: 2.2181
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2279 - loss: 2.2183
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2283 - loss: 2.2184
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2286 - loss: 2.2184
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2289 - loss: 2.2183
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2292 - loss: 2.2180
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2295 - loss: 2.2178
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2297 - loss: 2.2175
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2299 - loss: 2.2173
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2301 - loss: 2.2171
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2302 - loss: 2.2169
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2304 - loss: 2.2168
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2306 - loss: 2.2165
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2308 - loss: 2.2163
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2310 - loss: 2.2161
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2312 - loss: 2.2157
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2313 - loss: 2.2154
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2315 - loss: 2.2151
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2317 - loss: 2.2149 - val_accuracy: 0.2337 - val_loss: 2.1585
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.9506
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2610 - loss: 2.1421  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2604 - loss: 2.1452
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2569 - loss: 2.1510
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1579
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2530 - loss: 2.1625
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2520 - loss: 2.1667
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2511 - loss: 2.1698
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2506 - loss: 2.1714
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2501 - loss: 2.1721
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2495 - loss: 2.1727
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2490 - loss: 2.1730
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2484 - loss: 2.1734
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2479 - loss: 2.1739
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2475 - loss: 2.1743
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2471 - loss: 2.1748
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2468 - loss: 2.1750
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2465 - loss: 2.1752
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2461 - loss: 2.1753
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2458 - loss: 2.1754
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1754
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1755
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2450 - loss: 2.1757
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2447 - loss: 2.1758
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2445 - loss: 2.1758
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2443 - loss: 2.1759
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2442 - loss: 2.1759
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2441 - loss: 2.1760
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2439 - loss: 2.1761
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2438 - loss: 2.1763
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2438 - loss: 2.1763 - val_accuracy: 0.2483 - val_loss: 2.1137
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.5391
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2240 - loss: 2.1715  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2342 - loss: 2.1698
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2394 - loss: 2.1670
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2421 - loss: 2.1631
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2427 - loss: 2.1620
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2425 - loss: 2.1630
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2423 - loss: 2.1639
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2421 - loss: 2.1645
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2422 - loss: 2.1643
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2424 - loss: 2.1646
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2426 - loss: 2.1648
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2427 - loss: 2.1649
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2428 - loss: 2.1651
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2427 - loss: 2.1652
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2427 - loss: 2.1654
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2426 - loss: 2.1656
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2427 - loss: 2.1655
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2427 - loss: 2.1655
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2428 - loss: 2.1655
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2429 - loss: 2.1654
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2430 - loss: 2.1651
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2431 - loss: 2.1649
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2432 - loss: 2.1646
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2432 - loss: 2.1644
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2433 - loss: 2.1641
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2434 - loss: 2.1638
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2435 - loss: 2.1635
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2436 - loss: 2.1631
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2437 - loss: 2.1628
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2437 - loss: 2.1627 - val_accuracy: 0.2574 - val_loss: 2.1090
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.1959
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2364 - loss: 2.1412  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2354 - loss: 2.1419
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2351 - loss: 2.1461
[1m 168/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2355 - loss: 2.1488
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2370 - loss: 2.1483
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2381 - loss: 2.1481
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2393 - loss: 2.1476
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2403 - loss: 2.1469
[1m 381/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2412 - loss: 2.1458
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2422 - loss: 2.1449
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2430 - loss: 2.1439
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2439 - loss: 2.1430
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2445 - loss: 2.1424
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2450 - loss: 2.1419
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2453 - loss: 2.1416
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1411
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2462 - loss: 2.1407
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2467 - loss: 2.1402
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2470 - loss: 2.1398
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2473 - loss: 2.1393
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2476 - loss: 2.1389
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2478 - loss: 2.1386
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2480 - loss: 2.1382
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2481 - loss: 2.1379
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2482 - loss: 2.1377
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2483 - loss: 2.1375
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2484 - loss: 2.1373
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2484 - loss: 2.1371
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2485 - loss: 2.1369
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2486 - loss: 2.1369 - val_accuracy: 0.2544 - val_loss: 2.0910
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.0123
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2551 - loss: 2.0427  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0532
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0651
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0762
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2587 - loss: 2.0860
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2579 - loss: 2.0917
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2578 - loss: 2.0957
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2577 - loss: 2.0987
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2577 - loss: 2.1019
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.1050
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.1078
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2576 - loss: 2.1102
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2576 - loss: 2.1119
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.1131
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.1143
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.1152
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.1160
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.1165
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.1167
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.1169
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2580 - loss: 2.1169
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.1168
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2582 - loss: 2.1168
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2582 - loss: 2.1167
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2582 - loss: 2.1167
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2583 - loss: 2.1166
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2582 - loss: 2.1164
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2582 - loss: 2.1163
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2582 - loss: 2.1161
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2582 - loss: 2.1161 - val_accuracy: 0.2666 - val_loss: 2.0589
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.3750 - loss: 2.0177
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3031 - loss: 2.0329  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2902 - loss: 2.0560
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2840 - loss: 2.0690
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2794 - loss: 2.0746
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2773 - loss: 2.0774
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2759 - loss: 2.0786
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0798
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0809
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2719 - loss: 2.0815
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0822
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2697 - loss: 2.0831
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2689 - loss: 2.0837
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2683 - loss: 2.0844
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0850
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0856
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0862
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0869
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0874
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0879
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0881
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0883
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0884
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0885
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0886
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0888
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2648 - loss: 2.0891
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2646 - loss: 2.0892
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0894
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0896
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2641 - loss: 2.0897 - val_accuracy: 0.2683 - val_loss: 2.0712
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.3943
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2561 - loss: 2.1107  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2592 - loss: 2.1070
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0973
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0901
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0870
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0848
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0825
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2684 - loss: 2.0807
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2688 - loss: 2.0793
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2692 - loss: 2.0785
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0783
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0783
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0783
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0783
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2695 - loss: 2.0782
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 2.0780
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 2.0780
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2695 - loss: 2.0780
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2695 - loss: 2.0778
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2695 - loss: 2.0777
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0777
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0778
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0778
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0778
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2692 - loss: 2.0777
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2691 - loss: 2.0776
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2690 - loss: 2.0777
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2689 - loss: 2.0776
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2688 - loss: 2.0776
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2687 - loss: 2.0776 - val_accuracy: 0.2574 - val_loss: 2.0711
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.5321
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2675 - loss: 2.1118  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2610 - loss: 2.1005
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2628 - loss: 2.0931
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0868
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2680 - loss: 2.0817
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2691 - loss: 2.0778
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2697 - loss: 2.0748
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0723
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2706 - loss: 2.0704
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0681
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0663
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0649
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2719 - loss: 2.0638
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0631
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0628
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0625
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0625
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2714 - loss: 2.0627
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0628
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0630
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0632
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0633
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2706 - loss: 2.0633
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0633
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0632
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0633
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0633
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 2.0633
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2695 - loss: 2.0634
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2695 - loss: 2.0634 - val_accuracy: 0.2657 - val_loss: 2.0503
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.4016
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2362 - loss: 2.1225  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2389 - loss: 2.1001
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2431 - loss: 2.0923
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2449 - loss: 2.0884
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2461 - loss: 2.0885
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2466 - loss: 2.0892
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2475 - loss: 2.0883
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2484 - loss: 2.0864
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2492 - loss: 2.0851
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2499 - loss: 2.0842
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2506 - loss: 2.0831
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2514 - loss: 2.0820
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2522 - loss: 2.0812
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2530 - loss: 2.0801
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2536 - loss: 2.0793
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.0786
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0779
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2553 - loss: 2.0773
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2556 - loss: 2.0768
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.0764
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2562 - loss: 2.0760
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.0756
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0752
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0748
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0745
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2574 - loss: 2.0742
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2576 - loss: 2.0739
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.0735
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0730
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2581 - loss: 2.0730 - val_accuracy: 0.2646 - val_loss: 2.0418
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.9860
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2622 - loss: 2.1163  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2550 - loss: 2.1035
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2540 - loss: 2.0891
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2550 - loss: 2.0801
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0720
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2585 - loss: 2.0650
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2597 - loss: 2.0602
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0563
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2622 - loss: 2.0533
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0518
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2638 - loss: 2.0508
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0499
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0494
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0488
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0484
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0482
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0481
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0480
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0479
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0478
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0476
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0475
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0474
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0473
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0472
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0471
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0468
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0466
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0463
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2672 - loss: 2.0463 - val_accuracy: 0.2710 - val_loss: 2.0189
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.9674
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2836 - loss: 2.0337  
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2874 - loss: 2.0278
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2876 - loss: 2.0299
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2852 - loss: 2.0307
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2832 - loss: 2.0308
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2823 - loss: 2.0294
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2816 - loss: 2.0287
[1m 305/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2809 - loss: 2.0277
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2801 - loss: 2.0267
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2795 - loss: 2.0252
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 2.0236
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2785 - loss: 2.0225
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2781 - loss: 2.0218
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 2.0215
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2772 - loss: 2.0213
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2767 - loss: 2.0213
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2763 - loss: 2.0213
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2760 - loss: 2.0214
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2757 - loss: 2.0214
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2754 - loss: 2.0214
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2751 - loss: 2.0214
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0214
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0215
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0216
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0217
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2746 - loss: 2.0219
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0220
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2743 - loss: 2.0223
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2742 - loss: 2.0226
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2741 - loss: 2.0228
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2741 - loss: 2.0229 - val_accuracy: 0.2679 - val_loss: 2.0112
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.1923
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2435 - loss: 2.0136  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2539 - loss: 2.0159
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0218
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2576 - loss: 2.0248
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2584 - loss: 2.0265
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2585 - loss: 2.0276
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2585 - loss: 2.0280
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2590 - loss: 2.0277
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2594 - loss: 2.0281
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2596 - loss: 2.0289
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2600 - loss: 2.0296
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0302
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2608 - loss: 2.0306
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2612 - loss: 2.0308
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2616 - loss: 2.0310
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2619 - loss: 2.0311
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2623 - loss: 2.0310
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2626 - loss: 2.0311
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0312
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0314
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0313
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0313
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0312
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0310
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0309
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0307
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2654 - loss: 2.0306
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0304
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0302
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2661 - loss: 2.0300 - val_accuracy: 0.2673 - val_loss: 2.0368
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.2500 - loss: 2.4351
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2903 - loss: 2.0322  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2867 - loss: 2.0249
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2872 - loss: 2.0176
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2887 - loss: 2.0130
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2896 - loss: 2.0099
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2900 - loss: 2.0085
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2902 - loss: 2.0080
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2902 - loss: 2.0078
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2899 - loss: 2.0078
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2897 - loss: 2.0074
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2896 - loss: 2.0067
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2893 - loss: 2.0064
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2891 - loss: 2.0061
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2890 - loss: 2.0057
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2888 - loss: 2.0053
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2887 - loss: 2.0048
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2884 - loss: 2.0044
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2882 - loss: 2.0041
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2880 - loss: 2.0038
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2877 - loss: 2.0036
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2875 - loss: 2.0033
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2871 - loss: 2.0032
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2868 - loss: 2.0031
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2865 - loss: 2.0030
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2862 - loss: 2.0029
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2860 - loss: 2.0028
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2858 - loss: 2.0028
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2856 - loss: 2.0028
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2853 - loss: 2.0028
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2852 - loss: 2.0028 - val_accuracy: 0.2670 - val_loss: 2.0026
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.8669
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2206 - loss: 2.2159  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2414 - loss: 2.1390
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2515 - loss: 2.1056
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2558 - loss: 2.0884
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0719
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2619 - loss: 2.0622
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0542
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0484
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0433
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0399
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0367
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2678 - loss: 2.0340
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0316
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0295
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2690 - loss: 2.0274
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0256
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0238
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0223
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2706 - loss: 2.0209
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0195
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0184
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2719 - loss: 2.0172
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0163
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2725 - loss: 2.0155
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2728 - loss: 2.0148
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2730 - loss: 2.0141
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2733 - loss: 2.0134
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2735 - loss: 2.0129
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2738 - loss: 2.0123
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2738 - loss: 2.0122 - val_accuracy: 0.2786 - val_loss: 1.9973
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.4375 - loss: 1.8515
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2762 - loss: 2.0221  
[1m  68/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2808 - loss: 2.0088
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2803 - loss: 2.0052
[1m 149/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2785 - loss: 2.0048
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2775 - loss: 2.0045
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2776 - loss: 2.0024
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2776 - loss: 2.0008
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2778 - loss: 1.9989
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2782 - loss: 1.9974
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2785 - loss: 1.9963
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2788 - loss: 1.9955
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2791 - loss: 1.9949
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2794 - loss: 1.9943
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2797 - loss: 1.9938
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 1.9934
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2802 - loss: 1.9931
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2803 - loss: 1.9929
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 1.9928
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 1.9927
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 1.9925
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 1.9923
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 1.9922
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2807 - loss: 1.9921
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2808 - loss: 1.9919
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 1.9917
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 1.9915
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9913
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2814 - loss: 1.9912
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2814 - loss: 1.9910
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2814 - loss: 1.9910 - val_accuracy: 0.2675 - val_loss: 2.0201
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.2224
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3105 - loss: 1.9800  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3122 - loss: 1.9572
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3112 - loss: 1.9545
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3086 - loss: 1.9568
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3062 - loss: 1.9580
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3035 - loss: 1.9598
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3011 - loss: 1.9617
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2990 - loss: 1.9637
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2968 - loss: 1.9662
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2952 - loss: 1.9682
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2938 - loss: 1.9697
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2930 - loss: 1.9706
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2921 - loss: 1.9716
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2913 - loss: 1.9726
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2907 - loss: 1.9736
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2901 - loss: 1.9745
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2895 - loss: 1.9754
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2891 - loss: 1.9759
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2888 - loss: 1.9764
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2886 - loss: 1.9767
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2885 - loss: 1.9769
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2883 - loss: 1.9771
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2882 - loss: 1.9773
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2881 - loss: 1.9775
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2880 - loss: 1.9777
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2878 - loss: 1.9779
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2877 - loss: 1.9781
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2876 - loss: 1.9782
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2874 - loss: 1.9784
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2874 - loss: 1.9785 - val_accuracy: 0.2655 - val_loss: 2.0081
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.1816
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2121 - loss: 2.0836  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2385 - loss: 2.0543
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2466 - loss: 2.0392
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2529 - loss: 2.0319
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2564 - loss: 2.0280
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2594 - loss: 2.0245
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2619 - loss: 2.0207
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2638 - loss: 2.0178
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0155
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0136
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0116
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0100
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2689 - loss: 2.0086
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 2.0075
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0063
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0055
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0048
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0040
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0032
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2725 - loss: 2.0026
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2727 - loss: 2.0018
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2729 - loss: 2.0011
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0005
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2733 - loss: 1.9999
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2735 - loss: 1.9993
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 1.9986
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 1.9980
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2742 - loss: 1.9975
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 1.9969
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2744 - loss: 1.9967 - val_accuracy: 0.2718 - val_loss: 1.9977
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.6580
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2953 - loss: 2.0162  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2892 - loss: 2.0008
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2905 - loss: 1.9950
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2890 - loss: 1.9959
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2882 - loss: 1.9958
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2875 - loss: 1.9942
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2868 - loss: 1.9932
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2864 - loss: 1.9923
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2861 - loss: 1.9918
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2860 - loss: 1.9910
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2859 - loss: 1.9904
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2857 - loss: 1.9901
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2854 - loss: 1.9895
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2852 - loss: 1.9890
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2848 - loss: 1.9886
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2845 - loss: 1.9882
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2843 - loss: 1.9878
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2842 - loss: 1.9873
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2841 - loss: 1.9868
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2841 - loss: 1.9864
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2841 - loss: 1.9859
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2841 - loss: 1.9855
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2841 - loss: 1.9849
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2842 - loss: 1.9843
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2843 - loss: 1.9837
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2843 - loss: 1.9831
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2844 - loss: 1.9825
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2846 - loss: 1.9819
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2847 - loss: 1.9813
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2847 - loss: 1.9812 - val_accuracy: 0.2561 - val_loss: 2.0075

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 632ms/step
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 962us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:01[0m 827ms/step
[1m 59/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 865us/step  
[1m132/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 771us/step
[1m204/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 746us/step
[1m271/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 746us/step
[1m341/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 741us/step
[1m416/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 729us/step
[1m483/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 731us/step
[1m554/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 729us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 19ms/step
[1m67/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 763us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 68/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 749us/step
[1m145/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 699us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 28.53 [%]
Global F1 score (validation) = 24.83 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.14672142 0.18849674 0.1684283  ... 0.00300608 0.12040171 0.01573659]
 [0.15849973 0.18380025 0.16614914 ... 0.00269532 0.11940078 0.01700434]
 [0.15478247 0.2061126  0.16926682 ... 0.00274355 0.12489733 0.01453906]
 ...
 [0.187676   0.20847295 0.19162288 ... 0.00133883 0.14953737 0.02149141]
 [0.1561619  0.18631305 0.169776   ... 0.00258747 0.1480768  0.02073068]
 [0.15384792 0.20953102 0.1601474  ... 0.00194026 0.12796986 0.01358582]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 31.46 [%]
Global accuracy score (test) = 27.99 [%]
Global F1 score (train) = 28.57 [%]
Global F1 score (test) = 25.55 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.14      0.04      0.06       184
 CAMINAR CON MÓVIL O LIBRO       0.16      0.67      0.26       184
       CAMINAR USUAL SPEED       0.07      0.03      0.04       184
            CAMINAR ZIGZAG       0.02      0.01      0.01       184
          DE PIE BARRIENDO       0.25      0.55      0.35       184
   DE PIE DOBLANDO TOALLAS       0.17      0.10      0.13       184
    DE PIE MOVIENDO LIBROS       0.32      0.16      0.22       184
          DE PIE USANDO PC       0.26      0.71      0.38       184
        FASE REPOSO CON K5       0.67      0.62      0.65       184
INCREMENTAL CICLOERGOMETRO       0.65      0.18      0.28       184
           SENTADO LEYENDO       0.26      0.22      0.24       184
         SENTADO USANDO PC       0.27      0.16      0.20       184
      SENTADO VIENDO LA TV       0.54      0.36      0.43       184
   SUBIR Y BAJAR ESCALERAS       0.44      0.06      0.11       184
                    TROTAR       1.00      0.32      0.49       161

                  accuracy                           0.28      2737
                 macro avg       0.35      0.28      0.26      2737
              weighted avg       0.34      0.28      0.25      2737


Accuracy capturado en la ejecución 11: 27.99 [%]
F1-score capturado en la ejecución 11: 25.55 [%]

=== EJECUCIÓN 12 ===

--- TRAIN (ejecución 12) ---

--- TEST (ejecución 12) ---
2025-11-07 14:19:07.829323: 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 14:19:07.841224: 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 00:00:1762521547.854594 2952948 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762521547.858678 2952948 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762521547.868600 2952948 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521547.868619 2952948 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521547.868620 2952948 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521547.868621 2952948 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:19:07.871778: 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 00:00:1762521550.121289 2952948 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762521551.603838 2953078 service.cc:152] XLA service 0x7404e400bfb0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762521551.603863 2953078 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:19:11.630826: 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 00:00:1762521551.775646 2953078 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762521553.209790 2953078 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47:37[0m 2s/step - accuracy: 0.0625 - loss: 3.3162
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0624 - loss: 3.2981  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0633 - loss: 3.2972
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0648 - loss: 3.2934
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0647 - loss: 3.2896
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0648 - loss: 3.2847
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0650 - loss: 3.2789
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0652 - loss: 3.2722
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0654 - loss: 3.2648
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0656 - loss: 3.2584
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0659 - loss: 3.2515
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0661 - loss: 3.2456
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0665 - loss: 3.2393
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0670 - loss: 3.2328
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0675 - loss: 3.2270
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0682 - loss: 3.2208
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0689 - loss: 3.2147
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0695 - loss: 3.2088
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0702 - loss: 3.2030
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0709 - loss: 3.1973
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0717 - loss: 3.1917
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0724 - loss: 3.1861
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0732 - loss: 3.1809
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0739 - loss: 3.1756
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0746 - loss: 3.1707
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0753 - loss: 3.1655
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0761 - loss: 3.1605
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0767 - loss: 3.1563
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0774 - loss: 3.1514
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0777 - loss: 3.1493
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0778 - loss: 3.1492 - val_accuracy: 0.1171 - val_loss: 2.6704
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.0625 - loss: 3.2514
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1301 - loss: 2.8146  
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1330 - loss: 2.8097
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1341 - loss: 2.8059
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1347 - loss: 2.7999
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1347 - loss: 2.7940
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1349 - loss: 2.7885
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1352 - loss: 2.7839
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1352 - loss: 2.7806
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1351 - loss: 2.7778
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1349 - loss: 2.7751
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1348 - loss: 2.7725
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1349 - loss: 2.7700
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1350 - loss: 2.7677
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1350 - loss: 2.7654
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1350 - loss: 2.7634
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1349 - loss: 2.7614
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1348 - loss: 2.7593
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1347 - loss: 2.7573
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1346 - loss: 2.7552
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1345 - loss: 2.7534
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1343 - loss: 2.7517
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1341 - loss: 2.7499
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1340 - loss: 2.7481
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1340 - loss: 2.7465
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1340 - loss: 2.7446
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1340 - loss: 2.7428
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1340 - loss: 2.7409
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1340 - loss: 2.7390
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.1340 - loss: 2.7371
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1340 - loss: 2.7371 - val_accuracy: 0.1188 - val_loss: 2.5560
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.4906
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1739 - loss: 2.5896  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1671 - loss: 2.5908
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1648 - loss: 2.5837
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1620 - loss: 2.5771
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1595 - loss: 2.5728
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1579 - loss: 2.5704
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1567 - loss: 2.5679
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1557 - loss: 2.5655
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1549 - loss: 2.5633
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1542 - loss: 2.5618
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1538 - loss: 2.5603
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1535 - loss: 2.5588
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1533 - loss: 2.5574
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1531 - loss: 2.5561
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1528 - loss: 2.5552
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1526 - loss: 2.5543
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1525 - loss: 2.5534
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1524 - loss: 2.5525
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1523 - loss: 2.5516
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1522 - loss: 2.5507
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1521 - loss: 2.5498
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1520 - loss: 2.5490
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1519 - loss: 2.5483
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1519 - loss: 2.5474
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1519 - loss: 2.5465
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1518 - loss: 2.5456
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1518 - loss: 2.5448
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1518 - loss: 2.5440
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.1518 - loss: 2.5432
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1518 - loss: 2.5432 - val_accuracy: 0.1541 - val_loss: 2.4571
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.0625 - loss: 2.8712
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1749 - loss: 2.4857  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1702 - loss: 2.4851
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1687 - loss: 2.4818
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1686 - loss: 2.4779
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1682 - loss: 2.4763
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1677 - loss: 2.4757
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1671 - loss: 2.4746
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1669 - loss: 2.4732
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1664 - loss: 2.4722
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1659 - loss: 2.4713
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1655 - loss: 2.4704
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1651 - loss: 2.4696
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1649 - loss: 2.4690
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1648 - loss: 2.4684
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1646 - loss: 2.4678
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1644 - loss: 2.4672
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1643 - loss: 2.4665
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1641 - loss: 2.4658
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1641 - loss: 2.4652
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1640 - loss: 2.4648
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1640 - loss: 2.4642
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1640 - loss: 2.4636
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1640 - loss: 2.4631
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1640 - loss: 2.4627
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1641 - loss: 2.4622
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1641 - loss: 2.4618
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1641 - loss: 2.4614
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1641 - loss: 2.4611
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1641 - loss: 2.4608 - val_accuracy: 0.1750 - val_loss: 2.4079
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.3724
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1577 - loss: 2.4135  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1588 - loss: 2.4176
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1604 - loss: 2.4165
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1621 - loss: 2.4143
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1644 - loss: 2.4140
[1m 249/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1658 - loss: 2.4140
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1665 - loss: 2.4146
[1m 333/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1671 - loss: 2.4151
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1676 - loss: 2.4153
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1680 - loss: 2.4152
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1683 - loss: 2.4151
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1686 - loss: 2.4149
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1688 - loss: 2.4147
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1692 - loss: 2.4144
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1695 - loss: 2.4140
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1699 - loss: 2.4137
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1702 - loss: 2.4134
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1704 - loss: 2.4132
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1706 - loss: 2.4131
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1708 - loss: 2.4131
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1709 - loss: 2.4131
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1710 - loss: 2.4132
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1711 - loss: 2.4133
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1711 - loss: 2.4133
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1712 - loss: 2.4133
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1712 - loss: 2.4132
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1713 - loss: 2.4131
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1713 - loss: 2.4129
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.1714 - loss: 2.4127
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1714 - loss: 2.4127 - val_accuracy: 0.1970 - val_loss: 2.3811
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.1468
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1721 - loss: 2.3387  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1742 - loss: 2.3528
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1746 - loss: 2.3633
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1760 - loss: 2.3668
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1774 - loss: 2.3700
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1783 - loss: 2.3724
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1787 - loss: 2.3733
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1789 - loss: 2.3735
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1793 - loss: 2.3740
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1795 - loss: 2.3745
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1797 - loss: 2.3743
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1798 - loss: 2.3743
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1798 - loss: 2.3744
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1797 - loss: 2.3746
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1796 - loss: 2.3749
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1796 - loss: 2.3748
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1796 - loss: 2.3749
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1796 - loss: 2.3749
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1796 - loss: 2.3750
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1796 - loss: 2.3751
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1797 - loss: 2.3751
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1798 - loss: 2.3751
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1798 - loss: 2.3751
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1799 - loss: 2.3751
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1799 - loss: 2.3751
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1799 - loss: 2.3751
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1799 - loss: 2.3751
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1799 - loss: 2.3751
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1799 - loss: 2.3751 - val_accuracy: 0.1735 - val_loss: 2.3606
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.0625 - loss: 2.3742
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1750 - loss: 2.3510  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1751 - loss: 2.3608
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1710 - loss: 2.3665
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1699 - loss: 2.3667
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1703 - loss: 2.3663
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1708 - loss: 2.3666
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1705 - loss: 2.3674
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1704 - loss: 2.3677
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1707 - loss: 2.3675
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1712 - loss: 2.3671
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1717 - loss: 2.3667
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1720 - loss: 2.3665
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1724 - loss: 2.3662
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1729 - loss: 2.3661
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1734 - loss: 2.3659
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1740 - loss: 2.3656
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1745 - loss: 2.3653
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1749 - loss: 2.3649
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1753 - loss: 2.3645
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1758 - loss: 2.3640
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1763 - loss: 2.3634
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1767 - loss: 2.3630
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1771 - loss: 2.3626
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1776 - loss: 2.3622
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1780 - loss: 2.3618
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1783 - loss: 2.3614
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1787 - loss: 2.3609
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1789 - loss: 2.3605
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1792 - loss: 2.3601
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1792 - loss: 2.3601 - val_accuracy: 0.2154 - val_loss: 2.3225
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0000e+00 - loss: 2.7539
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1791 - loss: 2.3795      
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1836 - loss: 2.3643
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1840 - loss: 2.3619
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1839 - loss: 2.3601
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1842 - loss: 2.3580
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1847 - loss: 2.3558
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1852 - loss: 2.3541
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1855 - loss: 2.3518
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1858 - loss: 2.3499
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1859 - loss: 2.3480
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1860 - loss: 2.3462
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1862 - loss: 2.3447
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1867 - loss: 2.3432
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1871 - loss: 2.3421
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1873 - loss: 2.3411
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1876 - loss: 2.3401
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1878 - loss: 2.3392
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1880 - loss: 2.3383
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1881 - loss: 2.3377
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1882 - loss: 2.3372
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1884 - loss: 2.3365
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1885 - loss: 2.3359
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1886 - loss: 2.3354
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1887 - loss: 2.3350
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1888 - loss: 2.3346
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1889 - loss: 2.3342
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1890 - loss: 2.3339
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1892 - loss: 2.3335
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1894 - loss: 2.3331 - val_accuracy: 0.2244 - val_loss: 2.2892
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.0893
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1823 - loss: 2.3291  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1745 - loss: 2.3285
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1765 - loss: 2.3270
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1800 - loss: 2.3228
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1826 - loss: 2.3205
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1839 - loss: 2.3196
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1851 - loss: 2.3184
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1862 - loss: 2.3175
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1871 - loss: 2.3164
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1877 - loss: 2.3159
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1883 - loss: 2.3151
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1887 - loss: 2.3143
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1891 - loss: 2.3137
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1894 - loss: 2.3133
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1897 - loss: 2.3128
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1899 - loss: 2.3124
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1902 - loss: 2.3120
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1905 - loss: 2.3116
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1907 - loss: 2.3111
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1910 - loss: 2.3106
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1913 - loss: 2.3101
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1915 - loss: 2.3098
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1917 - loss: 2.3094
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1918 - loss: 2.3091
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1920 - loss: 2.3088
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1921 - loss: 2.3083
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1923 - loss: 2.3079
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1925 - loss: 2.3076
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1926 - loss: 2.3072
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1927 - loss: 2.3071 - val_accuracy: 0.2427 - val_loss: 2.2570
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 2.2241
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1924 - loss: 2.3023  
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1920 - loss: 2.3021
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1917 - loss: 2.3052
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1913 - loss: 2.3086
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1912 - loss: 2.3092
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1911 - loss: 2.3087
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1911 - loss: 2.3083
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1912 - loss: 2.3072
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1912 - loss: 2.3065
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1911 - loss: 2.3061
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1911 - loss: 2.3060
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1911 - loss: 2.3057
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1912 - loss: 2.3049
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1914 - loss: 2.3040
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1916 - loss: 2.3032
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1918 - loss: 2.3024
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1920 - loss: 2.3017
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1923 - loss: 2.3009
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1925 - loss: 2.3001
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1928 - loss: 2.2994
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1930 - loss: 2.2987
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1933 - loss: 2.2981
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1935 - loss: 2.2975
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1937 - loss: 2.2969
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1939 - loss: 2.2963
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1941 - loss: 2.2958
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1944 - loss: 2.2953
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1946 - loss: 2.2948
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1947 - loss: 2.2944 - val_accuracy: 0.2461 - val_loss: 2.2568
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.2837
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1773 - loss: 2.2806  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1913 - loss: 2.2647
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1981 - loss: 2.2560
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2004 - loss: 2.2526
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2012 - loss: 2.2506
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2019 - loss: 2.2494
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2018 - loss: 2.2491
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2018 - loss: 2.2487
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2019 - loss: 2.2485
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2018 - loss: 2.2488
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2017 - loss: 2.2491
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2016 - loss: 2.2496
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2016 - loss: 2.2501
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2018 - loss: 2.2504
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2019 - loss: 2.2506
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2021 - loss: 2.2508
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2022 - loss: 2.2508
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2024 - loss: 2.2509
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2026 - loss: 2.2510
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2028 - loss: 2.2511
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2030 - loss: 2.2511
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2032 - loss: 2.2512
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2034 - loss: 2.2513
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2035 - loss: 2.2514
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2037 - loss: 2.2515
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2039 - loss: 2.2517
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2041 - loss: 2.2518
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2042 - loss: 2.2520
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2044 - loss: 2.2521 - val_accuracy: 0.2442 - val_loss: 2.2078
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.2987
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1988 - loss: 2.2143  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2055 - loss: 2.2138
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2058 - loss: 2.2211
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2061 - loss: 2.2255
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2069 - loss: 2.2281
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2079 - loss: 2.2297
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2084 - loss: 2.2316
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2089 - loss: 2.2331
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2091 - loss: 2.2340
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2091 - loss: 2.2348
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2089 - loss: 2.2356
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2088 - loss: 2.2363
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2085 - loss: 2.2372
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2082 - loss: 2.2381
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2080 - loss: 2.2386
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2080 - loss: 2.2391
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2080 - loss: 2.2394
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2081 - loss: 2.2396
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2081 - loss: 2.2398
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2081 - loss: 2.2399
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2081 - loss: 2.2400
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2081 - loss: 2.2401
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2081 - loss: 2.2402
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2081 - loss: 2.2402
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2080 - loss: 2.2403
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2080 - loss: 2.2403
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2079 - loss: 2.2404
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2079 - loss: 2.2404
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2079 - loss: 2.2403 - val_accuracy: 0.2500 - val_loss: 2.1927
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.2665
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2031 - loss: 2.2161  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2125 - loss: 2.2140
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2133 - loss: 2.2156
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2133 - loss: 2.2141
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2133 - loss: 2.2131
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2130 - loss: 2.2132
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2130 - loss: 2.2145
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2130 - loss: 2.2157
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2133 - loss: 2.2171
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2137 - loss: 2.2180
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2140 - loss: 2.2186
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2144 - loss: 2.2189
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2146 - loss: 2.2192
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2147 - loss: 2.2195
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2148 - loss: 2.2198
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2150 - loss: 2.2201
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2152 - loss: 2.2204
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2152 - loss: 2.2207
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2153 - loss: 2.2209
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2154 - loss: 2.2211
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2154 - loss: 2.2212
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2155 - loss: 2.2213
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2155 - loss: 2.2214
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2155 - loss: 2.2214
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2155 - loss: 2.2215
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2154 - loss: 2.2216
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2154 - loss: 2.2216
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2154 - loss: 2.2217
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2154 - loss: 2.2217 - val_accuracy: 0.2622 - val_loss: 2.1730
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.2616
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1788 - loss: 2.2166  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1921 - loss: 2.2083
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1997 - loss: 2.2040
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2052 - loss: 2.2032
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2076 - loss: 2.2045
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2093 - loss: 2.2057
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2105 - loss: 2.2060
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2110 - loss: 2.2062
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2114 - loss: 2.2062
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2118 - loss: 2.2063
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2121 - loss: 2.2067
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2125 - loss: 2.2070
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2128 - loss: 2.2073
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2132 - loss: 2.2073
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2136 - loss: 2.2072
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2139 - loss: 2.2071
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2141 - loss: 2.2070
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2143 - loss: 2.2072
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2144 - loss: 2.2072
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2146 - loss: 2.2072
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2149 - loss: 2.2073
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2151 - loss: 2.2073
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2153 - loss: 2.2073
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2155 - loss: 2.2072
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2157 - loss: 2.2070
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2159 - loss: 2.2069
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2160 - loss: 2.2068
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2161 - loss: 2.2068
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2162 - loss: 2.2067 - val_accuracy: 0.2544 - val_loss: 2.1443
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.4226
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1684 - loss: 2.2547  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1841 - loss: 2.2405
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1893 - loss: 2.2344
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1938 - loss: 2.2291
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1972 - loss: 2.2235
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2002 - loss: 2.2196
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2026 - loss: 2.2164
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2045 - loss: 2.2139
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2060 - loss: 2.2124
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2072 - loss: 2.2110
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2083 - loss: 2.2097
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2089 - loss: 2.2088
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2096 - loss: 2.2079
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2103 - loss: 2.2072
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2108 - loss: 2.2063
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2113 - loss: 2.2055
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2118 - loss: 2.2049
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2123 - loss: 2.2042
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2128 - loss: 2.2037
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2132 - loss: 2.2032
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2137 - loss: 2.2026
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2141 - loss: 2.2022
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2145 - loss: 2.2019
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2148 - loss: 2.2016
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2152 - loss: 2.2012
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2155 - loss: 2.2010
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2158 - loss: 2.2007
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2160 - loss: 2.2004
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2163 - loss: 2.2002 - val_accuracy: 0.2631 - val_loss: 2.1318
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.1973
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2050 - loss: 2.1410  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2154 - loss: 2.1438
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2187 - loss: 2.1487
[1m 149/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2187 - loss: 2.1550
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2196 - loss: 2.1572
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2208 - loss: 2.1586
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2217 - loss: 2.1606
[1m 306/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2224 - loss: 2.1621
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2227 - loss: 2.1632
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2230 - loss: 2.1638
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2232 - loss: 2.1642
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2233 - loss: 2.1645
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2235 - loss: 2.1646
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2236 - loss: 2.1647
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2237 - loss: 2.1649
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2238 - loss: 2.1652
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2239 - loss: 2.1655
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2240 - loss: 2.1657
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2240 - loss: 2.1660
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2240 - loss: 2.1663
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2240 - loss: 2.1666
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2240 - loss: 2.1669
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2241 - loss: 2.1671
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2242 - loss: 2.1673
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2243 - loss: 2.1674
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2244 - loss: 2.1675
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2246 - loss: 2.1675
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2247 - loss: 2.1675
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2249 - loss: 2.1675
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2250 - loss: 2.1675 - val_accuracy: 0.2688 - val_loss: 2.1257
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 1.9798
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2371 - loss: 2.1250  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2428 - loss: 2.1178
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2404 - loss: 2.1258
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2395 - loss: 2.1322
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2393 - loss: 2.1362
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2393 - loss: 2.1388
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2395 - loss: 2.1401
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2397 - loss: 2.1416
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2401 - loss: 2.1427
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2405 - loss: 2.1437
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2407 - loss: 2.1445
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2410 - loss: 2.1449
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2413 - loss: 2.1455
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2415 - loss: 2.1462
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2415 - loss: 2.1466
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2415 - loss: 2.1470
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2414 - loss: 2.1472
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2412 - loss: 2.1476
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2410 - loss: 2.1478
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2408 - loss: 2.1481
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2405 - loss: 2.1485
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2403 - loss: 2.1487
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2403 - loss: 2.1488
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2402 - loss: 2.1488
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2402 - loss: 2.1488
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2401 - loss: 2.1488
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2400 - loss: 2.1488
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2400 - loss: 2.1488
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2399 - loss: 2.1488 - val_accuracy: 0.2783 - val_loss: 2.1070
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.4589
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2465 - loss: 2.2008  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2327 - loss: 2.2055
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2289 - loss: 2.1991
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2288 - loss: 2.1943
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2292 - loss: 2.1900
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2293 - loss: 2.1875
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2295 - loss: 2.1851
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2296 - loss: 2.1830
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2296 - loss: 2.1812
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2295 - loss: 2.1795
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2294 - loss: 2.1780
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2294 - loss: 2.1768
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2296 - loss: 2.1758
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2297 - loss: 2.1747
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2300 - loss: 2.1735
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2302 - loss: 2.1726
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2303 - loss: 2.1716
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2305 - loss: 2.1707
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2307 - loss: 2.1698
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2309 - loss: 2.1689
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2311 - loss: 2.1681
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2313 - loss: 2.1673
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2316 - loss: 2.1664
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2318 - loss: 2.1655
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2320 - loss: 2.1647
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2323 - loss: 2.1639
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2325 - loss: 2.1630
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2327 - loss: 2.1622
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2329 - loss: 2.1614
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2329 - loss: 2.1613 - val_accuracy: 0.2945 - val_loss: 2.0731
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 20ms/step - accuracy: 0.1875 - loss: 2.1611
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2389 - loss: 2.1140  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2442 - loss: 2.1076
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2448 - loss: 2.1116
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2427 - loss: 2.1155
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2413 - loss: 2.1176
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2403 - loss: 2.1203
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2402 - loss: 2.1219
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2400 - loss: 2.1232
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2401 - loss: 2.1243
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2401 - loss: 2.1251
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2400 - loss: 2.1257
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2401 - loss: 2.1258
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2402 - loss: 2.1256
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2402 - loss: 2.1252
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2402 - loss: 2.1249
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2402 - loss: 2.1248
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2402 - loss: 2.1247
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2402 - loss: 2.1244
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2402 - loss: 2.1242
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2402 - loss: 2.1239
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2402 - loss: 2.1236
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2402 - loss: 2.1234
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2402 - loss: 2.1232
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2402 - loss: 2.1230
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2403 - loss: 2.1228
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2404 - loss: 2.1226
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2404 - loss: 2.1225
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2405 - loss: 2.1224
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2405 - loss: 2.1223
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2405 - loss: 2.1223 - val_accuracy: 0.2809 - val_loss: 2.0611
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 1.9521
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2234 - loss: 2.1121  
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2316 - loss: 2.1260
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2330 - loss: 2.1319
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2337 - loss: 2.1349
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2347 - loss: 2.1347
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2359 - loss: 2.1345
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2368 - loss: 2.1341
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2374 - loss: 2.1340
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2379 - loss: 2.1339
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2386 - loss: 2.1330
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2392 - loss: 2.1318
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2397 - loss: 2.1306
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2401 - loss: 2.1297
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2405 - loss: 2.1288
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2408 - loss: 2.1282
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2410 - loss: 2.1276
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2412 - loss: 2.1271
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2413 - loss: 2.1267
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2415 - loss: 2.1263
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2417 - loss: 2.1258
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2418 - loss: 2.1253
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1249
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1245
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1242
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1238
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1234
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1231
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1226
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2420 - loss: 2.1221
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2421 - loss: 2.1218 - val_accuracy: 0.2907 - val_loss: 2.0456
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 1.8001
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2205 - loss: 2.1320  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2159 - loss: 2.1432
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2184 - loss: 2.1422
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2191 - loss: 2.1400
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2204 - loss: 2.1393
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2218 - loss: 2.1387
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2232 - loss: 2.1372
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2246 - loss: 2.1353
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2260 - loss: 2.1332
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2272 - loss: 2.1309
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.1289
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2293 - loss: 2.1268
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2302 - loss: 2.1250
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2310 - loss: 2.1232
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2317 - loss: 2.1218
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2325 - loss: 2.1203
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2331 - loss: 2.1189
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2337 - loss: 2.1177
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2341 - loss: 2.1168
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2345 - loss: 2.1158
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2349 - loss: 2.1149
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2353 - loss: 2.1140
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2357 - loss: 2.1131
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2359 - loss: 2.1123
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2362 - loss: 2.1116
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2364 - loss: 2.1109
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2367 - loss: 2.1102
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2369 - loss: 2.1094
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2372 - loss: 2.1088
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2373 - loss: 2.1084 - val_accuracy: 0.2999 - val_loss: 2.0326
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0000e+00 - loss: 2.3376
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2115 - loss: 2.1673      
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2240 - loss: 2.1299
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2289 - loss: 2.1153
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2338 - loss: 2.1053
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2370 - loss: 2.1004
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2387 - loss: 2.0976
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2397 - loss: 2.0963
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2405 - loss: 2.0958
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2409 - loss: 2.0953
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2413 - loss: 2.0948
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2418 - loss: 2.0936
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2421 - loss: 2.0927
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2425 - loss: 2.0918
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2429 - loss: 2.0910
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2433 - loss: 2.0903
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2435 - loss: 2.0897
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2438 - loss: 2.0891
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2442 - loss: 2.0884
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2445 - loss: 2.0878
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2449 - loss: 2.0873
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.0868
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.0864
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.0860
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2459 - loss: 2.0856
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2461 - loss: 2.0852
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2463 - loss: 2.0847
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2465 - loss: 2.0843
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2468 - loss: 2.0839
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2470 - loss: 2.0836
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2471 - loss: 2.0833 - val_accuracy: 0.2881 - val_loss: 2.0136
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.3767
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2632 - loss: 2.0926  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2619 - loss: 2.0824
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2625 - loss: 2.0710
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2646 - loss: 2.0638
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2638 - loss: 2.0622
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2623 - loss: 2.0626
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0624
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2597 - loss: 2.0631
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2587 - loss: 2.0640
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2579 - loss: 2.0647
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0650
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0651
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2564 - loss: 2.0646
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0639
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0634
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0632
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2558 - loss: 2.0631
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2557 - loss: 2.0629
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2555 - loss: 2.0627
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2553 - loss: 2.0625
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2551 - loss: 2.0623
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2550 - loss: 2.0622
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2549 - loss: 2.0620
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0618
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2547 - loss: 2.0617
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2546 - loss: 2.0617
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2545 - loss: 2.0619
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.0619
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2542 - loss: 2.0621
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2542 - loss: 2.0621 - val_accuracy: 0.2949 - val_loss: 2.0140
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.8418
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2605 - loss: 2.0886  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2598 - loss: 2.0665
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2613 - loss: 2.0598
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2634 - loss: 2.0543
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0481
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0450
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0427
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0416
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0413
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2680 - loss: 2.0412
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0411
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2680 - loss: 2.0412
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0412
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0412
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0411
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0411
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0412
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0412
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0413
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0415
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0417
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0420
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0421
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0423
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0424
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2648 - loss: 2.0425
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2646 - loss: 2.0426
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0426
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2643 - loss: 2.0427 - val_accuracy: 0.2949 - val_loss: 1.9892
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.8894
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0244  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2641 - loss: 2.0276
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0283
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2596 - loss: 2.0266
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2592 - loss: 2.0243
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2588 - loss: 2.0238
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2585 - loss: 2.0232
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2583 - loss: 2.0228
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0230
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.0233
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2575 - loss: 2.0239
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0246
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0255
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2570 - loss: 2.0265
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.0276
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0285
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0293
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0299
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2566 - loss: 2.0303
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2566 - loss: 2.0307
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.0312
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0316
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0320
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2562 - loss: 2.0324
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0328
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0332
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0335
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0338
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0341
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2561 - loss: 2.0341 - val_accuracy: 0.2799 - val_loss: 2.0135

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m52s[0m 622ms/step
[1m66/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 779us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:04[0m 831ms/step
[1m 63/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 807us/step  
[1m137/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 737us/step
[1m207/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 732us/step
[1m277/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 729us/step
[1m351/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 718us/step
[1m425/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 712us/step
[1m493/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 717us/step
[1m563/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 717us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m68/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 753us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 68/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 756us/step
[1m139/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 730us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 25.61 [%]
Global F1 score (validation) = 23.68 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.20575365 0.1850005  0.23953867 ... 0.00180784 0.1434782  0.01639744]
 [0.2063491  0.16907056 0.19147651 ... 0.00306995 0.18629439 0.02347545]
 [0.16828679 0.16134368 0.18330024 ... 0.00487792 0.12999897 0.0139072 ]
 ...
 [0.20735238 0.19245285 0.18008453 ... 0.00299522 0.19792251 0.02217507]
 [0.17751926 0.19431554 0.19270313 ... 0.00261581 0.16709085 0.01693159]
 [0.17452364 0.16778308 0.18530226 ... 0.00439759 0.15420051 0.0136307 ]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 32.07 [%]
Global accuracy score (test) = 26.49 [%]
Global F1 score (train) = 30.46 [%]
Global F1 score (test) = 25.14 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.19      0.53      0.28       184
 CAMINAR CON MÓVIL O LIBRO       0.24      0.30      0.27       184
       CAMINAR USUAL SPEED       0.20      0.12      0.15       184
            CAMINAR ZIGZAG       0.50      0.03      0.05       184
          DE PIE BARRIENDO       0.19      0.29      0.23       184
   DE PIE DOBLANDO TOALLAS       0.27      0.23      0.25       184
    DE PIE MOVIENDO LIBROS       0.27      0.19      0.22       184
          DE PIE USANDO PC       0.26      0.78      0.39       184
        FASE REPOSO CON K5       0.98      0.27      0.43       184
INCREMENTAL CICLOERGOMETRO       0.48      0.21      0.29       184
           SENTADO LEYENDO       0.22      0.38      0.28       184
         SENTADO USANDO PC       0.13      0.05      0.07       184
      SENTADO VIENDO LA TV       0.31      0.12      0.18       184
   SUBIR Y BAJAR ESCALERAS       0.24      0.12      0.16       184
                    TROTAR       1.00      0.36      0.53       161

                  accuracy                           0.26      2737
                 macro avg       0.36      0.27      0.25      2737
              weighted avg       0.36      0.26      0.25      2737


Accuracy capturado en la ejecución 12: 26.49 [%]
F1-score capturado en la ejecución 12: 25.14 [%]

=== EJECUCIÓN 13 ===

--- TRAIN (ejecución 13) ---

--- TEST (ejecución 13) ---
2025-11-07 14:20:15.074662: 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 14:20:15.086714: 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 00:00:1762521615.102591 2956697 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762521615.106908 2956697 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762521615.117653 2956697 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521615.117675 2956697 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521615.117677 2956697 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521615.117678 2956697 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:20:15.120870: 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 00:00:1762521617.404304 2956697 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762521618.891997 2956827 service.cc:152] XLA service 0x72dcf000d2c0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762521618.892025 2956827 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:20:18.918870: 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 00:00:1762521619.070085 2956827 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762521620.483285 2956827 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47:28[0m 2s/step - accuracy: 0.0000e+00 - loss: 3.6763
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0536 - loss: 3.3427      
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0594 - loss: 3.2907
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0620 - loss: 3.2639
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0635 - loss: 3.2472
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0645 - loss: 3.2318
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0656 - loss: 3.2158
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0667 - loss: 3.2014
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0676 - loss: 3.1898
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0686 - loss: 3.1783
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0697 - loss: 3.1677
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0709 - loss: 3.1564
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0719 - loss: 3.1472
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0729 - loss: 3.1381
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0740 - loss: 3.1285
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0749 - loss: 3.1201
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0758 - loss: 3.1113
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0767 - loss: 3.1033
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0776 - loss: 3.0951
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0784 - loss: 3.0874
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0794 - loss: 3.0792
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0802 - loss: 3.0730
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0811 - loss: 3.0655
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0819 - loss: 3.0588
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0826 - loss: 3.0525
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0834 - loss: 3.0462
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0840 - loss: 3.0404
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0847 - loss: 3.0343
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0854 - loss: 3.0284
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0860 - loss: 3.0226
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0861 - loss: 3.0224
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0861 - loss: 3.0222 - val_accuracy: 0.1560 - val_loss: 2.5309
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.9296
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1218 - loss: 2.6698  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1247 - loss: 2.6753
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1253 - loss: 2.6731
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1275 - loss: 2.6701
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1289 - loss: 2.6671
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1300 - loss: 2.6641
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1308 - loss: 2.6617
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1317 - loss: 2.6592
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1326 - loss: 2.6571
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1336 - loss: 2.6552
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1344 - loss: 2.6535
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1352 - loss: 2.6516
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1360 - loss: 2.6498
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1367 - loss: 2.6479
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1373 - loss: 2.6464
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1380 - loss: 2.6448
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1386 - loss: 2.6432
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1392 - loss: 2.6415
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1398 - loss: 2.6398
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1404 - loss: 2.6382
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1409 - loss: 2.6366
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1414 - loss: 2.6350
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1419 - loss: 2.6334
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1424 - loss: 2.6317
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1428 - loss: 2.6302
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1432 - loss: 2.6289
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1437 - loss: 2.6274
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1441 - loss: 2.6261
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1444 - loss: 2.6251 - val_accuracy: 0.2026 - val_loss: 2.4193
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.5678
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1798 - loss: 2.5127  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1835 - loss: 2.5082
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1845 - loss: 2.5059
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1832 - loss: 2.5054
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1820 - loss: 2.5070
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1811 - loss: 2.5071
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1806 - loss: 2.5060
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1805 - loss: 2.5048
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1804 - loss: 2.5034
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1805 - loss: 2.5022
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1806 - loss: 2.5011
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1805 - loss: 2.5004
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1804 - loss: 2.4998
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1804 - loss: 2.4991
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1805 - loss: 2.4984
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1806 - loss: 2.4977
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1807 - loss: 2.4970
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1808 - loss: 2.4963
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1810 - loss: 2.4954
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1812 - loss: 2.4946
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1813 - loss: 2.4937
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1814 - loss: 2.4928
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1815 - loss: 2.4919
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1817 - loss: 2.4909
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1818 - loss: 2.4900
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1820 - loss: 2.4890
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1821 - loss: 2.4881
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1823 - loss: 2.4872
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1823 - loss: 2.4869 - val_accuracy: 0.2120 - val_loss: 2.3415
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 2.5765
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2050 - loss: 2.4113  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2016 - loss: 2.4078
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2002 - loss: 2.4050
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1992 - loss: 2.4053
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1983 - loss: 2.4057
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1980 - loss: 2.4046
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1980 - loss: 2.4034
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1979 - loss: 2.4020
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1977 - loss: 2.4004
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1976 - loss: 2.3998
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1975 - loss: 2.3993
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1976 - loss: 2.3990
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1977 - loss: 2.3984
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1978 - loss: 2.3981
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1978 - loss: 2.3978
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1978 - loss: 2.3976
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1978 - loss: 2.3974
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1978 - loss: 2.3971
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1978 - loss: 2.3968
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1979 - loss: 2.3964
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1980 - loss: 2.3960
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1981 - loss: 2.3956
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1982 - loss: 2.3952
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1984 - loss: 2.3947
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1985 - loss: 2.3943
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1986 - loss: 2.3939
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1988 - loss: 2.3935
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1989 - loss: 2.3930
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1990 - loss: 2.3926 - val_accuracy: 0.2300 - val_loss: 2.2665
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.7214
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2198 - loss: 2.3791  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2238 - loss: 2.3579
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2246 - loss: 2.3474
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2258 - loss: 2.3401
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2257 - loss: 2.3356
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2249 - loss: 2.3332
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2240 - loss: 2.3319
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2231 - loss: 2.3309
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2222 - loss: 2.3306
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2217 - loss: 2.3304
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2213 - loss: 2.3301
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2210 - loss: 2.3298
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2208 - loss: 2.3294
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2206 - loss: 2.3289
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2204 - loss: 2.3286
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2202 - loss: 2.3283
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2201 - loss: 2.3279
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2201 - loss: 2.3277
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2200 - loss: 2.3275
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2199 - loss: 2.3273
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2198 - loss: 2.3271
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2197 - loss: 2.3270
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2197 - loss: 2.3268
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2196 - loss: 2.3267
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2195 - loss: 2.3266
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2194 - loss: 2.3264
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2193 - loss: 2.3262
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2192 - loss: 2.3260
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2192 - loss: 2.3260 - val_accuracy: 0.2392 - val_loss: 2.2310
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 1.9335
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2089 - loss: 2.2662  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2064 - loss: 2.2913
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2066 - loss: 2.3029
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2075 - loss: 2.3065
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2096 - loss: 2.3077
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2107 - loss: 2.3088
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2112 - loss: 2.3090
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2122 - loss: 2.3079
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2133 - loss: 2.3067
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2142 - loss: 2.3058
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2150 - loss: 2.3051
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2154 - loss: 2.3045
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2158 - loss: 2.3036
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2163 - loss: 2.3026
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2166 - loss: 2.3017
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2171 - loss: 2.3007
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2174 - loss: 2.3000
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2177 - loss: 2.2992
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2179 - loss: 2.2986
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2181 - loss: 2.2982
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2183 - loss: 2.2976
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2184 - loss: 2.2971
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2186 - loss: 2.2966
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2188 - loss: 2.2960
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2190 - loss: 2.2953
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2192 - loss: 2.2947
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2194 - loss: 2.2940
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2196 - loss: 2.2934
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.2198 - loss: 2.2928
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2198 - loss: 2.2927 - val_accuracy: 0.2435 - val_loss: 2.1840
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.0872
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2093 - loss: 2.2629  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2206 - loss: 2.2600
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2238 - loss: 2.2597
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2269 - loss: 2.2548
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2273 - loss: 2.2536
[1m 249/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2268 - loss: 2.2544
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2264 - loss: 2.2549
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2261 - loss: 2.2550
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2258 - loss: 2.2552
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2256 - loss: 2.2555
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2256 - loss: 2.2555
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2256 - loss: 2.2553
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2255 - loss: 2.2552
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2255 - loss: 2.2551
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2254 - loss: 2.2550
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2254 - loss: 2.2547
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2256 - loss: 2.2543
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2258 - loss: 2.2538
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2259 - loss: 2.2533
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2261 - loss: 2.2528
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2262 - loss: 2.2525
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2262 - loss: 2.2523
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2263 - loss: 2.2522
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2263 - loss: 2.2520
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2264 - loss: 2.2517
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2265 - loss: 2.2514
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2265 - loss: 2.2511
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2266 - loss: 2.2508
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2266 - loss: 2.2508 - val_accuracy: 0.2500 - val_loss: 2.1386
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.9594
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2891 - loss: 2.1311  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2651 - loss: 2.1674
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2544 - loss: 2.1848
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2504 - loss: 2.1917
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2473 - loss: 2.1980
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2450 - loss: 2.2032
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2432 - loss: 2.2065
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2418 - loss: 2.2092
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2407 - loss: 2.2110
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2399 - loss: 2.2121
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2392 - loss: 2.2128
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2387 - loss: 2.2132
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2383 - loss: 2.2133
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2379 - loss: 2.2134
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2378 - loss: 2.2133
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2378 - loss: 2.2130
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2377 - loss: 2.2129
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2377 - loss: 2.2127
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2376 - loss: 2.2125
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2377 - loss: 2.2122
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2377 - loss: 2.2121
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2377 - loss: 2.2119
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2377 - loss: 2.2119
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2377 - loss: 2.2118
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2377 - loss: 2.2117
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2377 - loss: 2.2115
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2377 - loss: 2.2115
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2377 - loss: 2.2114
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2377 - loss: 2.2113 - val_accuracy: 0.2549 - val_loss: 2.1307
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.8816
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2555 - loss: 2.1796  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2483 - loss: 2.1901
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2449 - loss: 2.1965
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2431 - loss: 2.2004
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2416 - loss: 2.2035
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2404 - loss: 2.2055
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2391 - loss: 2.2067
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2383 - loss: 2.2075
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2377 - loss: 2.2078
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2372 - loss: 2.2080
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2370 - loss: 2.2075
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2368 - loss: 2.2070
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2367 - loss: 2.2064
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2366 - loss: 2.2058
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2367 - loss: 2.2052
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2368 - loss: 2.2046
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2370 - loss: 2.2041
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2371 - loss: 2.2037
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2371 - loss: 2.2031
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2371 - loss: 2.2027
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2372 - loss: 2.2021
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2373 - loss: 2.2015
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2374 - loss: 2.2008
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2376 - loss: 2.2002
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2377 - loss: 2.1995
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2379 - loss: 2.1988
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2380 - loss: 2.1982
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2381 - loss: 2.1977
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2382 - loss: 2.1972 - val_accuracy: 0.2588 - val_loss: 2.1229
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.4375 - loss: 2.1207
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2765 - loss: 2.1317  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2685 - loss: 2.1399
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2634 - loss: 2.1461
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2598 - loss: 2.1497
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2564 - loss: 2.1548
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2542 - loss: 2.1587
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2524 - loss: 2.1612
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2511 - loss: 2.1636
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2499 - loss: 2.1660
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2490 - loss: 2.1678
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2484 - loss: 2.1686
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2480 - loss: 2.1691
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2476 - loss: 2.1693
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2474 - loss: 2.1692
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2472 - loss: 2.1691
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2471 - loss: 2.1689
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2469 - loss: 2.1687
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2469 - loss: 2.1684
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2469 - loss: 2.1681
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2469 - loss: 2.1678
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2469 - loss: 2.1675
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2469 - loss: 2.1672
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2469 - loss: 2.1671
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2468 - loss: 2.1669
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2468 - loss: 2.1668
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2467 - loss: 2.1667
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2466 - loss: 2.1666
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2466 - loss: 2.1666
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2465 - loss: 2.1665
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2465 - loss: 2.1665 - val_accuracy: 0.2698 - val_loss: 2.0726
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.5074
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2410 - loss: 2.1925  
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2444 - loss: 2.1637
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2438 - loss: 2.1567
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2442 - loss: 2.1525
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2441 - loss: 2.1509
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2433 - loss: 2.1514
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2428 - loss: 2.1517
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2428 - loss: 2.1516
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2430 - loss: 2.1511
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2435 - loss: 2.1503
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2440 - loss: 2.1496
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2445 - loss: 2.1492
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1484
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1474
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2463 - loss: 2.1463
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2468 - loss: 2.1455
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2472 - loss: 2.1445
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2476 - loss: 2.1439
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2479 - loss: 2.1433
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2482 - loss: 2.1429
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2484 - loss: 2.1424
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2487 - loss: 2.1420
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2489 - loss: 2.1417
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2491 - loss: 2.1414
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2493 - loss: 2.1411
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2495 - loss: 2.1408
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2497 - loss: 2.1406
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2499 - loss: 2.1404
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2500 - loss: 2.1402 - val_accuracy: 0.2609 - val_loss: 2.0904
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.2909
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2623 - loss: 2.1392  
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2538 - loss: 2.1437
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2488 - loss: 2.1502
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2465 - loss: 2.1516
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2469 - loss: 2.1483
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2481 - loss: 2.1451
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2490 - loss: 2.1427
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2496 - loss: 2.1404
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2500 - loss: 2.1385
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2505 - loss: 2.1366
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2510 - loss: 2.1348
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.1335
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2516 - loss: 2.1326
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2517 - loss: 2.1319
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2519 - loss: 2.1315
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2521 - loss: 2.1309
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2523 - loss: 2.1302
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2525 - loss: 2.1294
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2526 - loss: 2.1289
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2527 - loss: 2.1285
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.1282
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.1279
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2529 - loss: 2.1277
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2529 - loss: 2.1276
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2529 - loss: 2.1274
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2530 - loss: 2.1272
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2531 - loss: 2.1269
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2532 - loss: 2.1266
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2533 - loss: 2.1262
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2534 - loss: 2.1261 - val_accuracy: 0.2681 - val_loss: 2.0587
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.0727
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2692 - loss: 2.1233  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2647 - loss: 2.1214
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2645 - loss: 2.1160
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2642 - loss: 2.1103
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2634 - loss: 2.1062
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2626 - loss: 2.1043
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2625 - loss: 2.1026
[1m 333/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2627 - loss: 2.1011
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2632 - loss: 2.1001
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2635 - loss: 2.0993
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2635 - loss: 2.0988
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2635 - loss: 2.0991
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2634 - loss: 2.0994
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0996
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0996
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2632 - loss: 2.0999
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2631 - loss: 2.1001
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2630 - loss: 2.1002
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2629 - loss: 2.1004
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2629 - loss: 2.1004
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2629 - loss: 2.1005
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2629 - loss: 2.1006
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2630 - loss: 2.1006
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2630 - loss: 2.1006
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2629 - loss: 2.1007
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2629 - loss: 2.1008
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2628 - loss: 2.1009
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2628 - loss: 2.1009 - val_accuracy: 0.2749 - val_loss: 2.0246
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 2.0056
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0580  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2623 - loss: 2.0882
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2601 - loss: 2.0957
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2596 - loss: 2.0951
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2587 - loss: 2.0969
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2579 - loss: 2.0977
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2576 - loss: 2.0972
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2569 - loss: 2.0970
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.0969
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2562 - loss: 2.0971
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0970
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0969
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0969
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0966
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0964
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0961
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0959
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0957
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0955
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.0953
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0951
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0950
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0947
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2562 - loss: 2.0944
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0941
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2564 - loss: 2.0938
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2566 - loss: 2.0935
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0932
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0929
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2568 - loss: 2.0929 - val_accuracy: 0.2675 - val_loss: 2.0406
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.0871
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3072 - loss: 2.0546  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2872 - loss: 2.0633
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2812 - loss: 2.0648
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2778 - loss: 2.0631
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2763 - loss: 2.0620
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0618
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2741 - loss: 2.0623
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2734 - loss: 2.0627
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2728 - loss: 2.0628
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0630
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0633
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0639
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2706 - loss: 2.0643
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0648
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0653
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 2.0660
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2692 - loss: 2.0667
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2689 - loss: 2.0673
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0678
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2684 - loss: 2.0681
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0685
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0688
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2678 - loss: 2.0690
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0693
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0695
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0698
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2673 - loss: 2.0700
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0702
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0703
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2671 - loss: 2.0704 - val_accuracy: 0.2751 - val_loss: 2.0148
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.3760
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2830 - loss: 2.0547  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2826 - loss: 2.0444
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2798 - loss: 2.0454
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2773 - loss: 2.0512
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2756 - loss: 2.0551
[1m 249/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0568
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2741 - loss: 2.0585
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2733 - loss: 2.0597
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0602
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2729 - loss: 2.0606
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2727 - loss: 2.0604
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2726 - loss: 2.0603
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2723 - loss: 2.0604
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0604
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2719 - loss: 2.0603
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0601
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0599
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0597
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2714 - loss: 2.0595
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0593
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0592
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0592
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0592
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0592
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2714 - loss: 2.0592
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0592
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0592
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0592
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2713 - loss: 2.0592 - val_accuracy: 0.2784 - val_loss: 1.9909
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.2500 - loss: 1.9977
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2562 - loss: 2.0658  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2617 - loss: 2.0586
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2616 - loss: 2.0594
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2614 - loss: 2.0566
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0573
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0567
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2608 - loss: 2.0554
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0547
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0547
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0550
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0557
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0565
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2607 - loss: 2.0573
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2606 - loss: 2.0577
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2606 - loss: 2.0579
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2606 - loss: 2.0580
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2607 - loss: 2.0580
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2608 - loss: 2.0579
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0579
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0578
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2612 - loss: 2.0578
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2614 - loss: 2.0577
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2616 - loss: 2.0575
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2619 - loss: 2.0573
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2622 - loss: 2.0570
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2624 - loss: 2.0567
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2626 - loss: 2.0565
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2628 - loss: 2.0563
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0562
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2630 - loss: 2.0562 - val_accuracy: 0.2827 - val_loss: 1.9806
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.1930
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2838 - loss: 2.0004  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2906 - loss: 2.0033
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2925 - loss: 2.0075
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2917 - loss: 2.0124
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2899 - loss: 2.0178
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2882 - loss: 2.0213
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2866 - loss: 2.0234
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2851 - loss: 2.0254
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2841 - loss: 2.0271
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2832 - loss: 2.0284
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2823 - loss: 2.0296
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2817 - loss: 2.0303
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 2.0306
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 2.0309
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2797 - loss: 2.0314
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2791 - loss: 2.0318
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2786 - loss: 2.0320
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2782 - loss: 2.0321
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2778 - loss: 2.0320
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2774 - loss: 2.0321
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2771 - loss: 2.0321
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2768 - loss: 2.0322
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2765 - loss: 2.0323
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2762 - loss: 2.0325
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 2.0325
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2757 - loss: 2.0326
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2754 - loss: 2.0326
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0327
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2751 - loss: 2.0328 - val_accuracy: 0.2759 - val_loss: 1.9872
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.3125 - loss: 1.9517
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0663  
[1m  71/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2613 - loss: 2.0713
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0732
[1m 147/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2562 - loss: 2.0718
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0681
[1m 223/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0639
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0620
[1m 296/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0612
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2569 - loss: 2.0606
[1m 381/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0594
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2576 - loss: 2.0581
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2580 - loss: 2.0571
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2584 - loss: 2.0560
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2588 - loss: 2.0550
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2593 - loss: 2.0542
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2598 - loss: 2.0532
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0524
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2607 - loss: 2.0515
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2612 - loss: 2.0508
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2618 - loss: 2.0500
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2624 - loss: 2.0492
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0484
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2634 - loss: 2.0477
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2638 - loss: 2.0469
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0463
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2647 - loss: 2.0456
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0450
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2654 - loss: 2.0444
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0440
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2660 - loss: 2.0436 - val_accuracy: 0.2953 - val_loss: 1.9768
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0738
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3032 - loss: 1.9595  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2934 - loss: 1.9705
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2882 - loss: 1.9833
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2844 - loss: 1.9910
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2820 - loss: 1.9962
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2811 - loss: 1.9989
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2808 - loss: 2.0010
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2802 - loss: 2.0032
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 2.0050
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2791 - loss: 2.0064
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2787 - loss: 2.0077
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2785 - loss: 2.0086
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2783 - loss: 2.0094
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2783 - loss: 2.0100
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2781 - loss: 2.0104
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2779 - loss: 2.0108
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2777 - loss: 2.0112
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 2.0116
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2773 - loss: 2.0119
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2772 - loss: 2.0122
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2770 - loss: 2.0124
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2770 - loss: 2.0127
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2769 - loss: 2.0129
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2768 - loss: 2.0130
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2767 - loss: 2.0131
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2766 - loss: 2.0132
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2765 - loss: 2.0133
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2764 - loss: 2.0133
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2764 - loss: 2.0133 - val_accuracy: 0.2772 - val_loss: 1.9731
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.3125 - loss: 2.1033
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2931 - loss: 1.9961  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2845 - loss: 2.0165
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2804 - loss: 2.0226
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2789 - loss: 2.0224
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2779 - loss: 2.0231
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2776 - loss: 2.0237
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2778 - loss: 2.0230
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2785 - loss: 2.0217
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2790 - loss: 2.0204
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2793 - loss: 2.0197
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2797 - loss: 2.0192
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 2.0187
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2803 - loss: 2.0185
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 2.0183
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 2.0182
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 2.0182
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 2.0181
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 2.0180
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 2.0180
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 2.0180
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2802 - loss: 2.0180
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 2.0180
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 2.0180
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 2.0180
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2800 - loss: 2.0179
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2800 - loss: 2.0178
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 2.0177
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 2.0176
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2799 - loss: 2.0175 - val_accuracy: 0.2875 - val_loss: 1.9564
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 20ms/step - accuracy: 0.3125 - loss: 1.6437
[1m  44/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2598 - loss: 1.9891  
[1m  87/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2619 - loss: 2.0066
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0134
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0180
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0201
[1m 253/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2697 - loss: 2.0207
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0205
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0206
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2720 - loss: 2.0208
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2728 - loss: 2.0202
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2734 - loss: 2.0194
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0185
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2746 - loss: 2.0176
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0168
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2753 - loss: 2.0159
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2756 - loss: 2.0151
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 2.0143
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0135
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2763 - loss: 2.0129
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2765 - loss: 2.0124
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2766 - loss: 2.0120
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2768 - loss: 2.0117
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2769 - loss: 2.0113
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2771 - loss: 2.0110
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2772 - loss: 2.0107
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2774 - loss: 2.0104
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 2.0101
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 2.0098
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2776 - loss: 2.0097 - val_accuracy: 0.2825 - val_loss: 1.9615
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.9099
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2931 - loss: 1.9703  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2871 - loss: 1.9712
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2852 - loss: 1.9743
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2841 - loss: 1.9753
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2834 - loss: 1.9770
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2824 - loss: 1.9797
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2814 - loss: 1.9822
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2810 - loss: 1.9839
[1m 377/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 1.9863
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 1.9876
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2797 - loss: 1.9884
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9889
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 1.9890
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2800 - loss: 1.9891
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 1.9893
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2803 - loss: 1.9894
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 1.9895
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 1.9896
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 1.9898
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2807 - loss: 1.9899
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2809 - loss: 1.9900
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 1.9902
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2813 - loss: 1.9902
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2815 - loss: 1.9902
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2817 - loss: 1.9903
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2818 - loss: 1.9903
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2819 - loss: 1.9904
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2820 - loss: 1.9906
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2821 - loss: 1.9907 - val_accuracy: 0.2864 - val_loss: 1.9554
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.4375 - loss: 1.6163
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3350 - loss: 1.9261  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3199 - loss: 1.9466
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3096 - loss: 1.9622
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3050 - loss: 1.9684
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3016 - loss: 1.9726
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2995 - loss: 1.9753
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2978 - loss: 1.9776
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2964 - loss: 1.9795
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2954 - loss: 1.9808
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2944 - loss: 1.9815
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2936 - loss: 1.9820
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2931 - loss: 1.9825
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2929 - loss: 1.9828
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2928 - loss: 1.9829
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2926 - loss: 1.9830
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2924 - loss: 1.9832
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2922 - loss: 1.9835
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2919 - loss: 1.9838
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2916 - loss: 1.9841
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2914 - loss: 1.9844
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2912 - loss: 1.9846
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2910 - loss: 1.9849
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2907 - loss: 1.9852
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2905 - loss: 1.9854
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2903 - loss: 1.9856
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2901 - loss: 1.9858
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2899 - loss: 1.9859
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2897 - loss: 1.9860
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2895 - loss: 1.9860 - val_accuracy: 0.2777 - val_loss: 1.9528
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.0747
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2877 - loss: 1.9842  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2821 - loss: 1.9932
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2815 - loss: 1.9917
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2825 - loss: 1.9869
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2840 - loss: 1.9821
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2845 - loss: 1.9790
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2845 - loss: 1.9778
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2844 - loss: 1.9769
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2838 - loss: 1.9769
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2834 - loss: 1.9769
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2830 - loss: 1.9769
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2830 - loss: 1.9769
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2828 - loss: 1.9769
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2827 - loss: 1.9769
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2825 - loss: 1.9769
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2825 - loss: 1.9767
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2826 - loss: 1.9765
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2827 - loss: 1.9761
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2827 - loss: 1.9758
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2829 - loss: 1.9755
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2831 - loss: 1.9753
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2832 - loss: 1.9751
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2833 - loss: 1.9751
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2833 - loss: 1.9751
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2833 - loss: 1.9751
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2834 - loss: 1.9751
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2834 - loss: 1.9751
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2834 - loss: 1.9750
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2834 - loss: 1.9750 - val_accuracy: 0.2929 - val_loss: 1.9295

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 631ms/step
[1m66/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 777us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:17[0m 853ms/step
[1m 66/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 776us/step  
[1m139/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 730us/step
[1m216/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 703us/step
[1m292/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 693us/step
[1m365/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 693us/step
[1m440/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 689us/step
[1m509/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 694us/step
[1m575/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 702us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m71/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 718us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 65/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 782us/step
[1m132/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 766us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 27.99 [%]
Global F1 score (validation) = 21.99 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.18915243 0.15856193 0.1752528  ... 0.00133565 0.18466143 0.03880067]
 [0.15983756 0.19001597 0.12248264 ... 0.00650651 0.10253592 0.02105663]
 [0.15483858 0.15613702 0.16336584 ... 0.0025768  0.13062617 0.02894959]
 ...
 [0.2206175  0.17138003 0.16530837 ... 0.00179475 0.14905159 0.06484116]
 [0.10333262 0.1341964  0.08867545 ... 0.01207882 0.08447467 0.01171906]
 [0.04532722 0.05755874 0.04079275 ... 0.02120453 0.03656432 0.0056089 ]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 28.52 [%]
Global accuracy score (test) = 24.7 [%]
Global F1 score (train) = 23.61 [%]
Global F1 score (test) = 21.09 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.17      0.14      0.16       184
 CAMINAR CON MÓVIL O LIBRO       0.18      0.34      0.23       184
       CAMINAR USUAL SPEED       0.17      0.11      0.14       184
            CAMINAR ZIGZAG       0.00      0.00      0.00       184
          DE PIE BARRIENDO       0.14      0.54      0.22       184
   DE PIE DOBLANDO TOALLAS       0.19      0.11      0.14       184
    DE PIE MOVIENDO LIBROS       0.20      0.10      0.13       184
          DE PIE USANDO PC       0.27      0.43      0.34       184
        FASE REPOSO CON K5       0.48      0.72      0.58       184
INCREMENTAL CICLOERGOMETRO       0.00      0.00      0.00       184
           SENTADO LEYENDO       0.27      0.63      0.38       184
         SENTADO USANDO PC       0.35      0.15      0.21       184
      SENTADO VIENDO LA TV       0.00      0.00      0.00       184
   SUBIR Y BAJAR ESCALERAS       0.45      0.05      0.10       184
                    TROTAR       0.95      0.39      0.56       161

                  accuracy                           0.25      2737
                 macro avg       0.25      0.25      0.21      2737
              weighted avg       0.25      0.25      0.21      2737


Accuracy capturado en la ejecución 13: 24.7 [%]
F1-score capturado en la ejecución 13: 21.09 [%]

=== EJECUCIÓN 14 ===

--- TRAIN (ejecución 14) ---

--- TEST (ejecución 14) ---
2025-11-07 14:21:22.012396: 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 14:21:22.023950: 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 00:00:1762521682.037073 2960445 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762521682.040980 2960445 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762521682.051015 2960445 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521682.051032 2960445 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521682.051034 2960445 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521682.051035 2960445 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:21:22.053968: 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 00:00:1762521684.325789 2960445 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762521685.847584 2960553 service.cc:152] XLA service 0x7d88e00158b0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762521685.847610 2960553 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:21:25.876491: 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 00:00:1762521686.030838 2960553 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762521687.434021 2960553 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47:57[0m 2s/step - accuracy: 0.0625 - loss: 3.3108
[1m  31/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0681 - loss: 3.2645  
[1m  70/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0715 - loss: 3.2313
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0728 - loss: 3.2103
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0737 - loss: 3.1965
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0741 - loss: 3.1822
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0743 - loss: 3.1721
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0749 - loss: 3.1628
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0758 - loss: 3.1549
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0769 - loss: 3.1469
[1m 387/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0779 - loss: 3.1402
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0789 - loss: 3.1337
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0802 - loss: 3.1262
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0815 - loss: 3.1186
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0827 - loss: 3.1116
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0838 - loss: 3.1046
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0847 - loss: 3.0987
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0858 - loss: 3.0919
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0867 - loss: 3.0859
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0876 - loss: 3.0802
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0884 - loss: 3.0748
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0892 - loss: 3.0694
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0899 - loss: 3.0642
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0907 - loss: 3.0590
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0913 - loss: 3.0547
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0919 - loss: 3.0501
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0925 - loss: 3.0455
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0932 - loss: 3.0406
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0937 - loss: 3.0363
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0943 - loss: 3.0316
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0944 - loss: 3.0308
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0944 - loss: 3.0307 - val_accuracy: 0.1105 - val_loss: 2.6083
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 32ms/step - accuracy: 0.1875 - loss: 2.7279
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1449 - loss: 2.7158  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1508 - loss: 2.7074
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1548 - loss: 2.6955
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1559 - loss: 2.6896
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1562 - loss: 2.6853
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1559 - loss: 2.6823
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1558 - loss: 2.6794
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1560 - loss: 2.6770
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1561 - loss: 2.6748
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1559 - loss: 2.6724
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1555 - loss: 2.6706
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1551 - loss: 2.6688
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1547 - loss: 2.6672
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1543 - loss: 2.6658
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1541 - loss: 2.6644
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1538 - loss: 2.6627
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1535 - loss: 2.6610
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1533 - loss: 2.6593
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1530 - loss: 2.6576
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1529 - loss: 2.6557
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1528 - loss: 2.6540
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1528 - loss: 2.6521
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1527 - loss: 2.6503
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1527 - loss: 2.6484
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1526 - loss: 2.6466
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1526 - loss: 2.6447
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1526 - loss: 2.6430
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1526 - loss: 2.6414
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1527 - loss: 2.6399
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1527 - loss: 2.6396 - val_accuracy: 0.1730 - val_loss: 2.4574
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.6461
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1953 - loss: 2.4721  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1997 - loss: 2.4645
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1992 - loss: 2.4692
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1987 - loss: 2.4711
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1982 - loss: 2.4729
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1972 - loss: 2.4743
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1960 - loss: 2.4758
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1951 - loss: 2.4767
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1946 - loss: 2.4767
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1941 - loss: 2.4768
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1936 - loss: 2.4770
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1931 - loss: 2.4771
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1925 - loss: 2.4770
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1921 - loss: 2.4768
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1917 - loss: 2.4765
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1913 - loss: 2.4759
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1909 - loss: 2.4754
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1905 - loss: 2.4750
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1902 - loss: 2.4745
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1899 - loss: 2.4742
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1896 - loss: 2.4738
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1894 - loss: 2.4734
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1892 - loss: 2.4731
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1890 - loss: 2.4726
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1889 - loss: 2.4720
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1888 - loss: 2.4713
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1887 - loss: 2.4706
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1886 - loss: 2.4700
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1885 - loss: 2.4693
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1885 - loss: 2.4691 - val_accuracy: 0.2041 - val_loss: 2.3676
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.2214
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2001 - loss: 2.3317  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1985 - loss: 2.3494
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1934 - loss: 2.3623
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1912 - loss: 2.3698
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1904 - loss: 2.3749
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1893 - loss: 2.3793
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1882 - loss: 2.3823
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1877 - loss: 2.3836
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1875 - loss: 2.3840
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1875 - loss: 2.3839
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1877 - loss: 2.3836
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1880 - loss: 2.3832
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1882 - loss: 2.3829
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1884 - loss: 2.3826
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1887 - loss: 2.3822
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1890 - loss: 2.3817
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1892 - loss: 2.3810
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1894 - loss: 2.3805
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1896 - loss: 2.3800
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1897 - loss: 2.3796
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1898 - loss: 2.3792
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1900 - loss: 2.3788
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1900 - loss: 2.3784
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1901 - loss: 2.3780
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1902 - loss: 2.3775
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1903 - loss: 2.3770
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1905 - loss: 2.3765
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1906 - loss: 2.3759
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1908 - loss: 2.3754
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1908 - loss: 2.3753 - val_accuracy: 0.2174 - val_loss: 2.2997
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.3307
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2114 - loss: 2.3492  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2086 - loss: 2.3444
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2033 - loss: 2.3454
[1m 148/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2023 - loss: 2.3447
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2025 - loss: 2.3411
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2032 - loss: 2.3385
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2042 - loss: 2.3361
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2050 - loss: 2.3337
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2054 - loss: 2.3318
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2056 - loss: 2.3302
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2057 - loss: 2.3293
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2057 - loss: 2.3284
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2057 - loss: 2.3276
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2057 - loss: 2.3267
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2057 - loss: 2.3259
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2057 - loss: 2.3252
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2057 - loss: 2.3246
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2057 - loss: 2.3241
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2056 - loss: 2.3238
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2056 - loss: 2.3235
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2056 - loss: 2.3232
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2056 - loss: 2.3228
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2057 - loss: 2.3225
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2056 - loss: 2.3221
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2056 - loss: 2.3217
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2056 - loss: 2.3213
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2056 - loss: 2.3209
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2056 - loss: 2.3205
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2056 - loss: 2.3200
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2056 - loss: 2.3196
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2056 - loss: 2.3195 - val_accuracy: 0.2094 - val_loss: 2.2493
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.3823
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2163 - loss: 2.2673  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2201 - loss: 2.2664
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2212 - loss: 2.2659
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2218 - loss: 2.2649
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2223 - loss: 2.2646
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2223 - loss: 2.2651
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2222 - loss: 2.2657
[1m 333/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2221 - loss: 2.2659
[1m 377/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2220 - loss: 2.2667
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2219 - loss: 2.2671
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2217 - loss: 2.2678
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2215 - loss: 2.2683
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2213 - loss: 2.2687
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2210 - loss: 2.2690
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2208 - loss: 2.2693
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2207 - loss: 2.2695
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2205 - loss: 2.2697
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2203 - loss: 2.2697
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2201 - loss: 2.2697
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2199 - loss: 2.2699
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2197 - loss: 2.2699
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2195 - loss: 2.2700
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2193 - loss: 2.2701
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2191 - loss: 2.2701
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2189 - loss: 2.2702
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2187 - loss: 2.2702
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2184 - loss: 2.2703
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2182 - loss: 2.2703
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2181 - loss: 2.2703 - val_accuracy: 0.2211 - val_loss: 2.2169
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.2457
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2208 - loss: 2.3385  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2194 - loss: 2.3208
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2222 - loss: 2.3047
[1m 168/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2247 - loss: 2.2914
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2259 - loss: 2.2827
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2270 - loss: 2.2766
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2281 - loss: 2.2709
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2290 - loss: 2.2661
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2294 - loss: 2.2635
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2298 - loss: 2.2616
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2300 - loss: 2.2596
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2301 - loss: 2.2579
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2300 - loss: 2.2565
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2299 - loss: 2.2554
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2299 - loss: 2.2544
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2299 - loss: 2.2535
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2299 - loss: 2.2527
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2298 - loss: 2.2520
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2297 - loss: 2.2513
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2295 - loss: 2.2507
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2293 - loss: 2.2502
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2292 - loss: 2.2499
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2290 - loss: 2.2494
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2289 - loss: 2.2489
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2288 - loss: 2.2484
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2287 - loss: 2.2479
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2285 - loss: 2.2475
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2284 - loss: 2.2470
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2283 - loss: 2.2466
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2282 - loss: 2.2465 - val_accuracy: 0.2054 - val_loss: 2.1843
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.3002
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1491  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2387 - loss: 2.1727
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2388 - loss: 2.1797
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2378 - loss: 2.1860
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2359 - loss: 2.1906
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2340 - loss: 2.1939
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2325 - loss: 2.1957
[1m 307/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2316 - loss: 2.1970
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2310 - loss: 2.1982
[1m 387/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2305 - loss: 2.1992
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2299 - loss: 2.2001
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2294 - loss: 2.2009
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2290 - loss: 2.2018
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2286 - loss: 2.2028
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2283 - loss: 2.2037
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2279 - loss: 2.2046
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2276 - loss: 2.2055
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2273 - loss: 2.2063
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2269 - loss: 2.2070
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2265 - loss: 2.2078
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2262 - loss: 2.2085
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2259 - loss: 2.2091
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2257 - loss: 2.2096
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2255 - loss: 2.2098
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2254 - loss: 2.2100
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2253 - loss: 2.2101
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2252 - loss: 2.2101
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2251 - loss: 2.2100
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2250 - loss: 2.2100
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2250 - loss: 2.2100 - val_accuracy: 0.2461 - val_loss: 2.1638
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 1.9106
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2538 - loss: 2.1646  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2537 - loss: 2.1695
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2519 - loss: 2.1719
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2491 - loss: 2.1777
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2470 - loss: 2.1809
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2460 - loss: 2.1824
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1833
[1m 305/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2449 - loss: 2.1843
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2440 - loss: 2.1850
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2435 - loss: 2.1851
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2429 - loss: 2.1851
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2422 - loss: 2.1850
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2417 - loss: 2.1848
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2412 - loss: 2.1844
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2409 - loss: 2.1840
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2406 - loss: 2.1835
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2404 - loss: 2.1828
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2402 - loss: 2.1823
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2400 - loss: 2.1820
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2398 - loss: 2.1818
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2395 - loss: 2.1817
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2393 - loss: 2.1816
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2391 - loss: 2.1816
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2390 - loss: 2.1815
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2389 - loss: 2.1814
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2388 - loss: 2.1812
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2387 - loss: 2.1811
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2385 - loss: 2.1810
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2384 - loss: 2.1808
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2384 - loss: 2.1808 - val_accuracy: 0.2483 - val_loss: 2.1144
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3750 - loss: 1.9613
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2466 - loss: 2.1695  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2430 - loss: 2.1708
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2428 - loss: 2.1711
[1m 150/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2416 - loss: 2.1727
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2402 - loss: 2.1757
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2384 - loss: 2.1788
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2366 - loss: 2.1806
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2356 - loss: 2.1810
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2349 - loss: 2.1810
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2345 - loss: 2.1809
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2343 - loss: 2.1801
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2340 - loss: 2.1794
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2338 - loss: 2.1785
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2338 - loss: 2.1771
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2338 - loss: 2.1759
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2339 - loss: 2.1749
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2339 - loss: 2.1741
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2339 - loss: 2.1732
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2341 - loss: 2.1724
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2343 - loss: 2.1716
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2345 - loss: 2.1708
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2348 - loss: 2.1700
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2351 - loss: 2.1690
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2353 - loss: 2.1682
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2354 - loss: 2.1676
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2356 - loss: 2.1669
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2357 - loss: 2.1663
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2359 - loss: 2.1659
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2360 - loss: 2.1655
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2360 - loss: 2.1654 - val_accuracy: 0.2444 - val_loss: 2.1106
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3750 - loss: 2.0692
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2506 - loss: 2.1070  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2503 - loss: 2.1019
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2497 - loss: 2.1042
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2491 - loss: 2.1077
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2484 - loss: 2.1123
[1m 249/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2475 - loss: 2.1164
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2470 - loss: 2.1195
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2466 - loss: 2.1212
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2464 - loss: 2.1221
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2461 - loss: 2.1231
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2458 - loss: 2.1239
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1248
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1256
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2449 - loss: 2.1264
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2447 - loss: 2.1271
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2445 - loss: 2.1276
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2444 - loss: 2.1280
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2442 - loss: 2.1284
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2441 - loss: 2.1286
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2441 - loss: 2.1289
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2440 - loss: 2.1293
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2439 - loss: 2.1296
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2438 - loss: 2.1299
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2438 - loss: 2.1301
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2437 - loss: 2.1303
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2437 - loss: 2.1305
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2436 - loss: 2.1307
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2435 - loss: 2.1309
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2434 - loss: 2.1312 - val_accuracy: 0.2400 - val_loss: 2.1075
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.4392
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2628 - loss: 2.1264  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2534 - loss: 2.1211
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2489 - loss: 2.1254
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2465 - loss: 2.1270
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1273
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2450 - loss: 2.1282
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2449 - loss: 2.1286
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2447 - loss: 2.1294
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2445 - loss: 2.1302
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2443 - loss: 2.1304
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2444 - loss: 2.1303
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2445 - loss: 2.1300
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2445 - loss: 2.1298
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2444 - loss: 2.1296
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2442 - loss: 2.1296
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2441 - loss: 2.1295
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2439 - loss: 2.1294
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2438 - loss: 2.1295
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2437 - loss: 2.1297
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2436 - loss: 2.1298
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2434 - loss: 2.1298
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2434 - loss: 2.1299
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2433 - loss: 2.1298
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2434 - loss: 2.1297
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2433 - loss: 2.1295
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2433 - loss: 2.1293
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2433 - loss: 2.1290
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2434 - loss: 2.1287
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2434 - loss: 2.1284 - val_accuracy: 0.2501 - val_loss: 2.0735
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.3631
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2303 - loss: 2.1109  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2385 - loss: 2.0946
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2415 - loss: 2.0921
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2418 - loss: 2.0926
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2408 - loss: 2.0941
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2401 - loss: 2.0954
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2397 - loss: 2.0961
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2398 - loss: 2.0967
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2402 - loss: 2.0970
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2408 - loss: 2.0972
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2414 - loss: 2.0973
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2418 - loss: 2.0973
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2423 - loss: 2.0971
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2427 - loss: 2.0969
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2430 - loss: 2.0968
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2433 - loss: 2.0966
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2437 - loss: 2.0963
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2440 - loss: 2.0960
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2443 - loss: 2.0957
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2446 - loss: 2.0954
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2449 - loss: 2.0952
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.0950
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2453 - loss: 2.0949
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2455 - loss: 2.0947
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.0946
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2459 - loss: 2.0945
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2462 - loss: 2.0944
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2464 - loss: 2.0943
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2466 - loss: 2.0942 - val_accuracy: 0.2437 - val_loss: 2.0773
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 1.9545
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2696 - loss: 2.1330  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2571 - loss: 2.1511
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2545 - loss: 2.1508
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2528 - loss: 2.1482
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2518 - loss: 2.1420
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2509 - loss: 2.1380
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2504 - loss: 2.1340
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2504 - loss: 2.1303
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2505 - loss: 2.1270
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2506 - loss: 2.1249
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2506 - loss: 2.1223
[1m 463/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2506 - loss: 2.1201
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2507 - loss: 2.1179
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2508 - loss: 2.1163
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2507 - loss: 2.1148
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2507 - loss: 2.1136
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2507 - loss: 2.1124
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2507 - loss: 2.1113
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2508 - loss: 2.1101
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2510 - loss: 2.1090
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2511 - loss: 2.1079
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2512 - loss: 2.1070
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2512 - loss: 2.1061
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2512 - loss: 2.1053
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2512 - loss: 2.1045
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.1038
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.1031
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.1025
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.1020
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2513 - loss: 2.1018 - val_accuracy: 0.2474 - val_loss: 2.0582
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.1875 - loss: 2.2172
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2584 - loss: 2.0709  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2619 - loss: 2.0748
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0792
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2593 - loss: 2.0804
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0819
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2579 - loss: 2.0822
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2576 - loss: 2.0831
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2575 - loss: 2.0829
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0832
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0829
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0827
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2575 - loss: 2.0823
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.0816
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0808
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2584 - loss: 2.0800
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2586 - loss: 2.0796
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2588 - loss: 2.0789
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2590 - loss: 2.0784
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2591 - loss: 2.0780
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2591 - loss: 2.0775
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2592 - loss: 2.0769
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2592 - loss: 2.0763
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2592 - loss: 2.0760
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2592 - loss: 2.0756
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2592 - loss: 2.0752
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2592 - loss: 2.0748
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2592 - loss: 2.0745
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2591 - loss: 2.0743
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2591 - loss: 2.0740
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2590 - loss: 2.0740 - val_accuracy: 0.2612 - val_loss: 2.0293
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 1.9618
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2449 - loss: 2.1225  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2416 - loss: 2.1142
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2409 - loss: 2.1166
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2411 - loss: 2.1164
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2411 - loss: 2.1166
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2416 - loss: 2.1146
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2421 - loss: 2.1129
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2426 - loss: 2.1117
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2429 - loss: 2.1099
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2433 - loss: 2.1081
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2435 - loss: 2.1064
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2438 - loss: 2.1049
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2441 - loss: 2.1031
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2446 - loss: 2.1013
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.0996
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2455 - loss: 2.0982
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2460 - loss: 2.0967
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2464 - loss: 2.0950
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2469 - loss: 2.0934
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2474 - loss: 2.0920
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2478 - loss: 2.0907
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2482 - loss: 2.0897
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2486 - loss: 2.0886
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2490 - loss: 2.0876
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2493 - loss: 2.0867
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2496 - loss: 2.0859
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2499 - loss: 2.0852
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.0844
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2505 - loss: 2.0836
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2505 - loss: 2.0834 - val_accuracy: 0.2459 - val_loss: 2.0326
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.0105
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0726  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2449 - loss: 2.0795
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2440 - loss: 2.0766
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2441 - loss: 2.0769
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2439 - loss: 2.0763
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2452 - loss: 2.0743
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2468 - loss: 2.0722
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2482 - loss: 2.0708
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2492 - loss: 2.0695
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2503 - loss: 2.0679
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2511 - loss: 2.0668
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2517 - loss: 2.0657
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2524 - loss: 2.0647
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2529 - loss: 2.0640
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2534 - loss: 2.0631
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2537 - loss: 2.0625
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2540 - loss: 2.0620
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.0615
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2545 - loss: 2.0610
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2547 - loss: 2.0605
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2550 - loss: 2.0599
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2552 - loss: 2.0595
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2554 - loss: 2.0591
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2555 - loss: 2.0589
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2557 - loss: 2.0587
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2558 - loss: 2.0585
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.0583
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0580
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2562 - loss: 2.0579 - val_accuracy: 0.2496 - val_loss: 2.0211
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.7587
[1m  32/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2867 - loss: 1.9760  
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2853 - loss: 1.9870
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2856 - loss: 1.9949
[1m 150/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2848 - loss: 1.9981
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2847 - loss: 1.9977
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2850 - loss: 1.9964
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2847 - loss: 1.9956
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2842 - loss: 1.9954
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2830 - loss: 1.9962
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2817 - loss: 1.9972
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2808 - loss: 1.9978
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2800 - loss: 1.9986
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2794 - loss: 1.9992
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 2.0002
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2784 - loss: 2.0014
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2779 - loss: 2.0027
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 2.0040
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2771 - loss: 2.0050
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2768 - loss: 2.0061
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2764 - loss: 2.0071
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0082
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2757 - loss: 2.0092
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2754 - loss: 2.0099
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0108
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0117
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0126
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2741 - loss: 2.0135
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2738 - loss: 2.0143
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0151
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2735 - loss: 2.0153 - val_accuracy: 0.2546 - val_loss: 2.0112
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.9362
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2493 - loss: 2.0823  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2582 - loss: 2.0698
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2635 - loss: 2.0607
[1m 148/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0538
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0490
[1m 222/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0457
[1m 255/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0428
[1m 296/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0397
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0371
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0344
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0323
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2680 - loss: 2.0308
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0295
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0284
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0275
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0266
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0259
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0254
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0251
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0249
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2680 - loss: 2.0247
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0245
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2678 - loss: 2.0244
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0243
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0241
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0240
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0239
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0239
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0238
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2674 - loss: 2.0238 - val_accuracy: 0.2537 - val_loss: 2.0120
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5000 - loss: 2.1451
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3311 - loss: 1.9704  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3174 - loss: 1.9628
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3091 - loss: 1.9705
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3013 - loss: 1.9788
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2969 - loss: 1.9840
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2937 - loss: 1.9886
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2912 - loss: 1.9919
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2890 - loss: 1.9947
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2875 - loss: 1.9967
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2860 - loss: 1.9984
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2846 - loss: 1.9999
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2832 - loss: 2.0015
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2822 - loss: 2.0026
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 2.0036
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2802 - loss: 2.0048
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2793 - loss: 2.0057
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2783 - loss: 2.0069
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2777 - loss: 2.0077
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2771 - loss: 2.0084
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2766 - loss: 2.0091
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0096
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2757 - loss: 2.0100
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2753 - loss: 2.0104
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0108
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0111
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0112
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2743 - loss: 2.0112
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0113
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2738 - loss: 2.0115 - val_accuracy: 0.2598 - val_loss: 2.0033
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.1593
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2758 - loss: 2.0229  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2720 - loss: 2.0001
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2695 - loss: 1.9980
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0000
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2654 - loss: 2.0026
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0037
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0051
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0064
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0071
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0079
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0086
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0088
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0089
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0087
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2673 - loss: 2.0085
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0084
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0081
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0078
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0075
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2678 - loss: 2.0072
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0069
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0068
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0068
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2680 - loss: 2.0067
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0066
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0064
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2683 - loss: 2.0061
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2684 - loss: 2.0059
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0056
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2686 - loss: 2.0055 - val_accuracy: 0.2638 - val_loss: 1.9811
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 1.8441
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2398 - loss: 1.9881  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2508 - loss: 1.9878
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2569 - loss: 1.9848
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2602 - loss: 1.9837
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2623 - loss: 1.9854
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2642 - loss: 1.9871
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2657 - loss: 1.9886
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2673 - loss: 1.9896
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2685 - loss: 1.9900
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2692 - loss: 1.9907
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2698 - loss: 1.9911
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2706 - loss: 1.9910
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2714 - loss: 1.9907
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2718 - loss: 1.9909
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2721 - loss: 1.9914
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2725 - loss: 1.9916
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2729 - loss: 1.9920
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2731 - loss: 1.9923
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2734 - loss: 1.9925
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 1.9926
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2738 - loss: 1.9926
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2741 - loss: 1.9925
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2742 - loss: 1.9927
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2743 - loss: 1.9929
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 1.9930
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2746 - loss: 1.9931
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 1.9932
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2750 - loss: 1.9931
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 1.9931
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2753 - loss: 1.9931 - val_accuracy: 0.2535 - val_loss: 1.9928
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 2.1171
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2491 - loss: 1.9963  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2616 - loss: 1.9881
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2644 - loss: 1.9880
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2648 - loss: 1.9892
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2651 - loss: 1.9895
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2642 - loss: 1.9923
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2635 - loss: 1.9942
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2629 - loss: 1.9963
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2629 - loss: 1.9975
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2628 - loss: 1.9987
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2628 - loss: 1.9995
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2628 - loss: 2.0004
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2629 - loss: 2.0010
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0011
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0014
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2634 - loss: 2.0017
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2634 - loss: 2.0019
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2635 - loss: 2.0020
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0021
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0021
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2640 - loss: 2.0018
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2643 - loss: 2.0015
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0011
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2647 - loss: 2.0007
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0003
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2651 - loss: 1.9999
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 1.9996
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 1.9993
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 1.9990
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2660 - loss: 1.9987 - val_accuracy: 0.2475 - val_loss: 2.0026
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5000 - loss: 1.8869
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3115 - loss: 1.9396  
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2927 - loss: 1.9693
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2899 - loss: 1.9680
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2878 - loss: 1.9652
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2868 - loss: 1.9634
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2864 - loss: 1.9611
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2859 - loss: 1.9603
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2850 - loss: 1.9615
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2845 - loss: 1.9625
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2838 - loss: 1.9639
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2832 - loss: 1.9653
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2823 - loss: 1.9667
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2818 - loss: 1.9676
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2813 - loss: 1.9682
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2807 - loss: 1.9688
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2802 - loss: 1.9695
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2797 - loss: 1.9701
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2793 - loss: 1.9707
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9714
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2785 - loss: 1.9721
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2781 - loss: 1.9727
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2778 - loss: 1.9732
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2774 - loss: 1.9737
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2772 - loss: 1.9741
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2770 - loss: 1.9744
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2768 - loss: 1.9748
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2766 - loss: 1.9752
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2763 - loss: 1.9757
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 1.9761
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2759 - loss: 1.9763 - val_accuracy: 0.2577 - val_loss: 1.9783
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.1558
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2421 - loss: 2.0325  
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2586 - loss: 2.0172
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0149
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0156
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2712 - loss: 2.0115
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0078
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0044
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0023
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2769 - loss: 2.0006
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 1.9985
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2780 - loss: 1.9971
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2784 - loss: 1.9960
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2786 - loss: 1.9952
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9943
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2791 - loss: 1.9933
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2791 - loss: 1.9925
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2792 - loss: 1.9918
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2792 - loss: 1.9911
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2792 - loss: 1.9906
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2791 - loss: 1.9900
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2790 - loss: 1.9895
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9891
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9887
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2788 - loss: 1.9884
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2787 - loss: 1.9880
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2786 - loss: 1.9877
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2785 - loss: 1.9874
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2784 - loss: 1.9872
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2784 - loss: 1.9870
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2784 - loss: 1.9869 - val_accuracy: 0.2648 - val_loss: 1.9815

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 631ms/step
[1m67/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 765us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7:51[0m 810ms/step
[1m 64/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 803us/step  
[1m132/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 772us/step
[1m193/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 788us/step
[1m261/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 776us/step
[1m327/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 773us/step
[1m398/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 761us/step
[1m465/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 759us/step
[1m536/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 752us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m70/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 728us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 71/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 726us/step
[1m140/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 726us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 29.29 [%]
Global F1 score (validation) = 25.18 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.15876114 0.25308308 0.23011887 ... 0.00044382 0.13924658 0.0289027 ]
 [0.11475384 0.18541229 0.13704695 ... 0.00362367 0.10699949 0.01195506]
 [0.19751927 0.21757591 0.20608804 ... 0.00053633 0.14150247 0.02279887]
 ...
 [0.16081613 0.2573031  0.17099716 ... 0.00129412 0.15345968 0.02598744]
 [0.18538715 0.21490933 0.17083184 ... 0.00227853 0.12953801 0.01768067]
 [0.07229819 0.11196604 0.08168571 ... 0.00978473 0.05731791 0.00673823]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 32.21 [%]
Global accuracy score (test) = 25.76 [%]
Global F1 score (train) = 28.56 [%]
Global F1 score (test) = 21.66 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.08      0.02      0.03       184
 CAMINAR CON MÓVIL O LIBRO       0.17      0.68      0.27       184
       CAMINAR USUAL SPEED       0.04      0.02      0.02       184
            CAMINAR ZIGZAG       0.05      0.01      0.02       184
          DE PIE BARRIENDO       0.26      0.67      0.37       184
   DE PIE DOBLANDO TOALLAS       0.28      0.12      0.17       184
    DE PIE MOVIENDO LIBROS       0.21      0.11      0.15       184
          DE PIE USANDO PC       0.25      0.68      0.37       184
        FASE REPOSO CON K5       0.54      0.62      0.58       184
INCREMENTAL CICLOERGOMETRO       0.42      0.20      0.27       184
           SENTADO LEYENDO       0.44      0.11      0.18       184
         SENTADO USANDO PC       0.05      0.03      0.04       184
      SENTADO VIENDO LA TV       0.33      0.26      0.29       184
   SUBIR Y BAJAR ESCALERAS       0.08      0.01      0.01       184
                    TROTAR       0.94      0.32      0.47       161

                  accuracy                           0.26      2737
                 macro avg       0.28      0.26      0.22      2737
              weighted avg       0.27      0.26      0.21      2737


Accuracy capturado en la ejecución 14: 25.76 [%]
F1-score capturado en la ejecución 14: 21.66 [%]

=== EJECUCIÓN 15 ===

--- TRAIN (ejecución 15) ---

--- TEST (ejecución 15) ---
2025-11-07 14:22:29.433029: 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 14:22:29.444248: 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 00:00:1762521749.457388 2964174 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762521749.461277 2964174 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762521749.471212 2964174 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521749.471227 2964174 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521749.471237 2964174 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521749.471238 2964174 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:22:29.474173: 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 00:00:1762521751.755068 2964174 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762521753.258862 2964299 service.cc:152] XLA service 0x71dbc0003f70 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762521753.258892 2964299 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:22:33.286395: 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 00:00:1762521753.431047 2964299 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762521754.830785 2964299 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47:05[0m 2s/step - accuracy: 0.0000e+00 - loss: 3.6301
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0660 - loss: 3.2238      
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0690 - loss: 3.1990
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0701 - loss: 3.1934
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0702 - loss: 3.1895
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0702 - loss: 3.1835
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0705 - loss: 3.1755
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0709 - loss: 3.1665
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0714 - loss: 3.1575
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0718 - loss: 3.1492
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0722 - loss: 3.1415
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0726 - loss: 3.1337
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0730 - loss: 3.1258
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0734 - loss: 3.1182
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0738 - loss: 3.1109
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0742 - loss: 3.1041
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0747 - loss: 3.0973
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0752 - loss: 3.0912
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0757 - loss: 3.0848
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0761 - loss: 3.0786
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0767 - loss: 3.0723
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0771 - loss: 3.0667
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0777 - loss: 3.0605
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0781 - loss: 3.0551
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0786 - loss: 3.0495
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0791 - loss: 3.0444
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0797 - loss: 3.0391
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0801 - loss: 3.0352
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0805 - loss: 3.0306
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0807 - loss: 3.0284
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0807 - loss: 3.0283 - val_accuracy: 0.1238 - val_loss: 2.6229
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.4451
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1254 - loss: 2.6876  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1214 - loss: 2.7045
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1227 - loss: 2.7094
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1245 - loss: 2.7089
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1252 - loss: 2.7069
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1259 - loss: 2.7037
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1266 - loss: 2.7013
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1272 - loss: 2.6989
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1275 - loss: 2.6972
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1278 - loss: 2.6953
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1281 - loss: 2.6937
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1284 - loss: 2.6920
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1288 - loss: 2.6902
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1292 - loss: 2.6887
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1295 - loss: 2.6872
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1297 - loss: 2.6860
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1300 - loss: 2.6847
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1305 - loss: 2.6832
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1309 - loss: 2.6818
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1312 - loss: 2.6805
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1317 - loss: 2.6791
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1320 - loss: 2.6778
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1325 - loss: 2.6763
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1329 - loss: 2.6750
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1333 - loss: 2.6736
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1336 - loss: 2.6723
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1339 - loss: 2.6710
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1343 - loss: 2.6698
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1346 - loss: 2.6685
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1347 - loss: 2.6682 - val_accuracy: 0.1650 - val_loss: 2.5306
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.4744
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1780 - loss: 2.5408  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1717 - loss: 2.5482
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1664 - loss: 2.5555
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1639 - loss: 2.5573
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1626 - loss: 2.5569
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1625 - loss: 2.5547
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1627 - loss: 2.5526
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1628 - loss: 2.5513
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1628 - loss: 2.5500
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1629 - loss: 2.5487
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1628 - loss: 2.5477
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1629 - loss: 2.5468
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1632 - loss: 2.5457
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1634 - loss: 2.5448
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1638 - loss: 2.5437
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1641 - loss: 2.5426
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1645 - loss: 2.5416
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1648 - loss: 2.5405
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1651 - loss: 2.5395
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1654 - loss: 2.5387
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1656 - loss: 2.5378
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1657 - loss: 2.5371
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1658 - loss: 2.5366
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1660 - loss: 2.5358
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1662 - loss: 2.5350
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1663 - loss: 2.5343
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1665 - loss: 2.5336
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1667 - loss: 2.5328
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1668 - loss: 2.5321
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1669 - loss: 2.5319 - val_accuracy: 0.1737 - val_loss: 2.4666
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.4944
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1750 - loss: 2.4103  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1751 - loss: 2.4365
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1742 - loss: 2.4468
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1725 - loss: 2.4540
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1718 - loss: 2.4564
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1720 - loss: 2.4581
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1726 - loss: 2.4593
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1735 - loss: 2.4601
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1743 - loss: 2.4603
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1750 - loss: 2.4601
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1756 - loss: 2.4598
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1760 - loss: 2.4596
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1762 - loss: 2.4595
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1765 - loss: 2.4591
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1766 - loss: 2.4585
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1768 - loss: 2.4580
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1770 - loss: 2.4574
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1772 - loss: 2.4567
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1774 - loss: 2.4562
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1775 - loss: 2.4557
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1777 - loss: 2.4550
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1779 - loss: 2.4543
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1781 - loss: 2.4536
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1784 - loss: 2.4528
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1786 - loss: 2.4520
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1788 - loss: 2.4511
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1790 - loss: 2.4503
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1792 - loss: 2.4496
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1793 - loss: 2.4490
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1794 - loss: 2.4486 - val_accuracy: 0.1870 - val_loss: 2.3874
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 2.4682
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1505 - loss: 2.4088  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1705 - loss: 2.4008
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1785 - loss: 2.4003
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1841 - loss: 2.3993
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1870 - loss: 2.3993
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1889 - loss: 2.3989
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1899 - loss: 2.3987
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1906 - loss: 2.3982
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1908 - loss: 2.3978
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1911 - loss: 2.3974
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1912 - loss: 2.3971
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1914 - loss: 2.3966
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1916 - loss: 2.3959
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1920 - loss: 2.3952
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1922 - loss: 2.3946
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1925 - loss: 2.3940
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1927 - loss: 2.3934
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1930 - loss: 2.3927
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1932 - loss: 2.3920
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1934 - loss: 2.3912
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1936 - loss: 2.3905
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1938 - loss: 2.3898
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1940 - loss: 2.3891
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1943 - loss: 2.3883
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1945 - loss: 2.3876
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1947 - loss: 2.3868
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1949 - loss: 2.3860
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1951 - loss: 2.3853
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1952 - loss: 2.3846
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1953 - loss: 2.3843 - val_accuracy: 0.1904 - val_loss: 2.3160
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.4448
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2308 - loss: 2.3341  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2169 - loss: 2.3445
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2107 - loss: 2.3443
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2071 - loss: 2.3431
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2056 - loss: 2.3418
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2049 - loss: 2.3412
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2042 - loss: 2.3411
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2038 - loss: 2.3407
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2033 - loss: 2.3405
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2031 - loss: 2.3400
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2031 - loss: 2.3393
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2031 - loss: 2.3385
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2033 - loss: 2.3376
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2035 - loss: 2.3366
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2038 - loss: 2.3355
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2040 - loss: 2.3343
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2043 - loss: 2.3332
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2045 - loss: 2.3323
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2047 - loss: 2.3315
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2049 - loss: 2.3307
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2050 - loss: 2.3300
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2052 - loss: 2.3292
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2054 - loss: 2.3284
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2055 - loss: 2.3277
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2056 - loss: 2.3269
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2057 - loss: 2.3262
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2058 - loss: 2.3255
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2060 - loss: 2.3249
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2061 - loss: 2.3243
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2061 - loss: 2.3242 - val_accuracy: 0.2091 - val_loss: 2.2575
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 19ms/step - accuracy: 0.2500 - loss: 2.2986
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2361 - loss: 2.2665  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2264 - loss: 2.2772
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2217 - loss: 2.2832
[1m 170/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2188 - loss: 2.2860
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2167 - loss: 2.2864
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2157 - loss: 2.2860
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2153 - loss: 2.2856
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2150 - loss: 2.2857
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2150 - loss: 2.2857
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2151 - loss: 2.2856
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2153 - loss: 2.2855
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2154 - loss: 2.2854
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2155 - loss: 2.2853
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2155 - loss: 2.2852
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2154 - loss: 2.2850
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2153 - loss: 2.2849
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2153 - loss: 2.2845
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2152 - loss: 2.2842
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2152 - loss: 2.2837
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2151 - loss: 2.2833
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2152 - loss: 2.2828
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2152 - loss: 2.2823
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2153 - loss: 2.2816
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2154 - loss: 2.2811
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2155 - loss: 2.2805
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2156 - loss: 2.2798
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2157 - loss: 2.2793
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2157 - loss: 2.2789
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2158 - loss: 2.2785
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2158 - loss: 2.2783 - val_accuracy: 0.2279 - val_loss: 2.2163
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.1993
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2362 - loss: 2.2306  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2400 - loss: 2.2323
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2381 - loss: 2.2361
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2358 - loss: 2.2357
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2339 - loss: 2.2351
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2326 - loss: 2.2357
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2319 - loss: 2.2366
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2315 - loss: 2.2376
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2314 - loss: 2.2379
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2313 - loss: 2.2381
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2312 - loss: 2.2383
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2312 - loss: 2.2384
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2313 - loss: 2.2380
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2315 - loss: 2.2374
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2316 - loss: 2.2368
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2316 - loss: 2.2363
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2317 - loss: 2.2358
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2317 - loss: 2.2354
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2317 - loss: 2.2350
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2316 - loss: 2.2347
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2316 - loss: 2.2343
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2316 - loss: 2.2339
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2315 - loss: 2.2335
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2315 - loss: 2.2332
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2314 - loss: 2.2329
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2314 - loss: 2.2326
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2313 - loss: 2.2323
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2313 - loss: 2.2320
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2312 - loss: 2.2317
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2311 - loss: 2.2315 - val_accuracy: 0.2287 - val_loss: 2.1817
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.2130
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2372 - loss: 2.2263  
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2353 - loss: 2.2150
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2368 - loss: 2.2057
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2356 - loss: 2.2043
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2342 - loss: 2.2051
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2328 - loss: 2.2070
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2317 - loss: 2.2081
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2307 - loss: 2.2084
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2300 - loss: 2.2086
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2295 - loss: 2.2088
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2294 - loss: 2.2086
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2293 - loss: 2.2084
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2292 - loss: 2.2083
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2292 - loss: 2.2081
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2292 - loss: 2.2078
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2293 - loss: 2.2075
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2294 - loss: 2.2075
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2296 - loss: 2.2074
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2298 - loss: 2.2072
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2300 - loss: 2.2069
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2303 - loss: 2.2065
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2306 - loss: 2.2062
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2309 - loss: 2.2057
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2312 - loss: 2.2052
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2315 - loss: 2.2048
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2317 - loss: 2.2043
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2320 - loss: 2.2038
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2322 - loss: 2.2034
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2323 - loss: 2.2030 - val_accuracy: 0.2228 - val_loss: 2.1439
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5000 - loss: 1.7166
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2506 - loss: 2.1380  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2499 - loss: 2.1444
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2490 - loss: 2.1442
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2477 - loss: 2.1454
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2466 - loss: 2.1472
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2462 - loss: 2.1493
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2456 - loss: 2.1521
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1534
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1542
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.1552
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1562
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1568
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1569
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2450 - loss: 2.1571
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2448 - loss: 2.1576
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2447 - loss: 2.1581
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2445 - loss: 2.1584
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2443 - loss: 2.1589
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2440 - loss: 2.1593
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2439 - loss: 2.1596
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2437 - loss: 2.1599
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2435 - loss: 2.1601
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2434 - loss: 2.1602
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2432 - loss: 2.1604
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2431 - loss: 2.1606
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2430 - loss: 2.1607
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2428 - loss: 2.1609
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2427 - loss: 2.1610
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2426 - loss: 2.1610
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2426 - loss: 2.1611 - val_accuracy: 0.2359 - val_loss: 2.1292
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 1.9177
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2766 - loss: 2.1563  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2664 - loss: 2.1680
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2610 - loss: 2.1685
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2574 - loss: 2.1683
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2554 - loss: 2.1662
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2539 - loss: 2.1627
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2527 - loss: 2.1598
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2522 - loss: 2.1575
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2519 - loss: 2.1540
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2516 - loss: 2.1512
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2514 - loss: 2.1486
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2511 - loss: 2.1468
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2509 - loss: 2.1451
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2506 - loss: 2.1437
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.1427
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2498 - loss: 2.1419
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2494 - loss: 2.1412
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2492 - loss: 2.1409
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2489 - loss: 2.1407
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2487 - loss: 2.1405
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2486 - loss: 2.1403
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2485 - loss: 2.1401
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2484 - loss: 2.1399
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2483 - loss: 2.1399
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2481 - loss: 2.1398
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2480 - loss: 2.1397
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2479 - loss: 2.1397
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2478 - loss: 2.1396
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2477 - loss: 2.1395
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2477 - loss: 2.1395 - val_accuracy: 0.2370 - val_loss: 2.0892
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.8990
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2266 - loss: 2.1320  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2346 - loss: 2.1402
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2379 - loss: 2.1355
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2406 - loss: 2.1322
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2423 - loss: 2.1316
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2436 - loss: 2.1316
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2445 - loss: 2.1312
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2448 - loss: 2.1306
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2449 - loss: 2.1306
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1304
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.1299
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2456 - loss: 2.1294
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2458 - loss: 2.1291
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2460 - loss: 2.1289
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2461 - loss: 2.1288
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2463 - loss: 2.1285
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2467 - loss: 2.1281
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2471 - loss: 2.1277
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2475 - loss: 2.1272
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2478 - loss: 2.1269
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2480 - loss: 2.1265
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2482 - loss: 2.1263
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2484 - loss: 2.1260
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2486 - loss: 2.1257
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2488 - loss: 2.1255
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2490 - loss: 2.1252
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2491 - loss: 2.1250
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2492 - loss: 2.1247
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2493 - loss: 2.1244 - val_accuracy: 0.2435 - val_loss: 2.0695
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.1589
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2762 - loss: 2.0640  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0696
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0728
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2629 - loss: 2.0768
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2614 - loss: 2.0784
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0805
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2593 - loss: 2.0819
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2583 - loss: 2.0839
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2576 - loss: 2.0856
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0872
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0884
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2566 - loss: 2.0896
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2566 - loss: 2.0904
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2566 - loss: 2.0908
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0910
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0913
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0917
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2566 - loss: 2.0922
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.0926
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.0930
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2564 - loss: 2.0933
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0936
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0938
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2562 - loss: 2.0941
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2562 - loss: 2.0943
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0944
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0945
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0947
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0949
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2563 - loss: 2.0950 - val_accuracy: 0.2413 - val_loss: 2.0735
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 1.8900
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2770 - loss: 2.0510  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2774 - loss: 2.0586
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2724 - loss: 2.0736
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2685 - loss: 2.0804
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0814
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0807
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0797
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0788
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0786
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0789
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2648 - loss: 2.0793
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0796
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2641 - loss: 2.0798
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2638 - loss: 2.0799
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2634 - loss: 2.0800
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0801
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2627 - loss: 2.0804
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2624 - loss: 2.0807
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2621 - loss: 2.0808
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2619 - loss: 2.0809
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2617 - loss: 2.0809
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2615 - loss: 2.0808
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2614 - loss: 2.0808
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2612 - loss: 2.0808
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0808
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0808
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0808
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2608 - loss: 2.0808
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2607 - loss: 2.0809 - val_accuracy: 0.2405 - val_loss: 2.0627
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 20ms/step - accuracy: 0.3125 - loss: 2.1348
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2989 - loss: 2.0145  
[1m  65/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2914 - loss: 2.0279
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2869 - loss: 2.0332
[1m 143/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2838 - loss: 2.0367
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2806 - loss: 2.0404
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2782 - loss: 2.0455
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2764 - loss: 2.0496
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0527
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2737 - loss: 2.0554
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2726 - loss: 2.0576
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0594
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2706 - loss: 2.0610
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 2.0623
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2688 - loss: 2.0636
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0645
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0653
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0660
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0668
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0676
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0682
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0687
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0691
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2647 - loss: 2.0695
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0698
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2643 - loss: 2.0700
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2641 - loss: 2.0702
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0703
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0704
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0704
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2636 - loss: 2.0704 - val_accuracy: 0.2549 - val_loss: 2.0231
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.3452
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2765 - loss: 2.0481  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2757 - loss: 2.0622
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2714 - loss: 2.0693
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0676
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0676
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0677
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2685 - loss: 2.0670
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0653
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0643
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2680 - loss: 2.0638
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0633
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2678 - loss: 2.0631
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0630
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0629
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0629
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0629
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0629
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0630
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0632
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0632
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0633
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0633
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0633
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0633
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0632
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0632
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0632
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2654 - loss: 2.0632
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0632
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2652 - loss: 2.0632 - val_accuracy: 0.2474 - val_loss: 2.0324
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.2323
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0255  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2680 - loss: 2.0243
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2678 - loss: 2.0274
[1m 150/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2684 - loss: 2.0306
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2684 - loss: 2.0349
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0379
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0391
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2690 - loss: 2.0394
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2691 - loss: 2.0394
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2690 - loss: 2.0398
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2689 - loss: 2.0402
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0409
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2685 - loss: 2.0416
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2683 - loss: 2.0423
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0427
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0431
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0433
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0435
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0436
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0438
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0439
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0439
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0438
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0436
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2678 - loss: 2.0433
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2678 - loss: 2.0431
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0429
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0428
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0427
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2679 - loss: 2.0426 - val_accuracy: 0.2538 - val_loss: 2.0334
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.3125 - loss: 1.9241
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2524 - loss: 2.0668  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2557 - loss: 2.0481
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0386
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2576 - loss: 2.0381
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2588 - loss: 2.0370
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2596 - loss: 2.0353
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2594 - loss: 2.0347
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2597 - loss: 2.0338
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2598 - loss: 2.0331
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0327
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2601 - loss: 2.0328
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2605 - loss: 2.0324
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2608 - loss: 2.0320
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0316
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2614 - loss: 2.0312
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2617 - loss: 2.0307
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2619 - loss: 2.0304
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2621 - loss: 2.0303
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2623 - loss: 2.0302
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2625 - loss: 2.0301
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2626 - loss: 2.0300
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2628 - loss: 2.0299
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0298
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2632 - loss: 2.0295
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0292
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2635 - loss: 2.0290
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0288
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0285
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2640 - loss: 2.0283
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2641 - loss: 2.0283 - val_accuracy: 0.2574 - val_loss: 1.9994
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.6938
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2854 - loss: 2.0811  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0596
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2737 - loss: 2.0513
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2729 - loss: 2.0473
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2719 - loss: 2.0458
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0458
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2697 - loss: 2.0453
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2690 - loss: 2.0449
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2683 - loss: 2.0444
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0436
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0430
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0431
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0430
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0428
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0424
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0422
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0420
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0419
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0417
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0415
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0411
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0407
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0402
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0397
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0392
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0387
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0384
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0380
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2661 - loss: 2.0377 - val_accuracy: 0.2638 - val_loss: 2.0076
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.3750 - loss: 2.2942
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3058 - loss: 2.0047  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3038 - loss: 1.9809
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3019 - loss: 1.9751
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2996 - loss: 1.9766
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2974 - loss: 1.9797
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2951 - loss: 1.9830
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2932 - loss: 1.9853
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2921 - loss: 1.9879
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2910 - loss: 1.9900
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2899 - loss: 1.9922
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2889 - loss: 1.9940
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2882 - loss: 1.9954
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2876 - loss: 1.9968
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2870 - loss: 1.9983
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2864 - loss: 1.9997
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2858 - loss: 2.0011
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2851 - loss: 2.0026
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2845 - loss: 2.0039
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2839 - loss: 2.0050
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2833 - loss: 2.0059
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2828 - loss: 2.0067
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2823 - loss: 2.0074
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2818 - loss: 2.0080
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2815 - loss: 2.0086
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 2.0090
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2809 - loss: 2.0094
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 2.0097
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2803 - loss: 2.0101
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 2.0104
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2800 - loss: 2.0104 - val_accuracy: 0.2522 - val_loss: 2.0184
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.2362
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2598 - loss: 1.9723  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2713 - loss: 1.9607
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2744 - loss: 1.9575
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2779 - loss: 1.9583
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2797 - loss: 1.9616
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2806 - loss: 1.9662
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2805 - loss: 1.9698
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2804 - loss: 1.9724
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2804 - loss: 1.9744
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2803 - loss: 1.9760
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 1.9771
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 1.9780
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2797 - loss: 1.9790
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9799
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9807
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9814
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9821
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9829
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9835
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9840
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 1.9845
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 1.9851
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2794 - loss: 1.9857
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2794 - loss: 1.9864
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2794 - loss: 1.9871
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2794 - loss: 1.9876
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2793 - loss: 1.9883
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2792 - loss: 1.9889
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2790 - loss: 1.9895
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2789 - loss: 1.9899 - val_accuracy: 0.2599 - val_loss: 1.9931
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0359
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2500 - loss: 2.0723  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0503
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2646 - loss: 2.0323
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0273
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2685 - loss: 2.0249
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0234
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0219
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0202
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2730 - loss: 2.0190
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2738 - loss: 2.0179
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2743 - loss: 2.0172
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0165
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0158
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0150
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2754 - loss: 2.0143
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2757 - loss: 2.0134
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 2.0125
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2760 - loss: 2.0117
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0108
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2762 - loss: 2.0101
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2763 - loss: 2.0093
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2765 - loss: 2.0086
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2766 - loss: 2.0080
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2767 - loss: 2.0075
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2768 - loss: 2.0070
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2769 - loss: 2.0065
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2770 - loss: 2.0061
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2772 - loss: 2.0057
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2773 - loss: 2.0053
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2773 - loss: 2.0051 - val_accuracy: 0.2633 - val_loss: 2.0097
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.1197
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2684 - loss: 1.9692  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2710 - loss: 1.9922
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2713 - loss: 1.9963
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2726 - loss: 1.9946
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2736 - loss: 1.9945
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2749 - loss: 1.9945
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2763 - loss: 1.9940
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2772 - loss: 1.9935
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2780 - loss: 1.9937
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2788 - loss: 1.9936
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 1.9932
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 1.9927
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2803 - loss: 1.9923
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 1.9920
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 1.9917
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2807 - loss: 1.9914
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2809 - loss: 1.9911
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 1.9910
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 1.9911
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9911
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2813 - loss: 1.9910
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2815 - loss: 1.9910
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2816 - loss: 1.9909
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2817 - loss: 1.9909
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2817 - loss: 1.9908
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2818 - loss: 1.9907
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2818 - loss: 1.9906
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2818 - loss: 1.9905
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2818 - loss: 1.9904
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2818 - loss: 1.9903 - val_accuracy: 0.2549 - val_loss: 2.0044
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.1514
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2592 - loss: 1.9967  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2638 - loss: 1.9881
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2686 - loss: 1.9836
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2694 - loss: 1.9872
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2693 - loss: 1.9896
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2693 - loss: 1.9919
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2697 - loss: 1.9934
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2698 - loss: 1.9942
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2697 - loss: 1.9949
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 1.9952
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 1.9955
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 1.9958
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 1.9958
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 1.9957
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2699 - loss: 1.9955
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2701 - loss: 1.9953
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 1.9951
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 1.9950
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2704 - loss: 1.9950
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2705 - loss: 1.9950
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 1.9949
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 1.9947
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 1.9945
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 1.9942
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2715 - loss: 1.9938
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 1.9934
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2719 - loss: 1.9932
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2721 - loss: 1.9928
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2723 - loss: 1.9924
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2724 - loss: 1.9923 - val_accuracy: 0.2599 - val_loss: 1.9955
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.0761
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2384 - loss: 2.0009  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2492 - loss: 1.9972
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2577 - loss: 1.9879
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2638 - loss: 1.9828
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2672 - loss: 1.9806
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2692 - loss: 1.9789
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2712 - loss: 1.9774
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2729 - loss: 1.9766
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 1.9756
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2754 - loss: 1.9748
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2762 - loss: 1.9743
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2768 - loss: 1.9741
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2773 - loss: 1.9738
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2777 - loss: 1.9738
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2781 - loss: 1.9736
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2785 - loss: 1.9734
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9732
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2793 - loss: 1.9731
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 1.9731
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2797 - loss: 1.9732
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 1.9732
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2802 - loss: 1.9731
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 1.9729
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 1.9727
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2813 - loss: 1.9726
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2816 - loss: 1.9724
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2820 - loss: 1.9723
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2823 - loss: 1.9722
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2825 - loss: 1.9721
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2826 - loss: 1.9721 - val_accuracy: 0.2599 - val_loss: 1.9824

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 634ms/step
[1m65/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 789us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7:54[0m 813ms/step
[1m 59/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 866us/step  
[1m130/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 783us/step
[1m202/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 754us/step
[1m272/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 744us/step
[1m347/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 727us/step
[1m412/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 735us/step
[1m482/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 732us/step
[1m556/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 725us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m68/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 755us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 65/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 785us/step
[1m141/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 717us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 26.48 [%]
Global F1 score (validation) = 23.36 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[1.2103382e-01 1.6346511e-01 1.1072930e-01 ... 3.4307032e-03
  9.3231246e-02 1.1838398e-02]
 [1.6798922e-01 2.2383326e-01 1.8509939e-01 ... 7.9016289e-04
  1.6060773e-01 2.3299187e-02]
 [1.0554543e-01 1.4430457e-01 1.2951671e-01 ... 4.3297983e-03
  1.0036399e-01 1.2377570e-02]
 ...
 [1.4383735e-01 1.8971016e-01 2.1633184e-01 ... 4.1775274e-05
  2.0296755e-01 1.0371880e-01]
 [1.3207056e-01 1.9766995e-01 1.6874656e-01 ... 1.4245082e-03
  1.5385245e-01 2.2320351e-02]
 [1.0667035e-01 1.4695247e-01 1.5172635e-01 ... 5.2172560e-03
  9.8092966e-02 1.3134233e-02]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 30.13 [%]
Global accuracy score (test) = 24.33 [%]
Global F1 score (train) = 26.92 [%]
Global F1 score (test) = 21.62 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.03      0.01      0.01       184
 CAMINAR CON MÓVIL O LIBRO       0.16      0.38      0.22       184
       CAMINAR USUAL SPEED       0.12      0.09      0.10       184
            CAMINAR ZIGZAG       0.00      0.00      0.00       184
          DE PIE BARRIENDO       0.09      0.29      0.13       184
   DE PIE DOBLANDO TOALLAS       0.19      0.22      0.20       184
    DE PIE MOVIENDO LIBROS       0.17      0.18      0.17       184
          DE PIE USANDO PC       0.35      0.76      0.48       184
        FASE REPOSO CON K5       0.71      0.62      0.67       184
INCREMENTAL CICLOERGOMETRO       0.00      0.00      0.00       184
           SENTADO LEYENDO       0.34      0.24      0.28       184
         SENTADO USANDO PC       0.20      0.05      0.08       184
      SENTADO VIENDO LA TV       0.31      0.49      0.38       184
   SUBIR Y BAJAR ESCALERAS       0.11      0.02      0.03       184
                    TROTAR       0.96      0.33      0.49       161

                  accuracy                           0.24      2737
                 macro avg       0.25      0.24      0.22      2737
              weighted avg       0.24      0.24      0.21      2737


Accuracy capturado en la ejecución 15: 24.33 [%]
F1-score capturado en la ejecución 15: 21.62 [%]

=== EJECUCIÓN 16 ===

--- TRAIN (ejecución 16) ---

--- TEST (ejecución 16) ---
2025-11-07 14:23:37.009991: 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 14:23:37.021657: 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 00:00:1762521817.035514 2967903 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762521817.039667 2967903 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762521817.049618 2967903 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521817.049635 2967903 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521817.049637 2967903 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521817.049638 2967903 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:23:37.052792: 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 00:00:1762521819.302199 2967903 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762521820.787903 2968033 service.cc:152] XLA service 0x74b22c00bc70 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762521820.787928 2968033 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:23:40.814996: 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 00:00:1762521820.959109 2968033 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762521822.333246 2968033 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46:26[0m 2s/step - accuracy: 0.0625 - loss: 3.0251
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0638 - loss: 3.0707  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0725 - loss: 3.0783
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0774 - loss: 3.0641
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0808 - loss: 3.0488
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0831 - loss: 3.0362
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0854 - loss: 3.0236
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0877 - loss: 3.0113
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0897 - loss: 2.9991
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0915 - loss: 2.9877
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0930 - loss: 2.9774
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0942 - loss: 2.9683
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0952 - loss: 2.9612
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0962 - loss: 2.9537
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0973 - loss: 2.9460
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0982 - loss: 2.9390
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0990 - loss: 2.9327
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0998 - loss: 2.9267
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1007 - loss: 2.9203
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1016 - loss: 2.9141
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1025 - loss: 2.9088
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1033 - loss: 2.9032
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1042 - loss: 2.8978
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1051 - loss: 2.8923
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1060 - loss: 2.8877
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1068 - loss: 2.8831
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1077 - loss: 2.8780
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1086 - loss: 2.8734
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1094 - loss: 2.8688
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.1095 - loss: 2.8682
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.1096 - loss: 2.8680 - val_accuracy: 0.1754 - val_loss: 2.5125
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.2500 - loss: 2.3462
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1551 - loss: 2.6248  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1530 - loss: 2.6236
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1535 - loss: 2.6210
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1546 - loss: 2.6171
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1555 - loss: 2.6149
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1557 - loss: 2.6138
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1563 - loss: 2.6120
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1570 - loss: 2.6097
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1577 - loss: 2.6073
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1584 - loss: 2.6044
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1589 - loss: 2.6020
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1594 - loss: 2.5996
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1598 - loss: 2.5977
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1600 - loss: 2.5960
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1603 - loss: 2.5943
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1606 - loss: 2.5926
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1609 - loss: 2.5910
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1613 - loss: 2.5895
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1618 - loss: 2.5878
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1623 - loss: 2.5859
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1628 - loss: 2.5843
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1634 - loss: 2.5824
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1639 - loss: 2.5806
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1645 - loss: 2.5789
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1650 - loss: 2.5773
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1656 - loss: 2.5754
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1661 - loss: 2.5738
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1667 - loss: 2.5720
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1671 - loss: 2.5704
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1672 - loss: 2.5702 - val_accuracy: 0.1795 - val_loss: 2.3930
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.3790
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1630 - loss: 2.4725  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1708 - loss: 2.4753
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1730 - loss: 2.4745
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1755 - loss: 2.4713
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1773 - loss: 2.4679
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1784 - loss: 2.4647
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1795 - loss: 2.4631
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1809 - loss: 2.4614
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1819 - loss: 2.4605
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1828 - loss: 2.4595
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1835 - loss: 2.4588
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1839 - loss: 2.4582
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1843 - loss: 2.4577
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1847 - loss: 2.4574
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1849 - loss: 2.4571
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1851 - loss: 2.4569
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1853 - loss: 2.4565
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1855 - loss: 2.4561
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1856 - loss: 2.4556
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1857 - loss: 2.4550
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1858 - loss: 2.4544
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1859 - loss: 2.4538
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1861 - loss: 2.4531
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1862 - loss: 2.4523
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1864 - loss: 2.4515
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1866 - loss: 2.4507
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1868 - loss: 2.4500
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1869 - loss: 2.4492
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1871 - loss: 2.4485
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1871 - loss: 2.4485 - val_accuracy: 0.1954 - val_loss: 2.3363
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.2500 - loss: 2.4100
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2049 - loss: 2.4237  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2047 - loss: 2.4097
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2023 - loss: 2.4019
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2000 - loss: 2.3973
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1986 - loss: 2.3942
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1980 - loss: 2.3912
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1981 - loss: 2.3889
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1985 - loss: 2.3873
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1989 - loss: 2.3857
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1993 - loss: 2.3842
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1996 - loss: 2.3826
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1999 - loss: 2.3812
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2004 - loss: 2.3797
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2007 - loss: 2.3785
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2010 - loss: 2.3774
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2013 - loss: 2.3763
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2017 - loss: 2.3751
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2020 - loss: 2.3741
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2023 - loss: 2.3729
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2025 - loss: 2.3719
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2026 - loss: 2.3711
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2028 - loss: 2.3702
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2030 - loss: 2.3694
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2031 - loss: 2.3687
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2032 - loss: 2.3681
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2033 - loss: 2.3675
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2034 - loss: 2.3669
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2035 - loss: 2.3663
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2036 - loss: 2.3658 - val_accuracy: 0.1920 - val_loss: 2.2955
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.1250 - loss: 2.6020
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2074 - loss: 2.3336  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2058 - loss: 2.3371
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2042 - loss: 2.3342
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2045 - loss: 2.3306
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2045 - loss: 2.3308
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2050 - loss: 2.3309
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2055 - loss: 2.3316
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2066 - loss: 2.3309
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2076 - loss: 2.3300
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2083 - loss: 2.3292
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2090 - loss: 2.3283
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2096 - loss: 2.3275
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2102 - loss: 2.3266
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2107 - loss: 2.3257
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2111 - loss: 2.3248
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2115 - loss: 2.3238
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2118 - loss: 2.3230
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2122 - loss: 2.3221
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2124 - loss: 2.3214
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2126 - loss: 2.3208
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2128 - loss: 2.3202
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2130 - loss: 2.3197
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2131 - loss: 2.3191
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2133 - loss: 2.3186
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2135 - loss: 2.3181
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2136 - loss: 2.3175
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2138 - loss: 2.3170
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2139 - loss: 2.3165
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2139 - loss: 2.3163 - val_accuracy: 0.2072 - val_loss: 2.2427
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.2285
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1862 - loss: 2.3304  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1919 - loss: 2.3293
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1966 - loss: 2.3221
[1m 168/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2000 - loss: 2.3162
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2015 - loss: 2.3126
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2023 - loss: 2.3100
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2033 - loss: 2.3075
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2043 - loss: 2.3056
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2052 - loss: 2.3034
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2062 - loss: 2.3012
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2073 - loss: 2.2990
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2080 - loss: 2.2974
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2087 - loss: 2.2958
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2093 - loss: 2.2945
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2097 - loss: 2.2932
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2102 - loss: 2.2918
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2105 - loss: 2.2908
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2108 - loss: 2.2900
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2110 - loss: 2.2893
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2112 - loss: 2.2886
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2114 - loss: 2.2882
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2115 - loss: 2.2877
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2116 - loss: 2.2873
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2117 - loss: 2.2867
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2118 - loss: 2.2862
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2119 - loss: 2.2858
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2120 - loss: 2.2854
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2121 - loss: 2.2849
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2122 - loss: 2.2846
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2123 - loss: 2.2844 - val_accuracy: 0.2163 - val_loss: 2.1934
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.2938
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2512 - loss: 2.2226  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2460 - loss: 2.2184
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2392 - loss: 2.2244
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2358 - loss: 2.2267
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2341 - loss: 2.2274
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2334 - loss: 2.2283
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2327 - loss: 2.2285
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2322 - loss: 2.2283
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2313 - loss: 2.2284
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2306 - loss: 2.2287
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2300 - loss: 2.2291
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2294 - loss: 2.2296
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2291 - loss: 2.2299
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2289 - loss: 2.2300
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2288 - loss: 2.2302
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2287 - loss: 2.2305
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2286 - loss: 2.2307
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2285 - loss: 2.2310
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2283 - loss: 2.2313
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2281 - loss: 2.2316
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2279 - loss: 2.2318
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2278 - loss: 2.2320
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2277 - loss: 2.2321
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2276 - loss: 2.2322
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2275 - loss: 2.2323
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2275 - loss: 2.2323
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2275 - loss: 2.2323
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2275 - loss: 2.2322
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2275 - loss: 2.2321
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2275 - loss: 2.2320 - val_accuracy: 0.2130 - val_loss: 2.2069
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.3172
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2123 - loss: 2.2728  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2124 - loss: 2.2419
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2140 - loss: 2.2317
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2163 - loss: 2.2242
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2171 - loss: 2.2219
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2171 - loss: 2.2204
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2174 - loss: 2.2197
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2177 - loss: 2.2186
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2178 - loss: 2.2182
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2179 - loss: 2.2181
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2179 - loss: 2.2181
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2181 - loss: 2.2181
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2183 - loss: 2.2180
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2185 - loss: 2.2178
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2186 - loss: 2.2177
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2187 - loss: 2.2177
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2189 - loss: 2.2175
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2192 - loss: 2.2174
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2195 - loss: 2.2171
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2198 - loss: 2.2168
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2201 - loss: 2.2165
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2204 - loss: 2.2163
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2206 - loss: 2.2162
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2209 - loss: 2.2160
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2211 - loss: 2.2158
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2213 - loss: 2.2156
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2215 - loss: 2.2154
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2217 - loss: 2.2152
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.2219 - loss: 2.2149
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2219 - loss: 2.2149 - val_accuracy: 0.2176 - val_loss: 2.1603
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 1.9902
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2750 - loss: 2.1247  
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2636 - loss: 2.1499
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2565 - loss: 2.1586
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2531 - loss: 2.1651
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2520 - loss: 2.1661
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2520 - loss: 2.1668
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2515 - loss: 2.1687
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2504 - loss: 2.1708
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2494 - loss: 2.1727
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2486 - loss: 2.1736
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2480 - loss: 2.1743
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2472 - loss: 2.1753
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2465 - loss: 2.1760
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2458 - loss: 2.1765
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2453 - loss: 2.1767
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2448 - loss: 2.1769
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2443 - loss: 2.1770
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2440 - loss: 2.1771
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2436 - loss: 2.1772
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2433 - loss: 2.1774
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2430 - loss: 2.1775
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2428 - loss: 2.1777
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2425 - loss: 2.1779
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2422 - loss: 2.1780
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2420 - loss: 2.1781
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2418 - loss: 2.1783
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2416 - loss: 2.1784
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2414 - loss: 2.1784
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2413 - loss: 2.1784 - val_accuracy: 0.2290 - val_loss: 2.1375
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5000 - loss: 1.8750
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2821 - loss: 2.1407  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2688 - loss: 2.1431
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2615 - loss: 2.1489
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2568 - loss: 2.1520
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2520 - loss: 2.1551
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2494 - loss: 2.1562
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2475 - loss: 2.1560
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2469 - loss: 2.1550
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2466 - loss: 2.1543
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2463 - loss: 2.1540
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2462 - loss: 2.1538
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2461 - loss: 2.1538
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2459 - loss: 2.1540
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1542
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2456 - loss: 2.1542
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1542
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1541
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1539
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.1538
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.1537
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.1534
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.1533
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2453 - loss: 2.1531
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2453 - loss: 2.1530
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.1527
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.1526
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.1524
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.1522
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2454 - loss: 2.1521 - val_accuracy: 0.2387 - val_loss: 2.1304
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 2.2440
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2738 - loss: 2.1270  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2567 - loss: 2.1547
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2542 - loss: 2.1563
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2523 - loss: 2.1565
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2518 - loss: 2.1551
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2516 - loss: 2.1541
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2514 - loss: 2.1529
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2511 - loss: 2.1519
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2506 - loss: 2.1514
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2501 - loss: 2.1513
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2496 - loss: 2.1510
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2494 - loss: 2.1507
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2492 - loss: 2.1502
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2490 - loss: 2.1495
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2488 - loss: 2.1492
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2485 - loss: 2.1489
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2483 - loss: 2.1487
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2481 - loss: 2.1485
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2479 - loss: 2.1485
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2478 - loss: 2.1484
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2477 - loss: 2.1483
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2475 - loss: 2.1481
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2474 - loss: 2.1479
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2473 - loss: 2.1478
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2471 - loss: 2.1477
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2470 - loss: 2.1476
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2469 - loss: 2.1474
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2468 - loss: 2.1472
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2467 - loss: 2.1470 - val_accuracy: 0.2431 - val_loss: 2.1089
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 2.1173
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2454 - loss: 2.1270  
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2490 - loss: 2.1092
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2478 - loss: 2.1113
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2458 - loss: 2.1176
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2444 - loss: 2.1202
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2437 - loss: 2.1220
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2432 - loss: 2.1236
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2430 - loss: 2.1248
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2428 - loss: 2.1261
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2428 - loss: 2.1268
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2427 - loss: 2.1274
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2427 - loss: 2.1275
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2427 - loss: 2.1275
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2427 - loss: 2.1275
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2428 - loss: 2.1273
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2430 - loss: 2.1269
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2432 - loss: 2.1265
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2433 - loss: 2.1264
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2435 - loss: 2.1262
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2436 - loss: 2.1262
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2438 - loss: 2.1260
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2439 - loss: 2.1259
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2441 - loss: 2.1257
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2443 - loss: 2.1256
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2444 - loss: 2.1256
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2446 - loss: 2.1255
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2447 - loss: 2.1254
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2448 - loss: 2.1253
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2449 - loss: 2.1252 - val_accuracy: 0.2533 - val_loss: 2.0842
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 1.9126
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2435 - loss: 2.1362  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2536 - loss: 2.1056
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2577 - loss: 2.1003
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2586 - loss: 2.0985
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2588 - loss: 2.0973
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2588 - loss: 2.0960
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2589 - loss: 2.0962
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2593 - loss: 2.0961
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2595 - loss: 2.0963
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2595 - loss: 2.0972
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2591 - loss: 2.0984
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2588 - loss: 2.0994
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2585 - loss: 2.1002
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2583 - loss: 2.1009
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.1013
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.1016
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.1019
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2576 - loss: 2.1021
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2575 - loss: 2.1024
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2575 - loss: 2.1027
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2574 - loss: 2.1029
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2573 - loss: 2.1031
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2572 - loss: 2.1033
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2571 - loss: 2.1035
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2570 - loss: 2.1036
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.1037
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.1039
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.1039
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.1041
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2568 - loss: 2.1042 - val_accuracy: 0.2522 - val_loss: 2.0873
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.2511
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2414 - loss: 2.1143  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2447 - loss: 2.0983
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2475 - loss: 2.0946
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2499 - loss: 2.0909
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2514 - loss: 2.0890
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2517 - loss: 2.0904
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2520 - loss: 2.0912
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2522 - loss: 2.0922
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2522 - loss: 2.0936
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.0941
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2531 - loss: 2.0943
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2533 - loss: 2.0943
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2536 - loss: 2.0940
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2538 - loss: 2.0937
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2540 - loss: 2.0935
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.0932
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2545 - loss: 2.0930
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2546 - loss: 2.0929
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2547 - loss: 2.0928
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0927
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0928
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2549 - loss: 2.0928
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2549 - loss: 2.0929
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2550 - loss: 2.0929
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2551 - loss: 2.0929
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2551 - loss: 2.0929
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2552 - loss: 2.0930
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2553 - loss: 2.0930
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2554 - loss: 2.0929
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2555 - loss: 2.0929 - val_accuracy: 0.2379 - val_loss: 2.0918
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0288
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2499 - loss: 2.0843  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2545 - loss: 2.0743
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2597 - loss: 2.0655
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2617 - loss: 2.0616
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2625 - loss: 2.0614
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0610
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0619
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2647 - loss: 2.0631
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0639
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0647
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0655
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0663
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0673
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0682
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0688
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0692
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0695
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0697
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0699
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0702
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0705
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0707
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0710
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0712
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0715
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0717
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0719
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0722
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0724
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2667 - loss: 2.0724 - val_accuracy: 0.2431 - val_loss: 2.0681
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.4375 - loss: 2.0897
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2958 - loss: 2.0973  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2836 - loss: 2.0841
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2777 - loss: 2.0796
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0777
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2701 - loss: 2.0782
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2678 - loss: 2.0803
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0818
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0827
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2643 - loss: 2.0832
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0835
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2626 - loss: 2.0835
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2622 - loss: 2.0834
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2619 - loss: 2.0833
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2617 - loss: 2.0832
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2615 - loss: 2.0829
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2613 - loss: 2.0824
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0821
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0818
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2607 - loss: 2.0816
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2606 - loss: 2.0813
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2605 - loss: 2.0810
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2605 - loss: 2.0808
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0805
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0801
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0797
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0793
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2605 - loss: 2.0789
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2605 - loss: 2.0785
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2605 - loss: 2.0781
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2605 - loss: 2.0779 - val_accuracy: 0.2527 - val_loss: 2.0772
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.7344
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3123 - loss: 1.9232  
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2953 - loss: 1.9497
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2839 - loss: 1.9739
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2797 - loss: 1.9887
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2779 - loss: 1.9968
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2758 - loss: 2.0031
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2739 - loss: 2.0083
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2724 - loss: 2.0134
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2714 - loss: 2.0170
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0195
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0213
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2705 - loss: 2.0228
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0243
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2701 - loss: 2.0257
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0271
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0283
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2697 - loss: 2.0295
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 2.0306
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2695 - loss: 2.0315
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0325
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0334
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2692 - loss: 2.0342
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2691 - loss: 2.0349
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2690 - loss: 2.0355
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2689 - loss: 2.0361
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2688 - loss: 2.0366
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0370
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0374
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2685 - loss: 2.0376 - val_accuracy: 0.2553 - val_loss: 2.0584
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 20ms/step - accuracy: 0.1875 - loss: 1.9779
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2620 - loss: 2.0728  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0736
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0719
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0652
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2688 - loss: 2.0612
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2692 - loss: 2.0580
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0551
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0531
[1m 378/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2690 - loss: 2.0512
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0504
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2683 - loss: 2.0499
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0492
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0485
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0477
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0470
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2683 - loss: 2.0465
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2683 - loss: 2.0461
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0458
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0453
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0449
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0444
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2680 - loss: 2.0440
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0437
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2678 - loss: 2.0435
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0432
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0431
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0430
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2675 - loss: 2.0428 - val_accuracy: 0.2537 - val_loss: 2.0467
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 1.9916
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2597 - loss: 2.0128  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0231
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2589 - loss: 2.0199
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0207
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2623 - loss: 2.0234
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2632 - loss: 2.0262
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0290
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0305
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2643 - loss: 2.0322
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0332
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2646 - loss: 2.0341
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2647 - loss: 2.0345
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0344
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0343
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0339
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0337
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0335
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0334
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0332
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0332
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0331
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0331
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0330
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0329
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0327
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0325
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2673 - loss: 2.0323
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0322
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0321
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2678 - loss: 2.0320 - val_accuracy: 0.2651 - val_loss: 2.0486
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.0625 - loss: 2.1060
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2520 - loss: 1.9732  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2605 - loss: 1.9967
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0027
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0087
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2685 - loss: 2.0137
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2684 - loss: 2.0161
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2685 - loss: 2.0167
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2685 - loss: 2.0172
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0178
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0185
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0190
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0191
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2689 - loss: 2.0190
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2690 - loss: 2.0191
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2690 - loss: 2.0192
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2692 - loss: 2.0192
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0192
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0192
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2695 - loss: 2.0192
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 2.0193
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 2.0193
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2697 - loss: 2.0193
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2697 - loss: 2.0194
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0193
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0192
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0191
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2701 - loss: 2.0189
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0188
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0186
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2703 - loss: 2.0185 - val_accuracy: 0.2583 - val_loss: 2.0338
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.3125 - loss: 2.0846
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0506  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0568
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0592
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0570
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0532
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0506
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0481
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0461
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0444
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0433
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0419
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0407
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0393
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0376
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2714 - loss: 2.0363
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2719 - loss: 2.0350
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2723 - loss: 2.0336
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2728 - loss: 2.0321
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0309
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0297
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0285
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2743 - loss: 2.0274
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2746 - loss: 2.0266
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0257
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0250
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0244
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2753 - loss: 2.0238
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2754 - loss: 2.0233
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2756 - loss: 2.0228
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2756 - loss: 2.0227 - val_accuracy: 0.2810 - val_loss: 2.0137
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.0207
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2431 - loss: 2.0400  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2575 - loss: 2.0265
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0193
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0099
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2701 - loss: 2.0046
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2723 - loss: 1.9998
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2737 - loss: 1.9965
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2751 - loss: 1.9930
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2762 - loss: 1.9905
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2770 - loss: 1.9892
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 1.9882
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2781 - loss: 1.9871
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2784 - loss: 1.9864
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2787 - loss: 1.9861
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9857
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9856
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9855
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9855
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9855
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9856
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2788 - loss: 1.9856
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2788 - loss: 1.9856
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2788 - loss: 1.9856
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2788 - loss: 1.9857
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2788 - loss: 1.9858
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2787 - loss: 1.9858
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2787 - loss: 1.9859
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2787 - loss: 1.9860
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2787 - loss: 1.9861
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2787 - loss: 1.9861 - val_accuracy: 0.2853 - val_loss: 1.9760
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.0812
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2855 - loss: 1.9695  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2842 - loss: 1.9770
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2820 - loss: 1.9799
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2822 - loss: 1.9821
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2823 - loss: 1.9838
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2822 - loss: 1.9836
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2822 - loss: 1.9828
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2820 - loss: 1.9827
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2818 - loss: 1.9827
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2816 - loss: 1.9826
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2814 - loss: 1.9823
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9822
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 1.9820
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2809 - loss: 1.9819
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 1.9821
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2803 - loss: 1.9822
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 1.9823
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9824
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2793 - loss: 1.9824
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2791 - loss: 1.9825
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9826
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2787 - loss: 1.9828
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2786 - loss: 1.9829
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2785 - loss: 1.9830
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2784 - loss: 1.9832
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2783 - loss: 1.9833
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2782 - loss: 1.9835
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2782 - loss: 1.9836
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2781 - loss: 1.9837
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2781 - loss: 1.9837 - val_accuracy: 0.2618 - val_loss: 2.0106
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.9717
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3178 - loss: 1.9958  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3080 - loss: 1.9862
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3016 - loss: 1.9830
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2987 - loss: 1.9824
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2972 - loss: 1.9816
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2958 - loss: 1.9803
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2951 - loss: 1.9791
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2946 - loss: 1.9785
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2943 - loss: 1.9786
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2938 - loss: 1.9789
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2934 - loss: 1.9788
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2929 - loss: 1.9789
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2925 - loss: 1.9792
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2920 - loss: 1.9795
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2915 - loss: 1.9799
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2911 - loss: 1.9801
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2908 - loss: 1.9802
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2905 - loss: 1.9803
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2903 - loss: 1.9802
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2900 - loss: 1.9802
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2896 - loss: 1.9802
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2893 - loss: 1.9802
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2891 - loss: 1.9800
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2889 - loss: 1.9800
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2887 - loss: 1.9798
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2885 - loss: 1.9797
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2884 - loss: 1.9796
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2882 - loss: 1.9796
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2882 - loss: 1.9795 - val_accuracy: 0.2873 - val_loss: 1.9928
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 1.8829
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2312 - loss: 2.0630  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2489 - loss: 2.0446
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2544 - loss: 2.0349
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2578 - loss: 2.0296
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0258
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2624 - loss: 2.0219
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0183
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0155
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0126
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0093
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0067
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0044
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0019
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2728 - loss: 1.9994
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 1.9974
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 1.9954
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 1.9938
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 1.9924
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2765 - loss: 1.9911
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2770 - loss: 1.9900
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 1.9889
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2779 - loss: 1.9881
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2782 - loss: 1.9874
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2786 - loss: 1.9868
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2788 - loss: 1.9862
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2791 - loss: 1.9857
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2794 - loss: 1.9853
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9849
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 1.9845
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2800 - loss: 1.9842 - val_accuracy: 0.2666 - val_loss: 2.0342

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m52s[0m 614ms/step
[1m62/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 824us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:01[0m 827ms/step
[1m 68/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 751us/step  
[1m135/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 750us/step
[1m207/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 733us/step
[1m266/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 761us/step
[1m327/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 774us/step
[1m396/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 765us/step
[1m468/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 755us/step
[1m541/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 746us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m66/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 772us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 67/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 763us/step
[1m130/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 780us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 25.99 [%]
Global F1 score (validation) = 23.5 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.12693715 0.19503711 0.16906875 ... 0.0013586  0.14581086 0.01722894]
 [0.10355486 0.14510435 0.11155245 ... 0.00294463 0.09679772 0.01044026]
 [0.1522298  0.2218183  0.17420146 ... 0.00095243 0.14819999 0.01637574]
 ...
 [0.15450859 0.21212992 0.17457476 ... 0.00118811 0.14259996 0.01800504]
 [0.16690168 0.16848162 0.1538221  ... 0.00195414 0.1637417  0.02298331]
 [0.10754614 0.14546086 0.11364999 ... 0.00347858 0.09501871 0.01366555]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 30.66 [%]
Global accuracy score (test) = 24.22 [%]
Global F1 score (train) = 27.54 [%]
Global F1 score (test) = 21.67 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.24      0.02      0.04       184
 CAMINAR CON MÓVIL O LIBRO       0.13      0.40      0.19       184
       CAMINAR USUAL SPEED       0.16      0.04      0.07       184
            CAMINAR ZIGZAG       0.12      0.08      0.10       184
          DE PIE BARRIENDO       0.16      0.45      0.23       184
   DE PIE DOBLANDO TOALLAS       0.27      0.23      0.25       184
    DE PIE MOVIENDO LIBROS       0.33      0.16      0.21       184
          DE PIE USANDO PC       0.25      0.73      0.38       184
        FASE REPOSO CON K5       0.64      0.62      0.63       184
INCREMENTAL CICLOERGOMETRO       0.58      0.15      0.24       184
           SENTADO LEYENDO       0.31      0.37      0.34       184
         SENTADO USANDO PC       0.03      0.02      0.02       184
      SENTADO VIENDO LA TV       0.00      0.00      0.00       184
   SUBIR Y BAJAR ESCALERAS       0.20      0.04      0.06       184
                    TROTAR       0.95      0.32      0.48       161

                  accuracy                           0.24      2737
                 macro avg       0.29      0.24      0.22      2737
              weighted avg       0.28      0.24      0.21      2737


Accuracy capturado en la ejecución 16: 24.22 [%]
F1-score capturado en la ejecución 16: 21.67 [%]

=== EJECUCIÓN 17 ===

--- TRAIN (ejecución 17) ---

--- TEST (ejecución 17) ---
2025-11-07 14:24:44.195654: 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 14:24:44.206845: 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 00:00:1762521884.219949 2971671 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762521884.224084 2971671 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762521884.234072 2971671 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521884.234090 2971671 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521884.234092 2971671 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521884.234093 2971671 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:24:44.237268: 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 00:00:1762521886.498162 2971671 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762521887.992257 2971765 service.cc:152] XLA service 0x7d11c000bd00 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762521887.992307 2971765 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:24:48.021712: 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 00:00:1762521888.177438 2971765 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762521889.595772 2971765 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47:41[0m 2s/step - accuracy: 0.0625 - loss: 3.4947
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0607 - loss: 3.3816  
[1m  71/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0673 - loss: 3.3164
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0691 - loss: 3.2882
[1m 145/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0691 - loss: 3.2674
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0697 - loss: 3.2474
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0698 - loss: 3.2322
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0698 - loss: 3.2214
[1m 304/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0698 - loss: 3.2138
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0697 - loss: 3.2060
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0697 - loss: 3.1986
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0698 - loss: 3.1918
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0701 - loss: 3.1846
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0703 - loss: 3.1775
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0706 - loss: 3.1710
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0709 - loss: 3.1647
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0712 - loss: 3.1590
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0715 - loss: 3.1530
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0717 - loss: 3.1477
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0720 - loss: 3.1420
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0722 - loss: 3.1369
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0725 - loss: 3.1320
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0727 - loss: 3.1273
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0729 - loss: 3.1229
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0732 - loss: 3.1185
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0734 - loss: 3.1141
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0737 - loss: 3.1097
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0741 - loss: 3.1050
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0744 - loss: 3.1010
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0747 - loss: 3.0972
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0747 - loss: 3.0965
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0747 - loss: 3.0964 - val_accuracy: 0.1319 - val_loss: 2.6813
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 3.0238
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0672 - loss: 2.9013  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0788 - loss: 2.8722
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0835 - loss: 2.8574
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0868 - loss: 2.8464
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0887 - loss: 2.8407
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0900 - loss: 2.8353
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0908 - loss: 2.8306
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0917 - loss: 2.8259
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0922 - loss: 2.8222
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0926 - loss: 2.8189
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0930 - loss: 2.8156
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0936 - loss: 2.8127
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0940 - loss: 2.8103
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0944 - loss: 2.8080
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0949 - loss: 2.8055
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0954 - loss: 2.8027
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0960 - loss: 2.8001
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0964 - loss: 2.7980
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0969 - loss: 2.7960
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0973 - loss: 2.7938
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0977 - loss: 2.7918
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0982 - loss: 2.7897
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0987 - loss: 2.7875
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0991 - loss: 2.7856
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0996 - loss: 2.7836
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1000 - loss: 2.7817
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1004 - loss: 2.7799
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1008 - loss: 2.7781
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1011 - loss: 2.7765 - val_accuracy: 0.1323 - val_loss: 2.5796
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.7961
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1306 - loss: 2.6754  
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1241 - loss: 2.6654
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1229 - loss: 2.6620
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1219 - loss: 2.6606
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1218 - loss: 2.6610
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1215 - loss: 2.6625
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1218 - loss: 2.6616
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1220 - loss: 2.6599
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1220 - loss: 2.6584
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1223 - loss: 2.6565
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1227 - loss: 2.6546
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1230 - loss: 2.6531
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1234 - loss: 2.6515
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1237 - loss: 2.6501
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1239 - loss: 2.6490
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1241 - loss: 2.6479
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1244 - loss: 2.6467
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1246 - loss: 2.6456
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1249 - loss: 2.6444
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1252 - loss: 2.6431
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1255 - loss: 2.6420
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1257 - loss: 2.6408
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1260 - loss: 2.6397
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1262 - loss: 2.6386
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1265 - loss: 2.6374
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1269 - loss: 2.6363
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1272 - loss: 2.6353
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1276 - loss: 2.6342
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1279 - loss: 2.6332
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1280 - loss: 2.6331 - val_accuracy: 0.2013 - val_loss: 2.4712
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.3900
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1608 - loss: 2.4779  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1671 - loss: 2.4928
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1672 - loss: 2.5060
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1675 - loss: 2.5132
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1673 - loss: 2.5172
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1673 - loss: 2.5189
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1677 - loss: 2.5196
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1681 - loss: 2.5196
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1685 - loss: 2.5199
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1688 - loss: 2.5201
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1691 - loss: 2.5202
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1692 - loss: 2.5202
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1693 - loss: 2.5200
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1693 - loss: 2.5196
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1693 - loss: 2.5194
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1693 - loss: 2.5192
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1692 - loss: 2.5189
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1691 - loss: 2.5187
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1691 - loss: 2.5184
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1690 - loss: 2.5181
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1689 - loss: 2.5178
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1688 - loss: 2.5175
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1688 - loss: 2.5172
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1688 - loss: 2.5167
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1688 - loss: 2.5163
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1688 - loss: 2.5158
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1689 - loss: 2.5153
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1689 - loss: 2.5148
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1689 - loss: 2.5146 - val_accuracy: 0.2159 - val_loss: 2.3914
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.5957
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1539 - loss: 2.4829  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1568 - loss: 2.4762
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1613 - loss: 2.4697
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1649 - loss: 2.4653
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1680 - loss: 2.4629
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1698 - loss: 2.4623
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1710 - loss: 2.4623
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1721 - loss: 2.4617
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1729 - loss: 2.4611
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1738 - loss: 2.4603
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1745 - loss: 2.4597
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1753 - loss: 2.4590
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1759 - loss: 2.4581
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1764 - loss: 2.4575
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1769 - loss: 2.4568
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1773 - loss: 2.4561
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1776 - loss: 2.4554
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1779 - loss: 2.4547
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1782 - loss: 2.4540
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1786 - loss: 2.4532
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1790 - loss: 2.4523
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1793 - loss: 2.4514
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1797 - loss: 2.4504
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1800 - loss: 2.4495
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1803 - loss: 2.4484
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1806 - loss: 2.4474
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1809 - loss: 2.4464
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1812 - loss: 2.4455
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1812 - loss: 2.4454 - val_accuracy: 0.2302 - val_loss: 2.3052
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.1875 - loss: 2.2238
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2170 - loss: 2.3067  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2120 - loss: 2.3201
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2099 - loss: 2.3287
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2076 - loss: 2.3346
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2059 - loss: 2.3368
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2050 - loss: 2.3371
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2040 - loss: 2.3379
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2032 - loss: 2.3390
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2029 - loss: 2.3397
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2024 - loss: 2.3402
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2023 - loss: 2.3402
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2020 - loss: 2.3406
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2018 - loss: 2.3408
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2015 - loss: 2.3411
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2012 - loss: 2.3413
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2010 - loss: 2.3415
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2009 - loss: 2.3417
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2007 - loss: 2.3419
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2007 - loss: 2.3421
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2006 - loss: 2.3423
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2005 - loss: 2.3426
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2004 - loss: 2.3429
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2003 - loss: 2.3430
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2003 - loss: 2.3432
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2003 - loss: 2.3432
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2003 - loss: 2.3433
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2003 - loss: 2.3434
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2003 - loss: 2.3436
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2003 - loss: 2.3437
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2003 - loss: 2.3437 - val_accuracy: 0.2368 - val_loss: 2.2361
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.4375 - loss: 2.0021
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2049 - loss: 2.3557  
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2036 - loss: 2.3515
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2023 - loss: 2.3458
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2021 - loss: 2.3412
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2011 - loss: 2.3392
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2003 - loss: 2.3374
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1998 - loss: 2.3356
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1991 - loss: 2.3339
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1986 - loss: 2.3330
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1983 - loss: 2.3318
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1982 - loss: 2.3305
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1983 - loss: 2.3290
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1987 - loss: 2.3275
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1990 - loss: 2.3265
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1993 - loss: 2.3256
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1996 - loss: 2.3246
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1998 - loss: 2.3237
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2001 - loss: 2.3227
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2004 - loss: 2.3218
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2006 - loss: 2.3209
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2009 - loss: 2.3200
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2012 - loss: 2.3192
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2015 - loss: 2.3183
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2019 - loss: 2.3173
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2023 - loss: 2.3163
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2026 - loss: 2.3155
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2030 - loss: 2.3147
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2032 - loss: 2.3140
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2035 - loss: 2.3133 - val_accuracy: 0.2546 - val_loss: 2.1846
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.4118
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2302 - loss: 2.3093  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2232 - loss: 2.2941
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2171 - loss: 2.2910
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2157 - loss: 2.2891
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2145 - loss: 2.2869
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2139 - loss: 2.2841
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2137 - loss: 2.2816
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2137 - loss: 2.2799
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2141 - loss: 2.2784
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2141 - loss: 2.2771
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2140 - loss: 2.2762
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2139 - loss: 2.2754
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2139 - loss: 2.2747
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2139 - loss: 2.2742
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2140 - loss: 2.2737
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2141 - loss: 2.2731
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2142 - loss: 2.2726
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2142 - loss: 2.2722
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2142 - loss: 2.2719
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2142 - loss: 2.2717
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2142 - loss: 2.2715
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2143 - loss: 2.2712
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2143 - loss: 2.2708
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2143 - loss: 2.2705
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2144 - loss: 2.2703
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2144 - loss: 2.2700
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2144 - loss: 2.2696
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2145 - loss: 2.2693
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2145 - loss: 2.2690 - val_accuracy: 0.2585 - val_loss: 2.1474
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.2500 - loss: 2.3308
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2539 - loss: 2.2695  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2393 - loss: 2.2545
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2338 - loss: 2.2495
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2317 - loss: 2.2458
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2301 - loss: 2.2448
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2289 - loss: 2.2444
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2441
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2275 - loss: 2.2436
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2267 - loss: 2.2434
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2263 - loss: 2.2426
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2259 - loss: 2.2420
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2257 - loss: 2.2412
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2255 - loss: 2.2405
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2255 - loss: 2.2398
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2254 - loss: 2.2391
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2255 - loss: 2.2383
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2256 - loss: 2.2376
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2256 - loss: 2.2370
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2257 - loss: 2.2363
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2257 - loss: 2.2356
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2257 - loss: 2.2348
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2258 - loss: 2.2341
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2258 - loss: 2.2334
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2259 - loss: 2.2328
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2259 - loss: 2.2322
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2259 - loss: 2.2317
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2259 - loss: 2.2313
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2260 - loss: 2.2308
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2260 - loss: 2.2304
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2260 - loss: 2.2301 - val_accuracy: 0.2657 - val_loss: 2.1099
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3750 - loss: 1.9815
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2585 - loss: 2.2164  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2519 - loss: 2.2170
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2490 - loss: 2.2148
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2470 - loss: 2.2103
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2453 - loss: 2.2061
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2439 - loss: 2.2035
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2434 - loss: 2.2011
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2433 - loss: 2.1991
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2428 - loss: 2.1974
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2422 - loss: 2.1965
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2418 - loss: 2.1955
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2414 - loss: 2.1946
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2410 - loss: 2.1941
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2408 - loss: 2.1936
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2404 - loss: 2.1933
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2402 - loss: 2.1930
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2400 - loss: 2.1927
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2397 - loss: 2.1923
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2395 - loss: 2.1918
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2392 - loss: 2.1915
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2390 - loss: 2.1913
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2388 - loss: 2.1911
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2386 - loss: 2.1908
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2384 - loss: 2.1906
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2383 - loss: 2.1904
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2381 - loss: 2.1902
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2379 - loss: 2.1899
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2378 - loss: 2.1897
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2377 - loss: 2.1894 - val_accuracy: 0.2703 - val_loss: 2.0915
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.1095
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2333 - loss: 2.1988  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2331 - loss: 2.2009
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2329 - loss: 2.2029
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2336 - loss: 2.1999
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2345 - loss: 2.1953
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2361 - loss: 2.1915
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2369 - loss: 2.1893
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2377 - loss: 2.1866
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2381 - loss: 2.1847
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2382 - loss: 2.1835
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2381 - loss: 2.1825
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2379 - loss: 2.1817
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2376 - loss: 2.1811
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2373 - loss: 2.1806
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2370 - loss: 2.1804
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2368 - loss: 2.1802
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2365 - loss: 2.1800
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2363 - loss: 2.1796
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2361 - loss: 2.1791
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2360 - loss: 2.1787
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2359 - loss: 2.1783
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2358 - loss: 2.1779
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2357 - loss: 2.1775
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2356 - loss: 2.1771
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2356 - loss: 2.1766
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2356 - loss: 2.1762
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2356 - loss: 2.1758
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2356 - loss: 2.1754
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2356 - loss: 2.1749
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2357 - loss: 2.1749 - val_accuracy: 0.2814 - val_loss: 2.0570
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 1.8415
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2410 - loss: 2.1456  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2367 - loss: 2.1541
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2379 - loss: 2.1516
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2375 - loss: 2.1505
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2366 - loss: 2.1493
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2360 - loss: 2.1491
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2355 - loss: 2.1486
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2350 - loss: 2.1487
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2345 - loss: 2.1489
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2341 - loss: 2.1488
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2341 - loss: 2.1485
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2341 - loss: 2.1479
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2342 - loss: 2.1473
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2343 - loss: 2.1471
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2342 - loss: 2.1471
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2343 - loss: 2.1471
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2344 - loss: 2.1469
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2345 - loss: 2.1469
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2345 - loss: 2.1469
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2346 - loss: 2.1467
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2347 - loss: 2.1466
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2349 - loss: 2.1464
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2351 - loss: 2.1461
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2353 - loss: 2.1459
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2355 - loss: 2.1457
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2357 - loss: 2.1456
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2358 - loss: 2.1454
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2360 - loss: 2.1452
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2363 - loss: 2.1450
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2363 - loss: 2.1450 - val_accuracy: 0.2694 - val_loss: 2.0460
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.3125 - loss: 2.1206
[1m  44/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2536 - loss: 2.1755  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2569 - loss: 2.1492
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2540 - loss: 2.1402
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2522 - loss: 2.1372
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2513 - loss: 2.1341
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2506 - loss: 2.1305
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2502 - loss: 2.1278
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2495 - loss: 2.1259
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2492 - loss: 2.1246
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2490 - loss: 2.1236
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2488 - loss: 2.1224
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2485 - loss: 2.1212
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2484 - loss: 2.1199
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2484 - loss: 2.1189
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2483 - loss: 2.1180
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2483 - loss: 2.1175
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2481 - loss: 2.1169
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2480 - loss: 2.1164
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2479 - loss: 2.1159
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2478 - loss: 2.1153
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2478 - loss: 2.1149
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2478 - loss: 2.1145
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2478 - loss: 2.1142
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2478 - loss: 2.1139
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2478 - loss: 2.1137
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2479 - loss: 2.1134
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2480 - loss: 2.1131
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2480 - loss: 2.1129
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2481 - loss: 2.1127 - val_accuracy: 0.2742 - val_loss: 2.0459
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.1866
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2140 - loss: 2.1474  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2276 - loss: 2.1402
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2349 - loss: 2.1367
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2425 - loss: 2.1303
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2460 - loss: 2.1262
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2480 - loss: 2.1237
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2491 - loss: 2.1223
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2505 - loss: 2.1203
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2518 - loss: 2.1186
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2526 - loss: 2.1171
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2532 - loss: 2.1157
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2537 - loss: 2.1142
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2540 - loss: 2.1132
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1122
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2544 - loss: 2.1114
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2544 - loss: 2.1108
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2544 - loss: 2.1106
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2544 - loss: 2.1103
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1101
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2542 - loss: 2.1097
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2542 - loss: 2.1095
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2541 - loss: 2.1092
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2540 - loss: 2.1089
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2540 - loss: 2.1086
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2540 - loss: 2.1084
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2541 - loss: 2.1080
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2541 - loss: 2.1077
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2541 - loss: 2.1073
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2542 - loss: 2.1070
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2542 - loss: 2.1067 - val_accuracy: 0.2764 - val_loss: 2.0228
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.3355
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2973 - loss: 2.0569  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2883 - loss: 2.0586
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2831 - loss: 2.0614
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2798 - loss: 2.0648
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2777 - loss: 2.0653
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2764 - loss: 2.0649
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2759 - loss: 2.0640
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0639
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0644
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2733 - loss: 2.0640
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2727 - loss: 2.0641
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2720 - loss: 2.0643
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0644
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0645
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2706 - loss: 2.0649
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2701 - loss: 2.0654
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2697 - loss: 2.0661
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0669
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2689 - loss: 2.0677
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2685 - loss: 2.0685
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0693
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0701
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0707
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0712
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0717
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0722
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0726
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0730
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2662 - loss: 2.0733 - val_accuracy: 0.2757 - val_loss: 2.0216
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.3412
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2550 - loss: 2.0814  
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2555 - loss: 2.0613
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2551 - loss: 2.0589
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2543 - loss: 2.0579
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2540 - loss: 2.0577
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2539 - loss: 2.0572
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2539 - loss: 2.0570
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2543 - loss: 2.0566
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2547 - loss: 2.0561
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2550 - loss: 2.0555
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2550 - loss: 2.0554
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2550 - loss: 2.0555
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0561
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0563
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0566
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2549 - loss: 2.0566
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2549 - loss: 2.0566
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2550 - loss: 2.0567
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2549 - loss: 2.0569
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2549 - loss: 2.0570
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2550 - loss: 2.0571
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2551 - loss: 2.0572
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2551 - loss: 2.0573
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2552 - loss: 2.0573
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2553 - loss: 2.0574
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2554 - loss: 2.0574
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2554 - loss: 2.0575
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2555 - loss: 2.0576
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2555 - loss: 2.0576
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2555 - loss: 2.0576 - val_accuracy: 0.2646 - val_loss: 2.0176
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 1.9713
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2492 - loss: 2.0951  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2485 - loss: 2.1011
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2468 - loss: 2.1002
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2479 - loss: 2.0972
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2496 - loss: 2.0958
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2504 - loss: 2.0953
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2511 - loss: 2.0941
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2515 - loss: 2.0924
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2521 - loss: 2.0899
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2525 - loss: 2.0882
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.0869
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2531 - loss: 2.0853
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2534 - loss: 2.0840
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2537 - loss: 2.0829
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2541 - loss: 2.0818
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2544 - loss: 2.0807
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2547 - loss: 2.0794
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2549 - loss: 2.0784
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2552 - loss: 2.0773
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2555 - loss: 2.0763
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2557 - loss: 2.0754
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.0745
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0738
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0732
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.0726
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2566 - loss: 2.0719
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0713
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.0707
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2570 - loss: 2.0702
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2570 - loss: 2.0701 - val_accuracy: 0.2551 - val_loss: 2.0109
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.1253
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0755  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2608 - loss: 2.0664
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2593 - loss: 2.0637
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2587 - loss: 2.0613
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2585 - loss: 2.0572
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0549
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0529
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0516
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2578 - loss: 2.0505
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2576 - loss: 2.0501
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2574 - loss: 2.0499
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0500
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2575 - loss: 2.0499
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.0499
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.0499
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0498
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2582 - loss: 2.0496
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2583 - loss: 2.0496
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2583 - loss: 2.0496
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2583 - loss: 2.0496
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2584 - loss: 2.0494
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2585 - loss: 2.0492
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2585 - loss: 2.0490
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2586 - loss: 2.0488
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2587 - loss: 2.0484
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2588 - loss: 2.0482
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2589 - loss: 2.0481
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2591 - loss: 2.0479
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2592 - loss: 2.0478
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2592 - loss: 2.0477 - val_accuracy: 0.2809 - val_loss: 1.9865
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 1.9020
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2429 - loss: 2.0614  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2488 - loss: 2.0639
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0533
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2595 - loss: 2.0459
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2613 - loss: 2.0411
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2625 - loss: 2.0380
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2632 - loss: 2.0355
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0340
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0332
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0332
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2638 - loss: 2.0332
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2640 - loss: 2.0331
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2640 - loss: 2.0331
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2640 - loss: 2.0331
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2641 - loss: 2.0331
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2641 - loss: 2.0331
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0331
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2643 - loss: 2.0332
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0332
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0332
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2647 - loss: 2.0331
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2648 - loss: 2.0332
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0333
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0334
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0335
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0336
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0338
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0339
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2651 - loss: 2.0339 - val_accuracy: 0.2831 - val_loss: 1.9782
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.2368
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2167 - loss: 2.0971  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2304 - loss: 2.0702
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2358 - loss: 2.0581
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2396 - loss: 2.0487
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2423 - loss: 2.0429
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2441 - loss: 2.0399
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2463 - loss: 2.0367
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2484 - loss: 2.0331
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2501 - loss: 2.0298
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2512 - loss: 2.0274
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2520 - loss: 2.0255
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.0240
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2534 - loss: 2.0228
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2540 - loss: 2.0220
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2545 - loss: 2.0214
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2551 - loss: 2.0210
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2556 - loss: 2.0207
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0205
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2564 - loss: 2.0206
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0207
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2570 - loss: 2.0207
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2574 - loss: 2.0205
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.0203
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0200
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2584 - loss: 2.0198
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2586 - loss: 2.0197
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2589 - loss: 2.0197
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2590 - loss: 2.0196
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2591 - loss: 2.0196 - val_accuracy: 0.2827 - val_loss: 1.9637
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 19ms/step - accuracy: 0.1250 - loss: 2.5465
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0050  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2650 - loss: 1.9916
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2666 - loss: 1.9881
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2682 - loss: 1.9873
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2701 - loss: 1.9860
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2704 - loss: 1.9867
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2707 - loss: 1.9881
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2708 - loss: 1.9895
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2710 - loss: 1.9908
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 1.9919
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 1.9930
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2706 - loss: 1.9938
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2705 - loss: 1.9944
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2704 - loss: 1.9950
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2704 - loss: 1.9957
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2704 - loss: 1.9963
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2705 - loss: 1.9968
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2706 - loss: 1.9972
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 1.9975
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 1.9978
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 1.9981
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 1.9984
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2712 - loss: 1.9986
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 1.9987
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2715 - loss: 1.9989
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 1.9993
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 1.9995
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 1.9998
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2718 - loss: 2.0002 - val_accuracy: 0.2777 - val_loss: 1.9705
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.0845
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2994 - loss: 2.0232  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2889 - loss: 2.0233
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2840 - loss: 2.0176
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2810 - loss: 2.0104
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2791 - loss: 2.0065
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2772 - loss: 2.0046
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2758 - loss: 2.0037
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0031
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2746 - loss: 2.0019
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0012
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0007
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2743 - loss: 2.0001
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2743 - loss: 1.9996
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2742 - loss: 1.9995
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2741 - loss: 1.9995
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2739 - loss: 1.9995
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2738 - loss: 1.9994
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 1.9993
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 1.9992
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 1.9991
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2735 - loss: 1.9990
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2735 - loss: 1.9990
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2735 - loss: 1.9989
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2735 - loss: 1.9989
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2734 - loss: 1.9989
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2734 - loss: 1.9989
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2734 - loss: 1.9989
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2734 - loss: 1.9990
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2734 - loss: 1.9990 - val_accuracy: 0.2746 - val_loss: 1.9808
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.2269
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2657 - loss: 1.9583  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2725 - loss: 1.9792
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2745 - loss: 1.9840
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2755 - loss: 1.9863
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2757 - loss: 1.9896
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2758 - loss: 1.9919
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2759 - loss: 1.9937
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2761 - loss: 1.9943
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2764 - loss: 1.9942
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2764 - loss: 1.9943
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2764 - loss: 1.9946
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2762 - loss: 1.9947
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2762 - loss: 1.9946
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2762 - loss: 1.9947
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2762 - loss: 1.9948
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 1.9951
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2760 - loss: 1.9953
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 1.9952
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 1.9949
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2763 - loss: 1.9945
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2764 - loss: 1.9942
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2764 - loss: 1.9939
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2765 - loss: 1.9936
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2765 - loss: 1.9933
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2766 - loss: 1.9930
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2766 - loss: 1.9928
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2767 - loss: 1.9925
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2768 - loss: 1.9923
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2769 - loss: 1.9920
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2769 - loss: 1.9920 - val_accuracy: 0.2912 - val_loss: 1.9666
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.0108
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2995 - loss: 1.8920  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2983 - loss: 1.9121
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2985 - loss: 1.9312
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2976 - loss: 1.9414
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2963 - loss: 1.9483
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2951 - loss: 1.9537
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2940 - loss: 1.9572
[1m 306/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2928 - loss: 1.9599
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2912 - loss: 1.9623
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2900 - loss: 1.9641
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2889 - loss: 1.9659
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2880 - loss: 1.9671
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2871 - loss: 1.9682
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2865 - loss: 1.9691
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2859 - loss: 1.9699
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2854 - loss: 1.9705
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2850 - loss: 1.9711
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2847 - loss: 1.9716
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2845 - loss: 1.9719
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2842 - loss: 1.9721
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2840 - loss: 1.9724
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2837 - loss: 1.9728
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2835 - loss: 1.9731
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2833 - loss: 1.9733
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2832 - loss: 1.9737
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2831 - loss: 1.9739
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2830 - loss: 1.9741
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2829 - loss: 1.9743
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2829 - loss: 1.9745
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2829 - loss: 1.9745 - val_accuracy: 0.2805 - val_loss: 1.9563
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.1877
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2378 - loss: 2.0297  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0030
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2651 - loss: 1.9981
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2679 - loss: 1.9970
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2698 - loss: 1.9951
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2708 - loss: 1.9918
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2712 - loss: 1.9904
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2716 - loss: 1.9885
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2720 - loss: 1.9872
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2726 - loss: 1.9856
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2731 - loss: 1.9841
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2733 - loss: 1.9832
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2735 - loss: 1.9826
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 1.9822
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2738 - loss: 1.9819
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2739 - loss: 1.9817
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2741 - loss: 1.9814
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2742 - loss: 1.9811
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2743 - loss: 1.9808
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 1.9806
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2746 - loss: 1.9804
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 1.9803
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 1.9801
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 1.9800
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 1.9800
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 1.9799
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 1.9798
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 1.9797
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 1.9796
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2748 - loss: 1.9795 - val_accuracy: 0.2851 - val_loss: 1.9501

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m52s[0m 614ms/step
[1m66/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 772us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7:46[0m 801ms/step
[1m 64/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 796us/step  
[1m133/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 762us/step
[1m205/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 738us/step
[1m273/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 740us/step
[1m338/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 748us/step
[1m408/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 742us/step
[1m477/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 741us/step
[1m545/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 742us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m66/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 780us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[1m 68/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 753us/step
[1m134/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 757us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 26.66 [%]
Global F1 score (validation) = 23.69 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.13356583 0.1343698  0.1677334  ... 0.00344316 0.15038358 0.01295411]
 [0.17311698 0.17272806 0.19401813 ... 0.00083127 0.19102268 0.0128064 ]
 [0.15109652 0.15757306 0.17260945 ... 0.00197403 0.1504834  0.0141988 ]
 ...
 [0.18466794 0.18528971 0.19867194 ... 0.00085367 0.13479392 0.01976696]
 [0.14796193 0.15649915 0.16376922 ... 0.00407385 0.16591892 0.01303174]
 [0.13027689 0.13730344 0.13165222 ... 0.00438641 0.13008536 0.00981523]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 29.55 [%]
Global accuracy score (test) = 23.27 [%]
Global F1 score (train) = 28.36 [%]
Global F1 score (test) = 20.67 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.15      0.17      0.16       184
 CAMINAR CON MÓVIL O LIBRO       0.13      0.04      0.06       184
       CAMINAR USUAL SPEED       0.18      0.36      0.24       184
            CAMINAR ZIGZAG       0.12      0.02      0.04       184
          DE PIE BARRIENDO       0.24      0.29      0.26       184
   DE PIE DOBLANDO TOALLAS       0.20      0.07      0.10       184
    DE PIE MOVIENDO LIBROS       0.20      0.14      0.16       184
          DE PIE USANDO PC       0.29      0.90      0.44       184
        FASE REPOSO CON K5       1.00      0.12      0.22       184
INCREMENTAL CICLOERGOMETRO       0.22      0.42      0.29       184
           SENTADO LEYENDO       0.21      0.24      0.22       184
         SENTADO USANDO PC       0.07      0.03      0.04       184
      SENTADO VIENDO LA TV       0.21      0.23      0.22       184
   SUBIR Y BAJAR ESCALERAS       0.15      0.12      0.14       184
                    TROTAR       0.98      0.34      0.51       161

                  accuracy                           0.23      2737
                 macro avg       0.29      0.23      0.21      2737
              weighted avg       0.28      0.23      0.20      2737


Accuracy capturado en la ejecución 17: 23.27 [%]
F1-score capturado en la ejecución 17: 20.67 [%]

=== EJECUCIÓN 18 ===

--- TRAIN (ejecución 18) ---

--- TEST (ejecución 18) ---
2025-11-07 14:25:51.468697: 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 14:25:51.479744: 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 00:00:1762521951.492866 2975407 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762521951.496802 2975407 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762521951.506598 2975407 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521951.506622 2975407 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521951.506624 2975407 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762521951.506625 2975407 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:25:51.509525: 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 00:00:1762521953.762068 2975407 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762521955.249395 2975508 service.cc:152] XLA service 0x7bc06801e450 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762521955.249444 2975508 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:25:55.281526: 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 00:00:1762521955.425770 2975508 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762521956.842647 2975508 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47:24[0m 2s/step - accuracy: 0.0000e+00 - loss: 3.0739
[1m  30/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0619 - loss: 3.2059      
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0678 - loss: 3.1871
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0721 - loss: 3.1770
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0743 - loss: 3.1676
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0752 - loss: 3.1558
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0763 - loss: 3.1440
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0768 - loss: 3.1338
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0777 - loss: 3.1221
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0788 - loss: 3.1113
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0799 - loss: 3.1009
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0807 - loss: 3.0927
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0815 - loss: 3.0830
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0823 - loss: 3.0743
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0830 - loss: 3.0659
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0838 - loss: 3.0581
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0844 - loss: 3.0516
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0850 - loss: 3.0457
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0856 - loss: 3.0393
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0861 - loss: 3.0341
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0868 - loss: 3.0282
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0875 - loss: 3.0224
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0883 - loss: 3.0167
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0890 - loss: 3.0113
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0898 - loss: 3.0061
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0905 - loss: 3.0008
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0913 - loss: 2.9956
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0919 - loss: 2.9912
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0926 - loss: 2.9866
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0933 - loss: 2.9819
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0933 - loss: 2.9818
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0933 - loss: 2.9817 - val_accuracy: 0.1784 - val_loss: 2.5516
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.7389
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1455 - loss: 2.6862  
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1425 - loss: 2.6818
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1406 - loss: 2.6827
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1413 - loss: 2.6822
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1419 - loss: 2.6829
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1425 - loss: 2.6831
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1424 - loss: 2.6829
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1422 - loss: 2.6824
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1423 - loss: 2.6817
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1425 - loss: 2.6805
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1428 - loss: 2.6790
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1432 - loss: 2.6773
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1437 - loss: 2.6758
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1442 - loss: 2.6738
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1446 - loss: 2.6720
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1449 - loss: 2.6703
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1452 - loss: 2.6688
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1455 - loss: 2.6670
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1459 - loss: 2.6651
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1462 - loss: 2.6634
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1465 - loss: 2.6619
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1467 - loss: 2.6602
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1470 - loss: 2.6585
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1473 - loss: 2.6568
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1475 - loss: 2.6552
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1478 - loss: 2.6537
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1480 - loss: 2.6520
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1483 - loss: 2.6504
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1485 - loss: 2.6489
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1486 - loss: 2.6486 - val_accuracy: 0.1959 - val_loss: 2.4470
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.5499
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1573 - loss: 2.5465  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1564 - loss: 2.5356
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1591 - loss: 2.5324
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1616 - loss: 2.5297
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1638 - loss: 2.5260
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1653 - loss: 2.5224
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1670 - loss: 2.5191
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1684 - loss: 2.5169
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1697 - loss: 2.5146
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1707 - loss: 2.5126
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1715 - loss: 2.5111
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1721 - loss: 2.5097
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1726 - loss: 2.5084
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1730 - loss: 2.5074
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1734 - loss: 2.5064
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1739 - loss: 2.5053
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1744 - loss: 2.5041
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1748 - loss: 2.5031
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1752 - loss: 2.5021
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1756 - loss: 2.5011
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1760 - loss: 2.5001
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1763 - loss: 2.4992
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1766 - loss: 2.4983
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1769 - loss: 2.4976
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1771 - loss: 2.4970
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1773 - loss: 2.4963
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1775 - loss: 2.4957
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1777 - loss: 2.4951
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1778 - loss: 2.4946 - val_accuracy: 0.2098 - val_loss: 2.3597
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.2500 - loss: 2.3032
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2061 - loss: 2.4377  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1904 - loss: 2.4608
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1900 - loss: 2.4623
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1910 - loss: 2.4586
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1917 - loss: 2.4544
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1921 - loss: 2.4501
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1918 - loss: 2.4473
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1915 - loss: 2.4449
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1912 - loss: 2.4430
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1910 - loss: 2.4408
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1908 - loss: 2.4390
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1906 - loss: 2.4378
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1904 - loss: 2.4367
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1902 - loss: 2.4356
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1902 - loss: 2.4347
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1904 - loss: 2.4335
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1905 - loss: 2.4322
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1908 - loss: 2.4310
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1910 - loss: 2.4299
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1913 - loss: 2.4288
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1916 - loss: 2.4277
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1919 - loss: 2.4266
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1922 - loss: 2.4257
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1924 - loss: 2.4247
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1927 - loss: 2.4240
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1929 - loss: 2.4232
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1932 - loss: 2.4224
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1934 - loss: 2.4216
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1937 - loss: 2.4208 - val_accuracy: 0.2146 - val_loss: 2.3000
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.4336
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2103 - loss: 2.3873  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2113 - loss: 2.3697
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2088 - loss: 2.3625
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2065 - loss: 2.3599
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2048 - loss: 2.3588
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2040 - loss: 2.3565
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2037 - loss: 2.3543
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2036 - loss: 2.3522
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2037 - loss: 2.3508
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2039 - loss: 2.3495
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2041 - loss: 2.3487
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2041 - loss: 2.3481
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2041 - loss: 2.3477
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2041 - loss: 2.3474
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2042 - loss: 2.3473
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2043 - loss: 2.3471
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2043 - loss: 2.3470
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2045 - loss: 2.3466
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2046 - loss: 2.3463
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2047 - loss: 2.3459
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2049 - loss: 2.3456
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2050 - loss: 2.3454
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2051 - loss: 2.3452
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2053 - loss: 2.3449
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2054 - loss: 2.3446
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2056 - loss: 2.3443
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2057 - loss: 2.3439
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2059 - loss: 2.3435
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2060 - loss: 2.3433 - val_accuracy: 0.2383 - val_loss: 2.2269
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.1665
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2305 - loss: 2.2606  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2218 - loss: 2.2826
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2176 - loss: 2.2946
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2144 - loss: 2.3011
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2126 - loss: 2.3044
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2115 - loss: 2.3056
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2109 - loss: 2.3062
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2108 - loss: 2.3062
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2112 - loss: 2.3057
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2116 - loss: 2.3055
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2119 - loss: 2.3051
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2122 - loss: 2.3046
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2125 - loss: 2.3038
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2128 - loss: 2.3031
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2130 - loss: 2.3026
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2131 - loss: 2.3023
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2133 - loss: 2.3020
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2135 - loss: 2.3015
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2137 - loss: 2.3011
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2138 - loss: 2.3006
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2141 - loss: 2.3000
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2143 - loss: 2.2994
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2145 - loss: 2.2988
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2147 - loss: 2.2982
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2149 - loss: 2.2977
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2152 - loss: 2.2972
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2154 - loss: 2.2967
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2155 - loss: 2.2961
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2157 - loss: 2.2956
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2157 - loss: 2.2955 - val_accuracy: 0.2426 - val_loss: 2.1899
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.3668
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2142 - loss: 2.2506  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2033 - loss: 2.2610
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2019 - loss: 2.2619
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2014 - loss: 2.2625
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2022 - loss: 2.2635
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2031 - loss: 2.2642
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2038 - loss: 2.2647
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2049 - loss: 2.2639
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2062 - loss: 2.2634
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2072 - loss: 2.2628
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2084 - loss: 2.2621
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2095 - loss: 2.2614
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2104 - loss: 2.2608
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2114 - loss: 2.2602
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2123 - loss: 2.2597
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2131 - loss: 2.2595
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2138 - loss: 2.2591
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2145 - loss: 2.2588
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2150 - loss: 2.2585
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2156 - loss: 2.2582
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2161 - loss: 2.2579
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2165 - loss: 2.2576
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2168 - loss: 2.2574
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2172 - loss: 2.2571
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2175 - loss: 2.2569
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2178 - loss: 2.2566
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2181 - loss: 2.2562
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2184 - loss: 2.2559
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2187 - loss: 2.2556
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2188 - loss: 2.2555 - val_accuracy: 0.2468 - val_loss: 2.1441
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.0625 - loss: 2.3671
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2027 - loss: 2.2576  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2144 - loss: 2.2572
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2184 - loss: 2.2549
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2207 - loss: 2.2496
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2228 - loss: 2.2447
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2243 - loss: 2.2416
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2262 - loss: 2.2384
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2278 - loss: 2.2355
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2293 - loss: 2.2324
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2304 - loss: 2.2300
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2313 - loss: 2.2280
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2319 - loss: 2.2265
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2324 - loss: 2.2252
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2326 - loss: 2.2243
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2328 - loss: 2.2233
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2330 - loss: 2.2225
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2332 - loss: 2.2216
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2334 - loss: 2.2209
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2337 - loss: 2.2202
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2339 - loss: 2.2196
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2341 - loss: 2.2191
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2342 - loss: 2.2185
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2343 - loss: 2.2180
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2344 - loss: 2.2176
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2345 - loss: 2.2172
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2345 - loss: 2.2168
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2345 - loss: 2.2165
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2346 - loss: 2.2162
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.2347 - loss: 2.2159
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2347 - loss: 2.2159 - val_accuracy: 0.2572 - val_loss: 2.1151
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.0625 - loss: 2.3171
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2183 - loss: 2.2305  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2325 - loss: 2.2175
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2351 - loss: 2.2131
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2370 - loss: 2.2079
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2373 - loss: 2.2057
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2375 - loss: 2.2042
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2375 - loss: 2.2026
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2373 - loss: 2.2013
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2370 - loss: 2.2007
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2364 - loss: 2.2004
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2358 - loss: 2.2006
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2352 - loss: 2.2008
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2349 - loss: 2.2007
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2348 - loss: 2.2002
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2349 - loss: 2.1999
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2349 - loss: 2.1993
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2350 - loss: 2.1987
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2351 - loss: 2.1980
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2353 - loss: 2.1973
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2354 - loss: 2.1965
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2356 - loss: 2.1957
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2358 - loss: 2.1950
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2360 - loss: 2.1944
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2361 - loss: 2.1939
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2362 - loss: 2.1933
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2364 - loss: 2.1928
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2365 - loss: 2.1923
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2366 - loss: 2.1917
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2367 - loss: 2.1913 - val_accuracy: 0.2437 - val_loss: 2.1136
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.4156
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2294 - loss: 2.1415  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2427 - loss: 2.1380
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1363
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2468 - loss: 2.1371
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2465 - loss: 2.1402
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2465 - loss: 2.1416
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2468 - loss: 2.1421
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2471 - loss: 2.1423
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2471 - loss: 2.1427
[1m 383/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2472 - loss: 2.1428
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2471 - loss: 2.1429
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2471 - loss: 2.1429
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2470 - loss: 2.1432
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2471 - loss: 2.1434
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2472 - loss: 2.1435
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2473 - loss: 2.1438
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2472 - loss: 2.1442
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2472 - loss: 2.1445
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2472 - loss: 2.1446
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2471 - loss: 2.1449
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2471 - loss: 2.1452
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2470 - loss: 2.1456
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2469 - loss: 2.1458
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2469 - loss: 2.1461
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2469 - loss: 2.1464
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2468 - loss: 2.1467
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2467 - loss: 2.1470
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2467 - loss: 2.1473
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2466 - loss: 2.1475
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2466 - loss: 2.1476 - val_accuracy: 0.2694 - val_loss: 2.0691
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0605
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2650 - loss: 2.1277  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2627 - loss: 2.1438
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2590 - loss: 2.1557
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2573 - loss: 2.1605
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2560 - loss: 2.1628
[1m 251/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2558 - loss: 2.1620
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2553 - loss: 2.1607
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2550 - loss: 2.1593
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2547 - loss: 2.1578
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2547 - loss: 2.1568
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.1556
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.1540
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2547 - loss: 2.1525
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2546 - loss: 2.1513
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1501
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2542 - loss: 2.1490
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2541 - loss: 2.1479
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2540 - loss: 2.1469
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2538 - loss: 2.1461
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2537 - loss: 2.1454
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2534 - loss: 2.1449
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2532 - loss: 2.1444
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2530 - loss: 2.1439
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.1435
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2526 - loss: 2.1431
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2524 - loss: 2.1428
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2522 - loss: 2.1426
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2520 - loss: 2.1424
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2519 - loss: 2.1422 - val_accuracy: 0.2685 - val_loss: 2.0493
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.4375 - loss: 1.6954
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3015 - loss: 2.0212  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2908 - loss: 2.0449
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2816 - loss: 2.0636
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2753 - loss: 2.0730
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2712 - loss: 2.0790
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0829
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0860
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2629 - loss: 2.0894
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2615 - loss: 2.0919
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0938
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2594 - loss: 2.0955
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2586 - loss: 2.0973
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.0989
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2572 - loss: 2.1003
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2566 - loss: 2.1016
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.1027
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2554 - loss: 2.1037
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.1046
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1054
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2539 - loss: 2.1061
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2535 - loss: 2.1067
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2532 - loss: 2.1072
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2530 - loss: 2.1076
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.1078
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2526 - loss: 2.1080
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2525 - loss: 2.1082
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2523 - loss: 2.1085
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2522 - loss: 2.1087
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2521 - loss: 2.1089 - val_accuracy: 0.2479 - val_loss: 2.0449
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.1015
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2312 - loss: 2.0687  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2382 - loss: 2.0845
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2436 - loss: 2.0881
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2460 - loss: 2.0898
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2476 - loss: 2.0906
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2487 - loss: 2.0908
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2489 - loss: 2.0926
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2491 - loss: 2.0942
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2496 - loss: 2.0950
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2500 - loss: 2.0957
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2504 - loss: 2.0959
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2507 - loss: 2.0960
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2510 - loss: 2.0960
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.0962
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2515 - loss: 2.0964
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2517 - loss: 2.0968
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2519 - loss: 2.0972
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2520 - loss: 2.0974
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2521 - loss: 2.0976
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2522 - loss: 2.0977
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2522 - loss: 2.0979
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2523 - loss: 2.0980
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2523 - loss: 2.0981
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2523 - loss: 2.0982
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2523 - loss: 2.0983
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2522 - loss: 2.0984
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2523 - loss: 2.0985
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2523 - loss: 2.0986
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2523 - loss: 2.0987
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2523 - loss: 2.0987 - val_accuracy: 0.2685 - val_loss: 2.0111
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.2643
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2348 - loss: 2.1259  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2523 - loss: 2.0990
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0954
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0956
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2555 - loss: 2.0961
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2552 - loss: 2.0950
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0939
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2547 - loss: 2.0933
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2549 - loss: 2.0923
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2550 - loss: 2.0916
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2551 - loss: 2.0909
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2554 - loss: 2.0901
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2558 - loss: 2.0893
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0887
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2564 - loss: 2.0881
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2566 - loss: 2.0876
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0873
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.0870
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2570 - loss: 2.0867
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0864
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0861
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2574 - loss: 2.0858
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2576 - loss: 2.0855
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.0851
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.0848
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2580 - loss: 2.0845
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0842
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2582 - loss: 2.0839
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2583 - loss: 2.0837
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2583 - loss: 2.0837 - val_accuracy: 0.2579 - val_loss: 1.9961
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5625 - loss: 1.4495
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2971 - loss: 1.9972  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0425
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0516
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0512
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2622 - loss: 2.0523
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0542
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2601 - loss: 2.0552
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0556
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2600 - loss: 2.0557
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2601 - loss: 2.0559
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0561
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0567
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0572
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0578
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0581
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0584
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0589
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0593
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2605 - loss: 2.0596
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2607 - loss: 2.0599
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2608 - loss: 2.0601
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2608 - loss: 2.0603
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2608 - loss: 2.0605
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0608
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0610
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0613
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2608 - loss: 2.0615
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2608 - loss: 2.0616
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2608 - loss: 2.0617 - val_accuracy: 0.2618 - val_loss: 2.0155
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.3354
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2224 - loss: 2.0996  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2344 - loss: 2.0857
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2397 - loss: 2.0816
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2441 - loss: 2.0774
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2476 - loss: 2.0745
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2501 - loss: 2.0738
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2519 - loss: 2.0728
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2529 - loss: 2.0715
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2534 - loss: 2.0707
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2538 - loss: 2.0697
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.0687
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2547 - loss: 2.0675
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2550 - loss: 2.0666
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2554 - loss: 2.0658
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2558 - loss: 2.0652
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2562 - loss: 2.0647
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2566 - loss: 2.0643
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.0640
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0638
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2575 - loss: 2.0637
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.0637
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0635
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2583 - loss: 2.0634
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2584 - loss: 2.0633
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2586 - loss: 2.0631
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2588 - loss: 2.0629
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2589 - loss: 2.0627
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2591 - loss: 2.0624
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2592 - loss: 2.0623 - val_accuracy: 0.2685 - val_loss: 1.9936
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.9961
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2456 - loss: 2.0147  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2505 - loss: 2.0155
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0178
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2593 - loss: 2.0193
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2616 - loss: 2.0206
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2632 - loss: 2.0222
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2640 - loss: 2.0236
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2646 - loss: 2.0244
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0251
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0262
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0275
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0288
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0302
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0313
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0324
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0333
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0340
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0347
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2678 - loss: 2.0353
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0358
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2680 - loss: 2.0362
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0367
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0371
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0374
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2683 - loss: 2.0377
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2684 - loss: 2.0379
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2685 - loss: 2.0381
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0383
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2686 - loss: 2.0384 - val_accuracy: 0.2807 - val_loss: 1.9756
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.5000 - loss: 1.8238
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0472  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0356
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2689 - loss: 2.0387
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0373
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2678 - loss: 2.0349
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0342
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0344
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0349
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0357
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2638 - loss: 2.0363
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0366
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0367
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0370
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0373
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0374
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2638 - loss: 2.0375
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0376
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2640 - loss: 2.0376
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2641 - loss: 2.0376
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0376
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0376
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0376
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2647 - loss: 2.0375
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2648 - loss: 2.0375
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0373
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0372
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0371
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0370
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2654 - loss: 2.0369 - val_accuracy: 0.2668 - val_loss: 1.9720
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 19ms/step - accuracy: 0.2500 - loss: 2.2180
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2787 - loss: 1.9633  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2759 - loss: 1.9837
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2750 - loss: 1.9904
[1m 170/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2732 - loss: 1.9972
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0029
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0061
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0084
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0101
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2695 - loss: 2.0112
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2691 - loss: 2.0126
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0143
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2684 - loss: 2.0154
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2683 - loss: 2.0165
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2684 - loss: 2.0171
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0173
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2689 - loss: 2.0175
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2692 - loss: 2.0176
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0177
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2697 - loss: 2.0179
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0179
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0178
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0177
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2706 - loss: 2.0177
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0178
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0178
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0177
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2712 - loss: 2.0178
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0178
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2713 - loss: 2.0178 - val_accuracy: 0.2736 - val_loss: 1.9492
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 1.8065
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2804 - loss: 1.9758  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2806 - loss: 1.9702
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2801 - loss: 1.9736
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2798 - loss: 1.9757
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2791 - loss: 1.9784
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2782 - loss: 1.9805
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2770 - loss: 1.9831
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2761 - loss: 1.9852
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2756 - loss: 1.9875
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2751 - loss: 1.9897
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2749 - loss: 1.9914
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 1.9928
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 1.9940
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2750 - loss: 1.9950
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2751 - loss: 1.9958
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 1.9965
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2754 - loss: 1.9970
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2755 - loss: 1.9975
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2756 - loss: 1.9981
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2756 - loss: 1.9987
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2756 - loss: 1.9993
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2757 - loss: 1.9998
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2757 - loss: 2.0002
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2757 - loss: 2.0006
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2758 - loss: 2.0010
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2758 - loss: 2.0013
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 2.0016
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 2.0018
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2760 - loss: 2.0020
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2760 - loss: 2.0020 - val_accuracy: 0.2683 - val_loss: 1.9849
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.1553
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2582 - loss: 2.0141  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0151
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0167
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2728 - loss: 2.0141
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2737 - loss: 2.0155
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0153
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2742 - loss: 2.0141
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0128
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0119
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0111
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0107
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2741 - loss: 2.0105
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2739 - loss: 2.0105
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 2.0105
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2734 - loss: 2.0106
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0106
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2730 - loss: 2.0104
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2729 - loss: 2.0102
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2728 - loss: 2.0101
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2727 - loss: 2.0100
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2725 - loss: 2.0099
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2724 - loss: 2.0099
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2723 - loss: 2.0099
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0098
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0097
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0096
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0094
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0091
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2723 - loss: 2.0088
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2723 - loss: 2.0086 - val_accuracy: 0.2766 - val_loss: 1.9443
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1875 - loss: 2.3856
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0723  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2826 - loss: 2.0310
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2891 - loss: 2.0162
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2904 - loss: 2.0082
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2915 - loss: 2.0031
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2914 - loss: 2.0012
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2910 - loss: 1.9999
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2901 - loss: 1.9992
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2895 - loss: 1.9985
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2891 - loss: 1.9978
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2887 - loss: 1.9971
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2882 - loss: 1.9969
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2877 - loss: 1.9967
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2873 - loss: 1.9966
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2870 - loss: 1.9967
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2867 - loss: 1.9967
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2865 - loss: 1.9967
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2863 - loss: 1.9966
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2862 - loss: 1.9965
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2862 - loss: 1.9964
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2861 - loss: 1.9962
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2861 - loss: 1.9961
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2860 - loss: 1.9959
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2859 - loss: 1.9958
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2858 - loss: 1.9957
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2858 - loss: 1.9954
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2858 - loss: 1.9952
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2857 - loss: 1.9951
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2857 - loss: 1.9949 - val_accuracy: 0.2770 - val_loss: 1.9584
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.1850
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0087  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2870 - loss: 1.9870
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2897 - loss: 1.9803
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2897 - loss: 1.9811
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2883 - loss: 1.9839
[1m 249/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2869 - loss: 1.9861
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2858 - loss: 1.9882
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2847 - loss: 1.9908
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2838 - loss: 1.9930
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2831 - loss: 1.9945
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2825 - loss: 1.9957
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2820 - loss: 1.9967
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2816 - loss: 1.9974
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2814 - loss: 1.9977
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2813 - loss: 1.9979
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9980
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 1.9980
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 1.9980
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 1.9980
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2809 - loss: 1.9979
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2808 - loss: 1.9980
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2807 - loss: 1.9981
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 1.9981
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 1.9980
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 1.9979
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 1.9979
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 1.9978
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 1.9976
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2804 - loss: 1.9976 - val_accuracy: 0.2792 - val_loss: 1.9256
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 1.8495
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2924 - loss: 1.9505  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2930 - loss: 1.9494
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2896 - loss: 1.9571
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2885 - loss: 1.9594
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2864 - loss: 1.9617
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2851 - loss: 1.9645
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2845 - loss: 1.9661
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2843 - loss: 1.9666
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2840 - loss: 1.9670
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2837 - loss: 1.9677
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2834 - loss: 1.9685
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2830 - loss: 1.9695
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2826 - loss: 1.9704
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2823 - loss: 1.9712
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2820 - loss: 1.9719
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2818 - loss: 1.9722
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2818 - loss: 1.9724
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2816 - loss: 1.9726
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2815 - loss: 1.9729
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2814 - loss: 1.9731
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9733
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 1.9735
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2809 - loss: 1.9738
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2808 - loss: 1.9741
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2807 - loss: 1.9743
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2807 - loss: 1.9745
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 1.9747
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 1.9750
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 1.9752
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2805 - loss: 1.9752 - val_accuracy: 0.2742 - val_loss: 1.9334
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 1.9552
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2690 - loss: 2.0174  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0094
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2692 - loss: 2.0061
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0005
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2740 - loss: 1.9962
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2750 - loss: 1.9943
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2756 - loss: 1.9929
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2764 - loss: 1.9919
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2769 - loss: 1.9909
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2773 - loss: 1.9901
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2778 - loss: 1.9890
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2781 - loss: 1.9881
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2782 - loss: 1.9877
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2783 - loss: 1.9875
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2784 - loss: 1.9874
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2785 - loss: 1.9872
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2786 - loss: 1.9872
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2788 - loss: 1.9871
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9870
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2790 - loss: 1.9868
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2790 - loss: 1.9867
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2791 - loss: 1.9866
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2792 - loss: 1.9864
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2793 - loss: 1.9862
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2794 - loss: 1.9860
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 1.9859
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9857
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2797 - loss: 1.9856
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2797 - loss: 1.9854
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2798 - loss: 1.9854 - val_accuracy: 0.2831 - val_loss: 1.9217

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 648ms/step
[1m60/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 854us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7:58[0m 821ms/step
[1m 66/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 774us/step  
[1m134/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 755us/step
[1m206/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 737us/step
[1m280/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 721us/step
[1m352/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 717us/step
[1m421/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 719us/step
[1m496/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 712us/step
[1m572/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 705us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m64/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 798us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 57/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 909us/step
[1m132/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 774us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 28.51 [%]
Global F1 score (validation) = 26.03 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.17521653 0.1801118  0.1382324  ... 0.00189237 0.1642411  0.01859593]
 [0.1851251  0.17326386 0.14102954 ... 0.00267539 0.16034824 0.01838197]
 [0.18410526 0.1911575  0.15179907 ... 0.00108514 0.15877058 0.0212322 ]
 ...
 [0.21743833 0.16948329 0.15355974 ... 0.00073717 0.16729967 0.02534   ]
 [0.21071118 0.16443329 0.14720283 ... 0.00111694 0.17721692 0.02184404]
 [0.16470045 0.18643816 0.1364543  ... 0.00400404 0.10609489 0.01181418]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 32.57 [%]
Global accuracy score (test) = 26.05 [%]
Global F1 score (train) = 30.09 [%]
Global F1 score (test) = 24.21 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.20      0.26      0.22       184
 CAMINAR CON MÓVIL O LIBRO       0.16      0.48      0.25       184
       CAMINAR USUAL SPEED       0.04      0.01      0.01       184
            CAMINAR ZIGZAG       0.11      0.10      0.11       184
          DE PIE BARRIENDO       0.28      0.40      0.33       184
   DE PIE DOBLANDO TOALLAS       0.25      0.26      0.26       184
    DE PIE MOVIENDO LIBROS       0.13      0.08      0.10       184
          DE PIE USANDO PC       0.27      0.68      0.39       184
        FASE REPOSO CON K5       0.63      0.62      0.63       184
INCREMENTAL CICLOERGOMETRO       0.41      0.22      0.29       184
           SENTADO LEYENDO       0.18      0.12      0.15       184
         SENTADO USANDO PC       0.16      0.04      0.07       184
      SENTADO VIENDO LA TV       0.30      0.25      0.27       184
   SUBIR Y BAJAR ESCALERAS       0.20      0.06      0.09       184
                    TROTAR       0.98      0.32      0.48       161

                  accuracy                           0.26      2737
                 macro avg       0.29      0.26      0.24      2737
              weighted avg       0.28      0.26      0.24      2737


Accuracy capturado en la ejecución 18: 26.05 [%]
F1-score capturado en la ejecución 18: 24.21 [%]

=== EJECUCIÓN 19 ===

--- TRAIN (ejecución 19) ---

--- TEST (ejecución 19) ---
2025-11-07 14:26:58.482419: 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 14:26:58.493774: 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 00:00:1762522018.506771 2979136 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762522018.510831 2979136 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762522018.520745 2979136 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522018.520765 2979136 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522018.520766 2979136 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522018.520768 2979136 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:26:58.523999: 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 00:00:1762522020.791959 2979136 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762522022.301061 2979270 service.cc:152] XLA service 0x7397d0002210 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762522022.301092 2979270 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:27:02.334031: 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 00:00:1762522022.479214 2979270 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762522023.880627 2979270 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47:19[0m 2s/step - accuracy: 0.0625 - loss: 3.1301
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0654 - loss: 3.1852  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0676 - loss: 3.2099
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0693 - loss: 3.2087
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0703 - loss: 3.2014
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0712 - loss: 3.1935
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0719 - loss: 3.1855
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0724 - loss: 3.1773
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0727 - loss: 3.1694
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0730 - loss: 3.1605
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0732 - loss: 3.1514
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0733 - loss: 3.1425
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0735 - loss: 3.1337
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0737 - loss: 3.1253
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0739 - loss: 3.1173
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0742 - loss: 3.1098
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0744 - loss: 3.1029
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0746 - loss: 3.0959
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0749 - loss: 3.0896
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0751 - loss: 3.0834
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0754 - loss: 3.0774
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0757 - loss: 3.0713
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0760 - loss: 3.0660
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0763 - loss: 3.0609
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0767 - loss: 3.0551
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0771 - loss: 3.0496
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0774 - loss: 3.0445
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0778 - loss: 3.0395
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0782 - loss: 3.0349
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0784 - loss: 3.0317
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0784 - loss: 3.0316 - val_accuracy: 0.1245 - val_loss: 2.6323
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.0625 - loss: 2.9356
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1362 - loss: 2.6815  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1354 - loss: 2.6833
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1331 - loss: 2.6854
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1311 - loss: 2.6864
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1294 - loss: 2.6870
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1284 - loss: 2.6857
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1278 - loss: 2.6843
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1275 - loss: 2.6829
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1271 - loss: 2.6817
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1269 - loss: 2.6807
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1267 - loss: 2.6799
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1266 - loss: 2.6790
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1265 - loss: 2.6779
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1265 - loss: 2.6767
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1266 - loss: 2.6755
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1267 - loss: 2.6744
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1270 - loss: 2.6732
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1272 - loss: 2.6721
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1276 - loss: 2.6708
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1279 - loss: 2.6694
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1282 - loss: 2.6680
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1286 - loss: 2.6666
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1289 - loss: 2.6654
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1292 - loss: 2.6641
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1296 - loss: 2.6627
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1300 - loss: 2.6613
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1304 - loss: 2.6597
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1308 - loss: 2.6582
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1313 - loss: 2.6567
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1314 - loss: 2.6563 - val_accuracy: 0.1798 - val_loss: 2.5201
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.5130
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1527 - loss: 2.5244  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1625 - loss: 2.5166
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1673 - loss: 2.5110
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1698 - loss: 2.5099
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1713 - loss: 2.5098
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1720 - loss: 2.5100
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1720 - loss: 2.5116
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1715 - loss: 2.5134
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1713 - loss: 2.5143
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1710 - loss: 2.5150
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1707 - loss: 2.5157
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1704 - loss: 2.5162
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1702 - loss: 2.5167
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1701 - loss: 2.5169
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1700 - loss: 2.5169
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1700 - loss: 2.5166
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1701 - loss: 2.5163
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1701 - loss: 2.5161
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1702 - loss: 2.5158
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1703 - loss: 2.5155
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1704 - loss: 2.5152
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1705 - loss: 2.5148
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1707 - loss: 2.5145
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1709 - loss: 2.5141
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1710 - loss: 2.5137
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1712 - loss: 2.5132
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1714 - loss: 2.5126
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1716 - loss: 2.5120
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1718 - loss: 2.5115 - val_accuracy: 0.2220 - val_loss: 2.3940
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3750 - loss: 2.2981
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1922 - loss: 2.4694  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2001 - loss: 2.4586
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2052 - loss: 2.4501
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2062 - loss: 2.4467
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2056 - loss: 2.4450
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2049 - loss: 2.4430
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2041 - loss: 2.4422
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2033 - loss: 2.4415
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2028 - loss: 2.4407
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2026 - loss: 2.4395
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2023 - loss: 2.4384
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2021 - loss: 2.4371
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2019 - loss: 2.4357
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2018 - loss: 2.4343
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2015 - loss: 2.4330
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2013 - loss: 2.4318
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2012 - loss: 2.4307
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2011 - loss: 2.4298
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2010 - loss: 2.4287
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2010 - loss: 2.4276
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2010 - loss: 2.4267
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2009 - loss: 2.4259
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2009 - loss: 2.4251
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2009 - loss: 2.4244
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2008 - loss: 2.4238
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2008 - loss: 2.4231
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2007 - loss: 2.4225
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2007 - loss: 2.4219
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2006 - loss: 2.4212
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2006 - loss: 2.4211 - val_accuracy: 0.2340 - val_loss: 2.3244
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.4788
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2058 - loss: 2.3586  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2172 - loss: 2.3439
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2190 - loss: 2.3424
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2176 - loss: 2.3438
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2165 - loss: 2.3453
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2155 - loss: 2.3473
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2150 - loss: 2.3476
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2148 - loss: 2.3476
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2147 - loss: 2.3467
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2147 - loss: 2.3460
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2146 - loss: 2.3451
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2145 - loss: 2.3444
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2144 - loss: 2.3438
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2144 - loss: 2.3432
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2144 - loss: 2.3425
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2144 - loss: 2.3418
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2145 - loss: 2.3409
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2145 - loss: 2.3402
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2146 - loss: 2.3396
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2146 - loss: 2.3391
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2146 - loss: 2.3385
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2147 - loss: 2.3380
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2147 - loss: 2.3375
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2147 - loss: 2.3370
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2147 - loss: 2.3366
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2147 - loss: 2.3363
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2147 - loss: 2.3360
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2146 - loss: 2.3357
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2146 - loss: 2.3356 - val_accuracy: 0.2522 - val_loss: 2.2361
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 2.2234
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2666 - loss: 2.2457  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2449 - loss: 2.2660
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2356 - loss: 2.2778
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2321 - loss: 2.2822
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2304 - loss: 2.2843
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2291 - loss: 2.2858
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2283 - loss: 2.2868
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2278 - loss: 2.2870
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2273 - loss: 2.2874
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2270 - loss: 2.2877
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2267 - loss: 2.2878
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2264 - loss: 2.2880
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2260 - loss: 2.2883
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2256 - loss: 2.2885
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2253 - loss: 2.2886
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2251 - loss: 2.2886
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2249 - loss: 2.2885
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2246 - loss: 2.2886
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2244 - loss: 2.2888
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2241 - loss: 2.2890
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2239 - loss: 2.2891
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2238 - loss: 2.2891
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2237 - loss: 2.2890
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2236 - loss: 2.2888
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2235 - loss: 2.2886
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2235 - loss: 2.2884
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2234 - loss: 2.2882
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2234 - loss: 2.2879
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2234 - loss: 2.2878 - val_accuracy: 0.2533 - val_loss: 2.2034
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.9516
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2360 - loss: 2.2444  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2354 - loss: 2.2429
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2331 - loss: 2.2422
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2315 - loss: 2.2428
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2303 - loss: 2.2440
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2298 - loss: 2.2441
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2296 - loss: 2.2441
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2294 - loss: 2.2441
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2290 - loss: 2.2448
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2286 - loss: 2.2451
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2284 - loss: 2.2451
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2281 - loss: 2.2453
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2281 - loss: 2.2453
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2452
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2283 - loss: 2.2454
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2283 - loss: 2.2456
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2457
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2458
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2281 - loss: 2.2459
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2280 - loss: 2.2460
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2280 - loss: 2.2460
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2280 - loss: 2.2460
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2280 - loss: 2.2459
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2281 - loss: 2.2457
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2454
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2451
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2283 - loss: 2.2449
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2284 - loss: 2.2446
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2284 - loss: 2.2444
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2284 - loss: 2.2444 - val_accuracy: 0.2324 - val_loss: 2.1834
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.2906
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2436 - loss: 2.1480  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2386 - loss: 2.1849
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2342 - loss: 2.2031
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2322 - loss: 2.2115
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2314 - loss: 2.2151
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2312 - loss: 2.2171
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2311 - loss: 2.2192
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2311 - loss: 2.2211
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2309 - loss: 2.2226
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2306 - loss: 2.2237
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2305 - loss: 2.2242
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2304 - loss: 2.2247
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2304 - loss: 2.2250
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2304 - loss: 2.2250
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2304 - loss: 2.2251
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2304 - loss: 2.2250
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2304 - loss: 2.2246
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2305 - loss: 2.2244
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2305 - loss: 2.2241
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2306 - loss: 2.2239
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2306 - loss: 2.2237
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2307 - loss: 2.2235
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2307 - loss: 2.2233
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2308 - loss: 2.2230
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2308 - loss: 2.2227
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2309 - loss: 2.2225
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2310 - loss: 2.2223
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2311 - loss: 2.2221
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2312 - loss: 2.2219
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2312 - loss: 2.2218 - val_accuracy: 0.2559 - val_loss: 2.1392
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.1893
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1970 - loss: 2.2433  
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2023 - loss: 2.2448
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2101 - loss: 2.2419
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2153 - loss: 2.2349
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2191 - loss: 2.2291
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2227 - loss: 2.2238
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2252 - loss: 2.2198
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2268 - loss: 2.2171
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2283 - loss: 2.2140
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2293 - loss: 2.2115
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2302 - loss: 2.2096
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2310 - loss: 2.2084
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2316 - loss: 2.2075
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2322 - loss: 2.2063
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2328 - loss: 2.2051
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2332 - loss: 2.2040
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2336 - loss: 2.2030
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2339 - loss: 2.2021
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2341 - loss: 2.2015
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2343 - loss: 2.2010
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2345 - loss: 2.2005
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2346 - loss: 2.2000
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2348 - loss: 2.1997
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2349 - loss: 2.1993
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2350 - loss: 2.1989
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2351 - loss: 2.1985
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2352 - loss: 2.1981
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2353 - loss: 2.1977
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2354 - loss: 2.1972
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2354 - loss: 2.1970 - val_accuracy: 0.2623 - val_loss: 2.0972
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.3125 - loss: 2.3665
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2023 - loss: 2.2886  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2129 - loss: 2.2557
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2172 - loss: 2.2428
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2201 - loss: 2.2344
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2227 - loss: 2.2269
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2254 - loss: 2.2194
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2278 - loss: 2.2131
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2299 - loss: 2.2080
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2317 - loss: 2.2036
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2330 - loss: 2.2009
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2343 - loss: 2.1980
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2353 - loss: 2.1955
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2363 - loss: 2.1931
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2371 - loss: 2.1911
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2379 - loss: 2.1892
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2384 - loss: 2.1877
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2389 - loss: 2.1862
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2393 - loss: 2.1849
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2397 - loss: 2.1837
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2401 - loss: 2.1825
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2404 - loss: 2.1815
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2407 - loss: 2.1806
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2409 - loss: 2.1796
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2412 - loss: 2.1787
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2414 - loss: 2.1778
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2415 - loss: 2.1771
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2417 - loss: 2.1764
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1757
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2420 - loss: 2.1750 - val_accuracy: 0.2720 - val_loss: 2.0841
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.3435
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2646 - loss: 2.1926  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2660 - loss: 2.1750
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2619 - loss: 2.1701
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2603 - loss: 2.1659
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2579 - loss: 2.1630
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2567 - loss: 2.1607
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2559 - loss: 2.1589
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2550 - loss: 2.1582
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2541 - loss: 2.1576
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2532 - loss: 2.1571
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2524 - loss: 2.1563
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2516 - loss: 2.1556
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2510 - loss: 2.1549
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2504 - loss: 2.1539
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2498 - loss: 2.1531
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2494 - loss: 2.1524
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2490 - loss: 2.1519
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2488 - loss: 2.1514
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2486 - loss: 2.1509
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2484 - loss: 2.1504
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2482 - loss: 2.1498
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2481 - loss: 2.1493
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2480 - loss: 2.1489
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2478 - loss: 2.1485
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2478 - loss: 2.1480
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2477 - loss: 2.1476
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2476 - loss: 2.1472
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2476 - loss: 2.1466
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2475 - loss: 2.1461
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2475 - loss: 2.1459 - val_accuracy: 0.2566 - val_loss: 2.0478
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3750 - loss: 2.0278
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2801 - loss: 2.0901  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0940
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0928
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0977
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2627 - loss: 2.1003
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2621 - loss: 2.1012
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2614 - loss: 2.1023
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2607 - loss: 2.1034
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2603 - loss: 2.1039
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2597 - loss: 2.1042
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2593 - loss: 2.1039
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2589 - loss: 2.1037
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2587 - loss: 2.1034
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2586 - loss: 2.1032
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2586 - loss: 2.1030
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2586 - loss: 2.1027
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2586 - loss: 2.1027
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2584 - loss: 2.1028
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2584 - loss: 2.1029
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2583 - loss: 2.1029
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2582 - loss: 2.1029
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.1029
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.1029
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2580 - loss: 2.1030
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2580 - loss: 2.1031
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.1032
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.1033
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.1034
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.1034
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2578 - loss: 2.1035 - val_accuracy: 0.2821 - val_loss: 2.0245
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.2039
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2699 - loss: 2.1031  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0957
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0903
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0881
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0867
[1m 227/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0849
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0843
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2635 - loss: 2.0851
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0852
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2627 - loss: 2.0853
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2623 - loss: 2.0857
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2621 - loss: 2.0861
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2620 - loss: 2.0864
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2618 - loss: 2.0866
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2616 - loss: 2.0869
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2614 - loss: 2.0871
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0875
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0878
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2607 - loss: 2.0880
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2606 - loss: 2.0883
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0886
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0889
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2601 - loss: 2.0893
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2600 - loss: 2.0895
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2598 - loss: 2.0897
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2597 - loss: 2.0900
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2595 - loss: 2.0903
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2594 - loss: 2.0905
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2593 - loss: 2.0907 - val_accuracy: 0.2659 - val_loss: 2.0351
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5000 - loss: 1.8965
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2929 - loss: 2.0526  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2737 - loss: 2.0619
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0671
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2619 - loss: 2.0705
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2616 - loss: 2.0729
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2615 - loss: 2.0744
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2612 - loss: 2.0747
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0753
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0757
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0760
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2593 - loss: 2.0764
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2589 - loss: 2.0769
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2586 - loss: 2.0774
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2583 - loss: 2.0778
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2580 - loss: 2.0782
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.0787
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2576 - loss: 2.0790
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2574 - loss: 2.0793
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0797
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0800
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2570 - loss: 2.0803
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0806
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0808
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2566 - loss: 2.0809
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.0811
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2564 - loss: 2.0812
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0811
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0811
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2564 - loss: 2.0810
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2564 - loss: 2.0810 - val_accuracy: 0.2938 - val_loss: 1.9975
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.3125 - loss: 1.5790
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2964 - loss: 1.9775  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2827 - loss: 2.0257
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2793 - loss: 2.0394
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2780 - loss: 2.0451
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2768 - loss: 2.0491
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2758 - loss: 2.0521
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2751 - loss: 2.0554
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0584
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2728 - loss: 2.0611
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0629
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0641
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0648
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2695 - loss: 2.0652
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2691 - loss: 2.0655
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0658
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2684 - loss: 2.0663
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0667
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0670
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2673 - loss: 2.0671
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0671
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0672
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0672
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0672
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0672
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0671
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0670
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0669
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0668
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0667
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2655 - loss: 2.0667 - val_accuracy: 0.2833 - val_loss: 1.9934
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.4075
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2910 - loss: 2.1131  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2882 - loss: 2.0856
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2861 - loss: 2.0766
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2836 - loss: 2.0728
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2815 - loss: 2.0700
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2794 - loss: 2.0687
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2775 - loss: 2.0687
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2758 - loss: 2.0685
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0684
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0687
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0687
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0686
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0684
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0682
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0680
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0675
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2692 - loss: 2.0671
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2690 - loss: 2.0667
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2688 - loss: 2.0664
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2685 - loss: 2.0661
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2683 - loss: 2.0658
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0657
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2678 - loss: 2.0655
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0653
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0650
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2673 - loss: 2.0646
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0642
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0638
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0634
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2670 - loss: 2.0633 - val_accuracy: 0.2821 - val_loss: 1.9911
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.4375 - loss: 2.0233
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2486 - loss: 2.0697  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2550 - loss: 2.0565
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2600 - loss: 2.0506
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0477
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0454
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2683 - loss: 2.0446
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0444
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2697 - loss: 2.0446
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2697 - loss: 2.0454
[1m 383/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0459
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2697 - loss: 2.0464
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0466
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0466
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0466
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2701 - loss: 2.0466
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0464
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0462
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0461
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0459
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0457
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0455
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2701 - loss: 2.0453
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2701 - loss: 2.0452
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0452
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0451
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0449
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0449
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0448
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0447
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2698 - loss: 2.0446 - val_accuracy: 0.2768 - val_loss: 1.9907
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.2123
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2439 - loss: 2.0352  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2459 - loss: 2.0462
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2510 - loss: 2.0439
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2541 - loss: 2.0433
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0421
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2592 - loss: 2.0408
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0397
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2623 - loss: 2.0393
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2634 - loss: 2.0387
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0378
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2648 - loss: 2.0372
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0368
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0366
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0363
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0362
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0361
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0361
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0360
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0358
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0356
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0355
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0354
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0353
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0352
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0350
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0348
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0346
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0344
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0342
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2663 - loss: 2.0341 - val_accuracy: 0.2790 - val_loss: 1.9696
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.8387
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2742 - loss: 2.0660  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2754 - loss: 2.0617
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2771 - loss: 2.0510
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2768 - loss: 2.0419
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2756 - loss: 2.0381
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0356
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2738 - loss: 2.0339
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0333
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2725 - loss: 2.0332
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2720 - loss: 2.0330
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0326
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0320
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0313
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0305
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0300
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0295
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0289
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0284
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0278
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2712 - loss: 2.0270
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0262
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0255
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0247
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0240
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0233
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2719 - loss: 2.0227
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2720 - loss: 2.0222
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0218
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0214
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2722 - loss: 2.0213 - val_accuracy: 0.2749 - val_loss: 1.9899
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.8974
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3047 - loss: 1.9925  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2915 - loss: 2.0137
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2879 - loss: 2.0164
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2855 - loss: 2.0180
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2842 - loss: 2.0179
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2834 - loss: 2.0155
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2827 - loss: 2.0142
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2818 - loss: 2.0134
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2813 - loss: 2.0126
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2808 - loss: 2.0119
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 2.0115
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 2.0113
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2798 - loss: 2.0113
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 2.0112
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2793 - loss: 2.0111
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2792 - loss: 2.0111
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2790 - loss: 2.0112
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2788 - loss: 2.0114
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2787 - loss: 2.0115
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2785 - loss: 2.0116
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2784 - loss: 2.0116
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2783 - loss: 2.0115
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2781 - loss: 2.0116
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2780 - loss: 2.0116
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2778 - loss: 2.0116
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 2.0116
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 2.0115
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2774 - loss: 2.0113
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2773 - loss: 2.0112
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2773 - loss: 2.0112 - val_accuracy: 0.2875 - val_loss: 1.9523
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.4375 - loss: 1.8007
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2643 - loss: 1.9676  
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2689 - loss: 1.9742
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2736 - loss: 1.9805
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2754 - loss: 1.9816
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2767 - loss: 1.9797
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2778 - loss: 1.9782
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2792 - loss: 1.9774
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2799 - loss: 1.9778
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2805 - loss: 1.9792
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2807 - loss: 1.9802
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 1.9813
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2814 - loss: 1.9822
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2817 - loss: 1.9832
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2819 - loss: 1.9839
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2821 - loss: 1.9846
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2822 - loss: 1.9852
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2824 - loss: 1.9858
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2825 - loss: 1.9863
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2826 - loss: 1.9868
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2826 - loss: 1.9870
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2827 - loss: 1.9872
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2828 - loss: 1.9875
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2828 - loss: 1.9877
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2829 - loss: 1.9879
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2830 - loss: 1.9881
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2830 - loss: 1.9883
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2831 - loss: 1.9884
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2831 - loss: 1.9885
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2832 - loss: 1.9886
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2832 - loss: 1.9887 - val_accuracy: 0.2797 - val_loss: 1.9570
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.0256
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2379 - loss: 2.0954  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2440 - loss: 2.0719
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2505 - loss: 2.0558
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0421
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2618 - loss: 2.0325
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0242
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0196
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0162
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2719 - loss: 2.0133
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2730 - loss: 2.0109
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2739 - loss: 2.0088
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0068
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2756 - loss: 2.0051
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0038
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2766 - loss: 2.0025
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2769 - loss: 2.0015
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2771 - loss: 2.0005
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2773 - loss: 1.9996
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 1.9987
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2777 - loss: 1.9981
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2778 - loss: 1.9976
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2779 - loss: 1.9972
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2780 - loss: 1.9968
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2781 - loss: 1.9964
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2783 - loss: 1.9959
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2784 - loss: 1.9955
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2785 - loss: 1.9951
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2786 - loss: 1.9946
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2788 - loss: 1.9942
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2789 - loss: 1.9940 - val_accuracy: 0.2936 - val_loss: 1.9308
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3750 - loss: 1.9316
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3053 - loss: 2.0283  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3003 - loss: 2.0159
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2985 - loss: 2.0068
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2979 - loss: 2.0021
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2963 - loss: 2.0000
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2948 - loss: 1.9986
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2944 - loss: 1.9971
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2939 - loss: 1.9964
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2934 - loss: 1.9963
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2928 - loss: 1.9962
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2927 - loss: 1.9953
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2924 - loss: 1.9944
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2919 - loss: 1.9941
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2915 - loss: 1.9936
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2912 - loss: 1.9932
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2908 - loss: 1.9927
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2904 - loss: 1.9924
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2901 - loss: 1.9921
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2897 - loss: 1.9918
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2893 - loss: 1.9915
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2889 - loss: 1.9913
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2885 - loss: 1.9913
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2882 - loss: 1.9913
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2879 - loss: 1.9912
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2877 - loss: 1.9911
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2874 - loss: 1.9909
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2872 - loss: 1.9906
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2870 - loss: 1.9904
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2869 - loss: 1.9901
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2868 - loss: 1.9900 - val_accuracy: 0.2921 - val_loss: 1.9319
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 20ms/step - accuracy: 0.3750 - loss: 1.5488
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2856 - loss: 1.9433  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2876 - loss: 1.9436
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2860 - loss: 1.9527
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2859 - loss: 1.9576
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2861 - loss: 1.9592
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2859 - loss: 1.9608
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2854 - loss: 1.9621
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2849 - loss: 1.9621
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2846 - loss: 1.9624
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2844 - loss: 1.9626
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2842 - loss: 1.9631
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2840 - loss: 1.9637
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2841 - loss: 1.9642
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2842 - loss: 1.9643
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2844 - loss: 1.9643
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2846 - loss: 1.9643
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2847 - loss: 1.9644
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2849 - loss: 1.9644
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2851 - loss: 1.9643
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2852 - loss: 1.9642
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2853 - loss: 1.9640
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2855 - loss: 1.9637
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2856 - loss: 1.9635
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2857 - loss: 1.9633
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2858 - loss: 1.9632
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2859 - loss: 1.9632
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2859 - loss: 1.9632
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2860 - loss: 1.9631
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2861 - loss: 1.9631
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2861 - loss: 1.9631 - val_accuracy: 0.2829 - val_loss: 1.9348
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0523
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2962 - loss: 1.9463  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2979 - loss: 1.9591
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3002 - loss: 1.9608
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2992 - loss: 1.9632
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2971 - loss: 1.9657
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2957 - loss: 1.9662
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2951 - loss: 1.9665
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2944 - loss: 1.9667
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2941 - loss: 1.9664
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2939 - loss: 1.9663
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2939 - loss: 1.9658
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2938 - loss: 1.9650
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2939 - loss: 1.9641
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2940 - loss: 1.9633
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2940 - loss: 1.9625
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2939 - loss: 1.9618
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2938 - loss: 1.9612
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2937 - loss: 1.9610
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2934 - loss: 1.9609
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2932 - loss: 1.9609
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2930 - loss: 1.9610
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2928 - loss: 1.9610
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2927 - loss: 1.9611
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2925 - loss: 1.9611
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2923 - loss: 1.9612
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2922 - loss: 1.9612
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2921 - loss: 1.9612
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2919 - loss: 1.9612
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2917 - loss: 1.9612
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2916 - loss: 1.9612 - val_accuracy: 0.2873 - val_loss: 1.9334

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 649ms/step
[1m59/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 874us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7:50[0m 807ms/step
[1m 66/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 773us/step  
[1m140/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 723us/step
[1m205/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 738us/step
[1m275/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 732us/step
[1m339/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 744us/step
[1m406/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 745us/step
[1m475/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 742us/step
[1m545/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 739us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m65/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 788us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 55/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 928us/step
[1m130/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 777us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 28.31 [%]
Global F1 score (validation) = 26.13 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[1.26230329e-01 1.40359342e-01 1.48800343e-01 ... 2.52651004e-03
  7.75698796e-02 7.48228328e-03]
 [1.08244210e-01 1.36473522e-01 1.17182441e-01 ... 4.21911990e-03
  7.96594545e-02 6.67685270e-03]
 [1.49640590e-01 1.62401885e-01 1.75639987e-01 ... 1.13146193e-03
  1.06873423e-01 2.19882466e-02]
 ...
 [2.18201414e-01 1.71505392e-01 1.40349194e-01 ... 2.04346812e-04
  1.20549634e-01 8.78752545e-02]
 [2.04981923e-01 1.50033355e-01 1.75008923e-01 ... 9.12898045e-04
  1.22170538e-01 3.40950899e-02]
 [1.45250306e-01 1.80413246e-01 1.69400394e-01 ... 3.30100441e-03
  9.39501077e-02 1.22142481e-02]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 32.29 [%]
Global accuracy score (test) = 27.99 [%]
Global F1 score (train) = 30.0 [%]
Global F1 score (test) = 25.53 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.19      0.10      0.13       184
 CAMINAR CON MÓVIL O LIBRO       0.21      0.49      0.29       184
       CAMINAR USUAL SPEED       0.17      0.21      0.19       184
            CAMINAR ZIGZAG       0.10      0.12      0.11       184
          DE PIE BARRIENDO       0.21      0.31      0.25       184
   DE PIE DOBLANDO TOALLAS       0.22      0.28      0.25       184
    DE PIE MOVIENDO LIBROS       0.35      0.15      0.21       184
          DE PIE USANDO PC       0.27      0.73      0.40       184
        FASE REPOSO CON K5       0.62      0.75      0.68       184
INCREMENTAL CICLOERGOMETRO       0.80      0.07      0.12       184
           SENTADO LEYENDO       0.37      0.37      0.37       184
         SENTADO USANDO PC       0.05      0.02      0.02       184
      SENTADO VIENDO LA TV       0.33      0.26      0.29       184
   SUBIR Y BAJAR ESCALERAS       0.00      0.00      0.00       184
                    TROTAR       0.91      0.37      0.53       161

                  accuracy                           0.28      2737
                 macro avg       0.32      0.28      0.26      2737
              weighted avg       0.31      0.28      0.25      2737


Accuracy capturado en la ejecución 19: 27.99 [%]
F1-score capturado en la ejecución 19: 25.53 [%]

=== EJECUCIÓN 20 ===

--- TRAIN (ejecución 20) ---

--- TEST (ejecución 20) ---
2025-11-07 14:28:05.903303: 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 14:28:05.914437: 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 00:00:1762522085.927774 2982866 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762522085.932001 2982866 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762522085.942029 2982866 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522085.942048 2982866 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522085.942049 2982866 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522085.942051 2982866 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:28:05.945238: 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 00:00:1762522088.216155 2982866 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762522089.689178 2982998 service.cc:152] XLA service 0x7fea4000ca30 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762522089.689210 2982998 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:28:09.727810: 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 00:00:1762522089.872122 2982998 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762522091.270502 2982998 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46:56[0m 2s/step - accuracy: 0.0625 - loss: 3.1723
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0684 - loss: 3.2492  
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0681 - loss: 3.2272
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0690 - loss: 3.2086
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0701 - loss: 3.1967
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0721 - loss: 3.1821
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0734 - loss: 3.1706
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0745 - loss: 3.1596
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0755 - loss: 3.1510
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0761 - loss: 3.1438
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0766 - loss: 3.1365
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0771 - loss: 3.1298
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0776 - loss: 3.1230
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0780 - loss: 3.1163
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0783 - loss: 3.1095
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0787 - loss: 3.1031
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0791 - loss: 3.0961
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0795 - loss: 3.0890
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0799 - loss: 3.0826
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0803 - loss: 3.0760
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0808 - loss: 3.0697
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0812 - loss: 3.0636
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0816 - loss: 3.0575
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0820 - loss: 3.0520
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0823 - loss: 3.0466
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0827 - loss: 3.0409
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0831 - loss: 3.0367
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0835 - loss: 3.0313
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0839 - loss: 3.0270
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0841 - loss: 3.0238
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0842 - loss: 3.0237 - val_accuracy: 0.1301 - val_loss: 2.6362
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.8607
[1m  44/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1161 - loss: 2.7589  
[1m  87/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1135 - loss: 2.7402
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1138 - loss: 2.7291
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1143 - loss: 2.7206
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1154 - loss: 2.7139
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1167 - loss: 2.7083
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1176 - loss: 2.7037
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1182 - loss: 2.7008
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1187 - loss: 2.6982
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1193 - loss: 2.6957
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1200 - loss: 2.6930
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1206 - loss: 2.6907
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1213 - loss: 2.6882
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1219 - loss: 2.6861
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1225 - loss: 2.6839
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1231 - loss: 2.6816
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1236 - loss: 2.6794
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1242 - loss: 2.6773
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1247 - loss: 2.6751
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1253 - loss: 2.6730
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1258 - loss: 2.6711
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1263 - loss: 2.6693
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1267 - loss: 2.6677
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1272 - loss: 2.6657
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1277 - loss: 2.6639
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1283 - loss: 2.6620
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1287 - loss: 2.6602
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1292 - loss: 2.6585
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1293 - loss: 2.6582 - val_accuracy: 0.1678 - val_loss: 2.5159
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.4872
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1622 - loss: 2.5705  
[1m  86/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1629 - loss: 2.5654
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1638 - loss: 2.5620
[1m 169/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1651 - loss: 2.5569
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1663 - loss: 2.5523
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1669 - loss: 2.5488
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1670 - loss: 2.5465
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1674 - loss: 2.5439
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1675 - loss: 2.5417
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1675 - loss: 2.5400
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1675 - loss: 2.5383
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1674 - loss: 2.5368
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1675 - loss: 2.5355
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1676 - loss: 2.5342
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1677 - loss: 2.5329
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1679 - loss: 2.5316
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1681 - loss: 2.5305
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1683 - loss: 2.5294
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1684 - loss: 2.5281
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1686 - loss: 2.5269
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1688 - loss: 2.5257
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1690 - loss: 2.5245
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1693 - loss: 2.5233
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1695 - loss: 2.5221
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1697 - loss: 2.5210
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1700 - loss: 2.5200
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1702 - loss: 2.5191
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1705 - loss: 2.5180
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1705 - loss: 2.5178 - val_accuracy: 0.1845 - val_loss: 2.4218
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.4231
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2177 - loss: 2.4172  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2098 - loss: 2.4238
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2074 - loss: 2.4267
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2044 - loss: 2.4307
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2029 - loss: 2.4317
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2019 - loss: 2.4324
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2010 - loss: 2.4323
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2004 - loss: 2.4318
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1999 - loss: 2.4312
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1996 - loss: 2.4303
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1995 - loss: 2.4292
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1993 - loss: 2.4281
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1992 - loss: 2.4273
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1991 - loss: 2.4264
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1990 - loss: 2.4256
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1989 - loss: 2.4248
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1987 - loss: 2.4241
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1986 - loss: 2.4235
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1985 - loss: 2.4228
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1984 - loss: 2.4220
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1982 - loss: 2.4214
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1981 - loss: 2.4207
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1980 - loss: 2.4201
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1978 - loss: 2.4195
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1977 - loss: 2.4190
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1976 - loss: 2.4185
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1975 - loss: 2.4179
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1974 - loss: 2.4174
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1973 - loss: 2.4169 - val_accuracy: 0.2070 - val_loss: 2.3506
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 2.3759
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2030 - loss: 2.3453  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1976 - loss: 2.3547
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1986 - loss: 2.3606
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2014 - loss: 2.3611
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2027 - loss: 2.3616
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2042 - loss: 2.3612
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2056 - loss: 2.3605
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2067 - loss: 2.3597
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2073 - loss: 2.3594
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2076 - loss: 2.3593
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2078 - loss: 2.3590
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2080 - loss: 2.3590
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2080 - loss: 2.3588
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2081 - loss: 2.3586
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2081 - loss: 2.3584
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2080 - loss: 2.3578
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2080 - loss: 2.3571
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2080 - loss: 2.3565
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2079 - loss: 2.3559
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2079 - loss: 2.3553
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2079 - loss: 2.3548
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2079 - loss: 2.3542
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2079 - loss: 2.3536
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2079 - loss: 2.3530
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2079 - loss: 2.3525
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2079 - loss: 2.3520
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2080 - loss: 2.3515
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2080 - loss: 2.3511
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2080 - loss: 2.3509 - val_accuracy: 0.2094 - val_loss: 2.2988
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.1479
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2208 - loss: 2.3050  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2093 - loss: 2.3218
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2077 - loss: 2.3257
[1m 149/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2075 - loss: 2.3264
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2075 - loss: 2.3262
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2077 - loss: 2.3252
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2081 - loss: 2.3240
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2082 - loss: 2.3236
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2083 - loss: 2.3226
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2087 - loss: 2.3213
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2089 - loss: 2.3203
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2091 - loss: 2.3195
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2093 - loss: 2.3186
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2096 - loss: 2.3178
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2097 - loss: 2.3173
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2098 - loss: 2.3165
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2100 - loss: 2.3157
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2101 - loss: 2.3149
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2102 - loss: 2.3141
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2104 - loss: 2.3132
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2106 - loss: 2.3124
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2107 - loss: 2.3116
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2108 - loss: 2.3108
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2109 - loss: 2.3100
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2110 - loss: 2.3093
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2111 - loss: 2.3087
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2113 - loss: 2.3080
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2114 - loss: 2.3073
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2116 - loss: 2.3069 - val_accuracy: 0.2142 - val_loss: 2.2566
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.9085
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2293 - loss: 2.1873  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2164 - loss: 2.2101
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2133 - loss: 2.2252
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2133 - loss: 2.2335
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2130 - loss: 2.2390
[1m 249/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2128 - loss: 2.2419
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2130 - loss: 2.2432
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2131 - loss: 2.2440
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2132 - loss: 2.2447
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2134 - loss: 2.2450
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2135 - loss: 2.2453
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2139 - loss: 2.2455
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2144 - loss: 2.2455
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2148 - loss: 2.2455
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2152 - loss: 2.2455
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2156 - loss: 2.2454
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2158 - loss: 2.2455
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2160 - loss: 2.2457
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2161 - loss: 2.2458
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2162 - loss: 2.2459
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2164 - loss: 2.2460
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2166 - loss: 2.2460
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2167 - loss: 2.2461
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2169 - loss: 2.2461
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2170 - loss: 2.2462
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2171 - loss: 2.2464
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2173 - loss: 2.2465
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2174 - loss: 2.2465
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2176 - loss: 2.2465 - val_accuracy: 0.2174 - val_loss: 2.2235
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.3300
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2429 - loss: 2.2127  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2305 - loss: 2.2226
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2260 - loss: 2.2291
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2240 - loss: 2.2330
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2235 - loss: 2.2339
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2231 - loss: 2.2350
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2231 - loss: 2.2356
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2231 - loss: 2.2361
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2231 - loss: 2.2359
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2233 - loss: 2.2354
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2236 - loss: 2.2350
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2239 - loss: 2.2348
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2241 - loss: 2.2347
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2244 - loss: 2.2346
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2247 - loss: 2.2343
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2250 - loss: 2.2338
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2253 - loss: 2.2333
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2255 - loss: 2.2329
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2256 - loss: 2.2326
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2256 - loss: 2.2323
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2257 - loss: 2.2320
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2257 - loss: 2.2317
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2258 - loss: 2.2315
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2258 - loss: 2.2312
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2258 - loss: 2.2309
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2258 - loss: 2.2307
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2258 - loss: 2.2305
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2257 - loss: 2.2303
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2257 - loss: 2.2302 - val_accuracy: 0.2239 - val_loss: 2.1938
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.1699
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2631 - loss: 2.1849  
[1m  86/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2492 - loss: 2.2070
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2485 - loss: 2.2059
[1m 169/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2484 - loss: 2.2052
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2478 - loss: 2.2037
[1m 253/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2465 - loss: 2.2029
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2453 - loss: 2.2031
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2438 - loss: 2.2039
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2427 - loss: 2.2043
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2420 - loss: 2.2042
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2414 - loss: 2.2041
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2408 - loss: 2.2041
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2403 - loss: 2.2042
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2397 - loss: 2.2043
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2392 - loss: 2.2043
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2387 - loss: 2.2042
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2383 - loss: 2.2040
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2379 - loss: 2.2037
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2376 - loss: 2.2034
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2373 - loss: 2.2031
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2370 - loss: 2.2028
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2368 - loss: 2.2025
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2365 - loss: 2.2023
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2363 - loss: 2.2021
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2361 - loss: 2.2019
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2359 - loss: 2.2017
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2357 - loss: 2.2015
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2355 - loss: 2.2013
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2355 - loss: 2.2012 - val_accuracy: 0.2416 - val_loss: 2.1636
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.0760
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2529 - loss: 2.2368  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2468 - loss: 2.2343
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2469 - loss: 2.2224
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2474 - loss: 2.2108
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2478 - loss: 2.2025
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2481 - loss: 2.1977
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2480 - loss: 2.1941
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2473 - loss: 2.1915
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2465 - loss: 2.1895
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2458 - loss: 2.1882
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2450 - loss: 2.1873
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2445 - loss: 2.1865
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2440 - loss: 2.1858
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2436 - loss: 2.1852
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2430 - loss: 2.1849
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2425 - loss: 2.1845
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2420 - loss: 2.1842
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2416 - loss: 2.1839
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2413 - loss: 2.1835
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2410 - loss: 2.1833
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2408 - loss: 2.1831
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2406 - loss: 2.1829
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2404 - loss: 2.1825
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2403 - loss: 2.1822
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2402 - loss: 2.1819
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2401 - loss: 2.1815
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2401 - loss: 2.1811
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2400 - loss: 2.1807
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2400 - loss: 2.1806 - val_accuracy: 0.2437 - val_loss: 2.1587
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 1.9948
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2409 - loss: 2.1394  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2384 - loss: 2.1338
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2389 - loss: 2.1388
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2393 - loss: 2.1416
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2389 - loss: 2.1458
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2383 - loss: 2.1489
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2378 - loss: 2.1515
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2374 - loss: 2.1528
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2371 - loss: 2.1543
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2368 - loss: 2.1555
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2364 - loss: 2.1568
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2363 - loss: 2.1577
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2361 - loss: 2.1584
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2361 - loss: 2.1588
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2362 - loss: 2.1590
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2362 - loss: 2.1593
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2362 - loss: 2.1596
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2363 - loss: 2.1597
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2365 - loss: 2.1598
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2366 - loss: 2.1597
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2367 - loss: 2.1595
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2369 - loss: 2.1594
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2370 - loss: 2.1593
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2371 - loss: 2.1592
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2373 - loss: 2.1590
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2374 - loss: 2.1589
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2375 - loss: 2.1587
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2375 - loss: 2.1586
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2376 - loss: 2.1584
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2376 - loss: 2.1584 - val_accuracy: 0.2366 - val_loss: 2.1549
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.2201
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2336 - loss: 2.1102  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1033
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2476 - loss: 2.1047
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2473 - loss: 2.1086
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2465 - loss: 2.1136
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2460 - loss: 2.1167
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1192
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2450 - loss: 2.1218
[1m 378/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2448 - loss: 2.1227
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2450 - loss: 2.1229
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1234
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1242
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2453 - loss: 2.1249
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2453 - loss: 2.1255
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1262
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1268
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1274
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2450 - loss: 2.1279
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2449 - loss: 2.1282
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2449 - loss: 2.1285
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2449 - loss: 2.1286
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2450 - loss: 2.1286
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2450 - loss: 2.1287
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1288
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1290
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1293
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1294
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1296
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2452 - loss: 2.1296 - val_accuracy: 0.2546 - val_loss: 2.0988
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.0782
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2234 - loss: 2.1348  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2245 - loss: 2.1284
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2276 - loss: 2.1226
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2310 - loss: 2.1201
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2328 - loss: 2.1187
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2347 - loss: 2.1178
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2363 - loss: 2.1173
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2378 - loss: 2.1170
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2389 - loss: 2.1166
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2399 - loss: 2.1161
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2407 - loss: 2.1156
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2414 - loss: 2.1149
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2421 - loss: 2.1144
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2426 - loss: 2.1140
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2431 - loss: 2.1136
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2435 - loss: 2.1132
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2439 - loss: 2.1130
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2441 - loss: 2.1128
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2444 - loss: 2.1127
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2446 - loss: 2.1126
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2448 - loss: 2.1126
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2450 - loss: 2.1126
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1126
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1126
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.1126
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1125
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2456 - loss: 2.1124
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1124
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2457 - loss: 2.1123 - val_accuracy: 0.2601 - val_loss: 2.1028
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 1.9865
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2292 - loss: 2.1104  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2355 - loss: 2.0940
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2387 - loss: 2.0932
[1m 175/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2403 - loss: 2.0920
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2414 - loss: 2.0922
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2421 - loss: 2.0934
[1m 301/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2430 - loss: 2.0943
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2439 - loss: 2.0947
[1m 377/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2449 - loss: 2.0950
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2456 - loss: 2.0956
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2464 - loss: 2.0962
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2470 - loss: 2.0968
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2475 - loss: 2.0972
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2479 - loss: 2.0977
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2481 - loss: 2.0982
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2483 - loss: 2.0986
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2485 - loss: 2.0988
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2488 - loss: 2.0991
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2490 - loss: 2.0993
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2492 - loss: 2.0995
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2494 - loss: 2.0997
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2495 - loss: 2.1000
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2496 - loss: 2.1003
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2497 - loss: 2.1005
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2498 - loss: 2.1007
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2499 - loss: 2.1008
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2500 - loss: 2.1008
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2501 - loss: 2.1008
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2501 - loss: 2.1008 - val_accuracy: 0.2492 - val_loss: 2.0885
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 1.8442
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2570 - loss: 2.0572  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2514 - loss: 2.0675
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2538 - loss: 2.0621
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2542 - loss: 2.0615
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2535 - loss: 2.0639
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2529 - loss: 2.0677
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2524 - loss: 2.0711
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2520 - loss: 2.0731
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2517 - loss: 2.0746
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2517 - loss: 2.0756
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2518 - loss: 2.0765
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2519 - loss: 2.0773
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2520 - loss: 2.0779
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2521 - loss: 2.0785
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2523 - loss: 2.0789
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2524 - loss: 2.0792
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2526 - loss: 2.0795
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.0795
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2530 - loss: 2.0796
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2531 - loss: 2.0798
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2533 - loss: 2.0800
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2533 - loss: 2.0802
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2534 - loss: 2.0805
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2535 - loss: 2.0807
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2536 - loss: 2.0808
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2536 - loss: 2.0809
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2537 - loss: 2.0810
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2537 - loss: 2.0811
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2537 - loss: 2.0811 - val_accuracy: 0.2559 - val_loss: 2.0929
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3750 - loss: 1.9547
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2796 - loss: 2.0635  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2764 - loss: 2.0716
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2743 - loss: 2.0700
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2696 - loss: 2.0719
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0712
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0721
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0730
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2626 - loss: 2.0737
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2615 - loss: 2.0748
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2606 - loss: 2.0756
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0766
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2594 - loss: 2.0773
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2588 - loss: 2.0781
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2583 - loss: 2.0786
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.0788
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.0788
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2576 - loss: 2.0787
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2574 - loss: 2.0787
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0785
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0784
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0782
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0779
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0778
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0777
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0776
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0775
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0773
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2574 - loss: 2.0771
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2574 - loss: 2.0771 - val_accuracy: 0.2568 - val_loss: 2.0764
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.3249
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2527 - loss: 2.0876  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2553 - loss: 2.0802
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0731
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2553 - loss: 2.0690
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2551 - loss: 2.0663
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0650
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2550 - loss: 2.0644
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2549 - loss: 2.0645
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2549 - loss: 2.0652
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2552 - loss: 2.0652
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2556 - loss: 2.0650
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0652
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2564 - loss: 2.0651
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0649
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0647
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2576 - loss: 2.0646
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.0647
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0648
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2583 - loss: 2.0649
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2585 - loss: 2.0649
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2586 - loss: 2.0649
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2588 - loss: 2.0649
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2589 - loss: 2.0649
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2591 - loss: 2.0649
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2592 - loss: 2.0648
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2593 - loss: 2.0648
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2595 - loss: 2.0647
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2596 - loss: 2.0646
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.2597 - loss: 2.0645
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2597 - loss: 2.0645 - val_accuracy: 0.2503 - val_loss: 2.0592
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 1.7908
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0537  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0664
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0678
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2616 - loss: 2.0680
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2622 - loss: 2.0657
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0633
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0629
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2640 - loss: 2.0629
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0626
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0626
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0628
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0629
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0629
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0630
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0631
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2648 - loss: 2.0632
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2647 - loss: 2.0631
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2647 - loss: 2.0629
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2646 - loss: 2.0628
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2646 - loss: 2.0627
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0627
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0626
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0624
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0622
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0620
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0618
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0616
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0614
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2645 - loss: 2.0613 - val_accuracy: 0.2446 - val_loss: 2.0616
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 1.9781
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2987 - loss: 2.0110  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2845 - loss: 2.0342
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2772 - loss: 2.0390
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0415
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2712 - loss: 2.0409
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0398
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0398
[1m 333/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0396
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2691 - loss: 2.0391
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2688 - loss: 2.0385
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2684 - loss: 2.0379
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0376
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0374
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0371
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0367
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0363
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0358
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0356
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0355
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0355
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0356
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0357
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0359
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0361
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0363
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0365
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0367
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0369
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2657 - loss: 2.0370 - val_accuracy: 0.2611 - val_loss: 2.0524
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.0319
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3376 - loss: 1.9605  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3169 - loss: 1.9787
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3089 - loss: 1.9864
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3029 - loss: 1.9938
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3003 - loss: 1.9980
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2976 - loss: 2.0015
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2953 - loss: 2.0049
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2936 - loss: 2.0077
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2925 - loss: 2.0096
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2916 - loss: 2.0106
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2910 - loss: 2.0112
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2904 - loss: 2.0118
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2899 - loss: 2.0124
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2895 - loss: 2.0127
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2892 - loss: 2.0130
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2888 - loss: 2.0133
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2883 - loss: 2.0139
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2880 - loss: 2.0144
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2876 - loss: 2.0147
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2872 - loss: 2.0152
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2869 - loss: 2.0156
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2865 - loss: 2.0162
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2860 - loss: 2.0168
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2855 - loss: 2.0173
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2851 - loss: 2.0178
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2847 - loss: 2.0182
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2843 - loss: 2.0185
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2840 - loss: 2.0188
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2837 - loss: 2.0190 - val_accuracy: 0.2524 - val_loss: 2.0469
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.2040
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2807 - loss: 2.0683  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2725 - loss: 2.0457
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0345
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0287
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0250
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0224
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0206
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0191
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2723 - loss: 2.0182
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2725 - loss: 2.0180
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2728 - loss: 2.0177
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0175
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0173
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2738 - loss: 2.0173
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0175
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0178
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0180
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0182
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2739 - loss: 2.0183
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2738 - loss: 2.0184
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2738 - loss: 2.0186
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 2.0187
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0188
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0189
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0189
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0188
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 2.0187
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 2.0187
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2737 - loss: 2.0187 - val_accuracy: 0.2675 - val_loss: 2.0510
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.5112
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2507 - loss: 2.1084  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2615 - loss: 2.0579
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2634 - loss: 2.0350
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2629 - loss: 2.0251
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2621 - loss: 2.0197
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2612 - loss: 2.0178
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0176
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2597 - loss: 2.0186
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2593 - loss: 2.0192
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2592 - loss: 2.0195
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2592 - loss: 2.0195
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2594 - loss: 2.0196
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2594 - loss: 2.0199
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2596 - loss: 2.0203
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2598 - loss: 2.0204
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2601 - loss: 2.0205
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0206
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2606 - loss: 2.0207
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0209
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2613 - loss: 2.0209
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2617 - loss: 2.0208
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2621 - loss: 2.0208
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2625 - loss: 2.0208
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2629 - loss: 2.0206
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2632 - loss: 2.0204
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2635 - loss: 2.0203
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2638 - loss: 2.0201
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2641 - loss: 2.0200
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2643 - loss: 2.0199 - val_accuracy: 0.2470 - val_loss: 2.0600
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.8605
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2729 - loss: 2.0255  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2812 - loss: 2.0120
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2817 - loss: 2.0071
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2806 - loss: 2.0038
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2802 - loss: 2.0020
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2802 - loss: 2.0004
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2803 - loss: 1.9993
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2803 - loss: 1.9988
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2804 - loss: 1.9986
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 1.9984
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 1.9984
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 1.9983
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2808 - loss: 1.9979
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 1.9974
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 1.9967
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9963
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2813 - loss: 1.9960
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2813 - loss: 1.9958
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9957
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9955
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9953
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9952
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9952
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9952
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9953
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9953
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9955
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 1.9956
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 1.9958
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2810 - loss: 1.9958 - val_accuracy: 0.2562 - val_loss: 2.0469
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 1.8826
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2601 - loss: 1.9999  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0178
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0177
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2726 - loss: 2.0182
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2730 - loss: 2.0188
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2738 - loss: 2.0174
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0150
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2758 - loss: 2.0128
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2762 - loss: 2.0117
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2766 - loss: 2.0107
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2769 - loss: 2.0103
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2770 - loss: 2.0103
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2771 - loss: 2.0103
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2771 - loss: 2.0101
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2770 - loss: 2.0098
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2771 - loss: 2.0094
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2773 - loss: 2.0088
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2774 - loss: 2.0083
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 2.0079
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 2.0076
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2777 - loss: 2.0072
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2778 - loss: 2.0070
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2779 - loss: 2.0068
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2779 - loss: 2.0067
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2780 - loss: 2.0066
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2781 - loss: 2.0064
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2782 - loss: 2.0062
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2783 - loss: 2.0060
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2783 - loss: 2.0059 - val_accuracy: 0.2603 - val_loss: 2.0521
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.9489
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3029 - loss: 1.9069  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2968 - loss: 1.9322
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2919 - loss: 1.9510
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2898 - loss: 1.9606
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2884 - loss: 1.9667
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2878 - loss: 1.9700
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2876 - loss: 1.9728
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2876 - loss: 1.9751
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2875 - loss: 1.9768
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2874 - loss: 1.9781
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2872 - loss: 1.9796
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2869 - loss: 1.9808
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2868 - loss: 1.9818
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2867 - loss: 1.9824
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2866 - loss: 1.9828
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2865 - loss: 1.9833
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2864 - loss: 1.9835
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2863 - loss: 1.9838
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2863 - loss: 1.9840
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2862 - loss: 1.9843
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2860 - loss: 1.9847
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2859 - loss: 1.9850
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2857 - loss: 1.9853
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2856 - loss: 1.9856
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2856 - loss: 1.9858
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2855 - loss: 1.9860
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2854 - loss: 1.9862
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2854 - loss: 1.9864
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2854 - loss: 1.9866 - val_accuracy: 0.2603 - val_loss: 2.0199

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 643ms/step
[1m59/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 864us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7:52[0m 811ms/step
[1m 60/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 849us/step  
[1m125/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 814us/step
[1m197/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 773us/step
[1m269/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 754us/step
[1m345/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 734us/step
[1m418/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 727us/step
[1m486/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 728us/step
[1m551/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 733us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m58/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 878us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 69/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 744us/step
[1m139/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 735us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 28.73 [%]
Global F1 score (validation) = 24.96 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.1702865  0.1594157  0.16499291 ... 0.00428539 0.13908274 0.02175606]
 [0.20269215 0.15279053 0.18160735 ... 0.00125937 0.13433443 0.03501273]
 [0.22075926 0.14818415 0.16202049 ... 0.00198454 0.13849708 0.03808238]
 ...
 [0.19260865 0.187992   0.1697597  ... 0.00273285 0.12155166 0.04026076]
 [0.16576132 0.1883945  0.14926967 ... 0.00337764 0.15559813 0.04029133]
 [0.09543375 0.12895918 0.08455854 ... 0.01574044 0.06889193 0.01077157]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 32.42 [%]
Global accuracy score (test) = 28.02 [%]
Global F1 score (train) = 29.44 [%]
Global F1 score (test) = 25.06 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.16      0.18      0.17       184
 CAMINAR CON MÓVIL O LIBRO       0.22      0.24      0.23       184
       CAMINAR USUAL SPEED       0.23      0.04      0.07       184
            CAMINAR ZIGZAG       0.20      0.56      0.29       184
          DE PIE BARRIENDO       0.30      0.64      0.41       184
   DE PIE DOBLANDO TOALLAS       0.00      0.00      0.00       184
    DE PIE MOVIENDO LIBROS       0.21      0.17      0.19       184
          DE PIE USANDO PC       0.26      0.76      0.39       184
        FASE REPOSO CON K5       0.82      0.62      0.71       184
INCREMENTAL CICLOERGOMETRO       0.78      0.20      0.31       184
           SENTADO LEYENDO       0.06      0.02      0.03       184
         SENTADO USANDO PC       0.10      0.10      0.10       184
      SENTADO VIENDO LA TV       0.26      0.23      0.25       184
   SUBIR Y BAJAR ESCALERAS       0.06      0.01      0.01       184
                    TROTAR       0.90      0.45      0.60       161

                  accuracy                           0.28      2737
                 macro avg       0.30      0.28      0.25      2737
              weighted avg       0.30      0.28      0.25      2737


Accuracy capturado en la ejecución 20: 28.02 [%]
F1-score capturado en la ejecución 20: 25.06 [%]

=== EJECUCIÓN 21 ===

--- TRAIN (ejecución 21) ---

--- TEST (ejecución 21) ---
2025-11-07 14:29:12.488310: 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 14:29:12.499663: 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 00:00:1762522152.513223 2986611 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762522152.517269 2986611 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762522152.527093 2986611 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522152.527109 2986611 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522152.527111 2986611 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522152.527112 2986611 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:29:12.530076: 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 00:00:1762522154.773655 2986611 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762522156.271389 2986721 service.cc:152] XLA service 0x7fa1a000b970 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762522156.271416 2986721 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:29:16.298964: 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 00:00:1762522156.444077 2986721 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762522157.843140 2986721 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47:12[0m 2s/step - accuracy: 0.0000e+00 - loss: 3.6119
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0560 - loss: 3.2193      
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0609 - loss: 3.1839
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0622 - loss: 3.1675
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0636 - loss: 3.1519
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0646 - loss: 3.1388
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0656 - loss: 3.1278
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0669 - loss: 3.1150
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0679 - loss: 3.1055
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0690 - loss: 3.0961
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0700 - loss: 3.0870
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0710 - loss: 3.0784
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0721 - loss: 3.0700
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0731 - loss: 3.0620
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0740 - loss: 3.0544
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0750 - loss: 3.0469
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0758 - loss: 3.0405
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0766 - loss: 3.0343
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0774 - loss: 3.0278
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0783 - loss: 3.0213
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0791 - loss: 3.0154
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0799 - loss: 3.0091
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0807 - loss: 3.0033
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0815 - loss: 2.9974
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0823 - loss: 2.9918
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0831 - loss: 2.9861
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0838 - loss: 2.9809
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0845 - loss: 2.9759
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0852 - loss: 2.9712
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0858 - loss: 2.9671
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0858 - loss: 2.9670 - val_accuracy: 0.1478 - val_loss: 2.5776
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.6625
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1322 - loss: 2.6245  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1260 - loss: 2.6231
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1259 - loss: 2.6234
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1256 - loss: 2.6246
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1260 - loss: 2.6255
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1265 - loss: 2.6266
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1275 - loss: 2.6273
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1282 - loss: 2.6278
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1289 - loss: 2.6283
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1295 - loss: 2.6285
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1302 - loss: 2.6285
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1310 - loss: 2.6280
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1317 - loss: 2.6274
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1325 - loss: 2.6267
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1332 - loss: 2.6261
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1338 - loss: 2.6253
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1344 - loss: 2.6245
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1349 - loss: 2.6237
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1355 - loss: 2.6227
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1360 - loss: 2.6218
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1364 - loss: 2.6210
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1369 - loss: 2.6199
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1373 - loss: 2.6189
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1378 - loss: 2.6178
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1382 - loss: 2.6167
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1386 - loss: 2.6156
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1390 - loss: 2.6143
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1394 - loss: 2.6132
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1398 - loss: 2.6121
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1400 - loss: 2.6114 - val_accuracy: 0.1863 - val_loss: 2.4634
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 2.3226
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1902 - loss: 2.4590  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1815 - loss: 2.4807
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1794 - loss: 2.4902
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1768 - loss: 2.4970
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1750 - loss: 2.5003
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1740 - loss: 2.5012
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1734 - loss: 2.5015
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1730 - loss: 2.5022
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1729 - loss: 2.5024
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1728 - loss: 2.5024
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1726 - loss: 2.5022
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1725 - loss: 2.5019
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1726 - loss: 2.5013
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1725 - loss: 2.5007
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1726 - loss: 2.5000
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1727 - loss: 2.4990
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1729 - loss: 2.4983
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1729 - loss: 2.4975
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1730 - loss: 2.4967
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1731 - loss: 2.4958
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1733 - loss: 2.4948
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1734 - loss: 2.4938
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1736 - loss: 2.4929
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1737 - loss: 2.4920
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1739 - loss: 2.4911
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1741 - loss: 2.4902
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1744 - loss: 2.4892
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1746 - loss: 2.4882
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1747 - loss: 2.4880 - val_accuracy: 0.2189 - val_loss: 2.3692
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.3153
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2333 - loss: 2.3687  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2285 - loss: 2.3760
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2213 - loss: 2.3876
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2172 - loss: 2.3927
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2139 - loss: 2.3952
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2116 - loss: 2.3979
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2094 - loss: 2.4010
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2079 - loss: 2.4031
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2066 - loss: 2.4048
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2057 - loss: 2.4056
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2051 - loss: 2.4059
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2046 - loss: 2.4059
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2044 - loss: 2.4056
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2041 - loss: 2.4052
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2038 - loss: 2.4047
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2036 - loss: 2.4041
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2033 - loss: 2.4035
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2031 - loss: 2.4029
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2029 - loss: 2.4023
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2027 - loss: 2.4016
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2025 - loss: 2.4010
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2023 - loss: 2.4004
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2021 - loss: 2.3999
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2020 - loss: 2.3993
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2018 - loss: 2.3986
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2017 - loss: 2.3980
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2017 - loss: 2.3974
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2016 - loss: 2.3968
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2015 - loss: 2.3963
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2015 - loss: 2.3962 - val_accuracy: 0.2167 - val_loss: 2.3139
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.3025
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2158 - loss: 2.3300  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2158 - loss: 2.3441
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2151 - loss: 2.3410
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2143 - loss: 2.3411
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2142 - loss: 2.3403
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2139 - loss: 2.3400
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2139 - loss: 2.3400
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2140 - loss: 2.3399
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2139 - loss: 2.3397
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2140 - loss: 2.3393
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2140 - loss: 2.3389
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2140 - loss: 2.3385
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2140 - loss: 2.3381
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2139 - loss: 2.3377
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2139 - loss: 2.3373
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2141 - loss: 2.3368
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2143 - loss: 2.3361
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2145 - loss: 2.3354
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2146 - loss: 2.3348
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2148 - loss: 2.3341
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2149 - loss: 2.3335
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2149 - loss: 2.3330
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2150 - loss: 2.3324
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2152 - loss: 2.3319
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2153 - loss: 2.3313
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2154 - loss: 2.3307
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2155 - loss: 2.3302
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2156 - loss: 2.3296
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2158 - loss: 2.3291
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2158 - loss: 2.3288 - val_accuracy: 0.2361 - val_loss: 2.2258
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.3806
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2199 - loss: 2.2705  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2164 - loss: 2.2845
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2160 - loss: 2.2904
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2182 - loss: 2.2890
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2195 - loss: 2.2870
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2209 - loss: 2.2851
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2220 - loss: 2.2840
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2224 - loss: 2.2833
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2226 - loss: 2.2830
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2225 - loss: 2.2828
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2226 - loss: 2.2826
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2226 - loss: 2.2825
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2226 - loss: 2.2823
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2226 - loss: 2.2822
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2226 - loss: 2.2818
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2227 - loss: 2.2813
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2228 - loss: 2.2807
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2228 - loss: 2.2802
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2228 - loss: 2.2798
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2228 - loss: 2.2794
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2228 - loss: 2.2791
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2229 - loss: 2.2786
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2229 - loss: 2.2782
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2229 - loss: 2.2779
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2230 - loss: 2.2775
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2231 - loss: 2.2771
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2231 - loss: 2.2767
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2231 - loss: 2.2763
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2231 - loss: 2.2760
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2231 - loss: 2.2757 - val_accuracy: 0.2359 - val_loss: 2.2000
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.4375 - loss: 2.1041
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2555 - loss: 2.2210  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2413 - loss: 2.2272
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2382 - loss: 2.2274
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2362 - loss: 2.2287
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2356 - loss: 2.2290
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2355 - loss: 2.2293
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2353 - loss: 2.2293
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2350 - loss: 2.2296
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2346 - loss: 2.2299
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2341 - loss: 2.2307
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2335 - loss: 2.2313
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2331 - loss: 2.2318
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2327 - loss: 2.2320
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2324 - loss: 2.2321
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2321 - loss: 2.2322
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2319 - loss: 2.2321
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2318 - loss: 2.2319
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2317 - loss: 2.2318
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2317 - loss: 2.2315
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2317 - loss: 2.2313
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2316 - loss: 2.2311
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2315 - loss: 2.2309
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2315 - loss: 2.2306
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2314 - loss: 2.2304
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2314 - loss: 2.2301
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2314 - loss: 2.2299
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2314 - loss: 2.2296
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2314 - loss: 2.2293
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2314 - loss: 2.2291
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2314 - loss: 2.2290 - val_accuracy: 0.2487 - val_loss: 2.1655
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.4056
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1830 - loss: 2.2795  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1980 - loss: 2.2649
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2055 - loss: 2.2549
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2082 - loss: 2.2475
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2114 - loss: 2.2405
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2146 - loss: 2.2345
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2170 - loss: 2.2302
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2188 - loss: 2.2278
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2203 - loss: 2.2260
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2214 - loss: 2.2244
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2224 - loss: 2.2226
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2235 - loss: 2.2208
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2245 - loss: 2.2192
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2253 - loss: 2.2181
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2262 - loss: 2.2169
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2269 - loss: 2.2159
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2275 - loss: 2.2149
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2280 - loss: 2.2139
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2286 - loss: 2.2128
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2291 - loss: 2.2119
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2295 - loss: 2.2110
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2300 - loss: 2.2101
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2304 - loss: 2.2092
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2308 - loss: 2.2084
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2312 - loss: 2.2075
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2315 - loss: 2.2066
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2318 - loss: 2.2060
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2321 - loss: 2.2053
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2323 - loss: 2.2048 - val_accuracy: 0.2372 - val_loss: 2.1432
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.1681
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2633 - loss: 2.0956  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2532 - loss: 2.1237
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2528 - loss: 2.1358
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2517 - loss: 2.1452
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2499 - loss: 2.1531
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2487 - loss: 2.1566
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2480 - loss: 2.1589
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2475 - loss: 2.1614
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2472 - loss: 2.1633
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2468 - loss: 2.1649
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2464 - loss: 2.1663
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2461 - loss: 2.1674
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1682
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.1687
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2453 - loss: 2.1690
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1694
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1694
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1693
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1692
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1690
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1687
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1684
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1681
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1679
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1677
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1676
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1675
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1673
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1671
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2450 - loss: 2.1670 - val_accuracy: 0.2398 - val_loss: 2.1309
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 30ms/step - accuracy: 0.1250 - loss: 2.3133
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2297 - loss: 2.2124  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1745
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2441 - loss: 2.1639
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1622
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2467 - loss: 2.1597
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2483 - loss: 2.1564
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2502 - loss: 2.1536
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2517 - loss: 2.1512
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2525 - loss: 2.1499
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2531 - loss: 2.1489
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2534 - loss: 2.1481
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2535 - loss: 2.1478
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2537 - loss: 2.1473
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2538 - loss: 2.1466
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2540 - loss: 2.1457
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2540 - loss: 2.1452
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2540 - loss: 2.1447
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2539 - loss: 2.1443
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2538 - loss: 2.1439
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2537 - loss: 2.1437
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2535 - loss: 2.1434
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2535 - loss: 2.1432
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2534 - loss: 2.1429
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2533 - loss: 2.1426
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2533 - loss: 2.1424
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2532 - loss: 2.1421
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2532 - loss: 2.1418
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2532 - loss: 2.1416
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2531 - loss: 2.1414
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2531 - loss: 2.1414 - val_accuracy: 0.2448 - val_loss: 2.1072
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.1102
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2281 - loss: 2.1407  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2357 - loss: 2.1320
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2406 - loss: 2.1257
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2432 - loss: 2.1234
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2441 - loss: 2.1229
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2463 - loss: 2.1204
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2483 - loss: 2.1182
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2497 - loss: 2.1171
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2506 - loss: 2.1166
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.1163
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2521 - loss: 2.1156
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.1148
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2535 - loss: 2.1141
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2540 - loss: 2.1133
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2544 - loss: 2.1130
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2546 - loss: 2.1129
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2547 - loss: 2.1130
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2547 - loss: 2.1131
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.1133
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.1136
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.1138
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.1140
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2549 - loss: 2.1143
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2549 - loss: 2.1144
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2550 - loss: 2.1147
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2550 - loss: 2.1148
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2550 - loss: 2.1151
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2550 - loss: 2.1153
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2550 - loss: 2.1154 - val_accuracy: 0.2461 - val_loss: 2.0834
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 2.0070
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0360  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0425
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2623 - loss: 2.0484
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0563
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0599
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2600 - loss: 2.0631
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2596 - loss: 2.0664
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2593 - loss: 2.0688
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2590 - loss: 2.0712
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2588 - loss: 2.0733
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2586 - loss: 2.0750
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2583 - loss: 2.0765
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0779
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.0795
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2576 - loss: 2.0809
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2574 - loss: 2.0822
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0834
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2570 - loss: 2.0845
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.0853
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0862
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0869
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.0877
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2564 - loss: 2.0885
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2562 - loss: 2.0892
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0898
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0903
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0907
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0911
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0914
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2560 - loss: 2.0914 - val_accuracy: 0.2477 - val_loss: 2.0855
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.0625 - loss: 2.1749
[1m  44/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2451 - loss: 2.0810  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2533 - loss: 2.0840
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2558 - loss: 2.0850
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0849
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2583 - loss: 2.0836
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2590 - loss: 2.0842
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2596 - loss: 2.0854
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2596 - loss: 2.0864
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2595 - loss: 2.0870
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2597 - loss: 2.0871
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0870
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2601 - loss: 2.0867
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0866
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0867
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2605 - loss: 2.0868
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2605 - loss: 2.0870
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0872
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0875
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0877
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2601 - loss: 2.0880
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2600 - loss: 2.0883
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2600 - loss: 2.0884
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0887
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0889
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0890
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0891
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0891
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0891
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2599 - loss: 2.0891 - val_accuracy: 0.2598 - val_loss: 2.0486
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.5625 - loss: 1.6138
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2988 - loss: 2.0224  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2898 - loss: 2.0241
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2879 - loss: 2.0223
[1m 169/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2842 - loss: 2.0277
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2821 - loss: 2.0312
[1m 251/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2811 - loss: 2.0332
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2804 - loss: 2.0346
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2798 - loss: 2.0364
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2792 - loss: 2.0389
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2786 - loss: 2.0413
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2781 - loss: 2.0434
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 2.0455
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2772 - loss: 2.0472
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2768 - loss: 2.0489
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2764 - loss: 2.0505
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2758 - loss: 2.0521
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2754 - loss: 2.0533
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0545
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0557
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0569
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0577
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0585
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2729 - loss: 2.0591
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2726 - loss: 2.0596
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2723 - loss: 2.0601
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0605
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2719 - loss: 2.0608
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0610
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2715 - loss: 2.0611 - val_accuracy: 0.2440 - val_loss: 2.0813
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.9686
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3202 - loss: 2.0713  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3045 - loss: 2.0463
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2975 - loss: 2.0419
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2924 - loss: 2.0433
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2880 - loss: 2.0434
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2842 - loss: 2.0452
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2816 - loss: 2.0470
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2795 - loss: 2.0490
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2779 - loss: 2.0500
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2771 - loss: 2.0503
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2764 - loss: 2.0504
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 2.0508
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2754 - loss: 2.0511
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0513
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0515
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0517
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0520
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2743 - loss: 2.0522
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2741 - loss: 2.0525
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2739 - loss: 2.0527
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2738 - loss: 2.0528
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 2.0530
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2735 - loss: 2.0531
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2734 - loss: 2.0533
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0535
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0536
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2730 - loss: 2.0537
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2729 - loss: 2.0539
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2728 - loss: 2.0540
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2727 - loss: 2.0541 - val_accuracy: 0.2468 - val_loss: 2.0492
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 1.7840
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2955 - loss: 1.9424  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2846 - loss: 1.9799
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2781 - loss: 1.9919
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2751 - loss: 1.9988
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2737 - loss: 2.0035
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2728 - loss: 2.0073
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2723 - loss: 2.0106
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0131
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0151
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2723 - loss: 2.0171
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0186
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0199
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0214
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2714 - loss: 2.0230
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0246
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0259
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2705 - loss: 2.0272
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0284
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0295
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0305
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 2.0316
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2695 - loss: 2.0326
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2695 - loss: 2.0333
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0341
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0347
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0353
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0357
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0361
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0364
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2694 - loss: 2.0364 - val_accuracy: 0.2611 - val_loss: 2.0309
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 2.2661
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3051 - loss: 2.0926  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2927 - loss: 2.0766
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2828 - loss: 2.0736
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2773 - loss: 2.0675
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0632
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2728 - loss: 2.0611
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2725 - loss: 2.0583
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0570
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2719 - loss: 2.0551
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0539
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2719 - loss: 2.0522
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0504
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2725 - loss: 2.0491
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2727 - loss: 2.0480
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2728 - loss: 2.0470
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2730 - loss: 2.0461
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0454
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2733 - loss: 2.0449
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2734 - loss: 2.0445
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2735 - loss: 2.0442
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0440
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0440
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0440
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0438
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0436
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0434
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0431
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0429
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2735 - loss: 2.0426
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2735 - loss: 2.0424 - val_accuracy: 0.2535 - val_loss: 2.0337
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.9543
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3166 - loss: 1.9779  
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2952 - loss: 1.9988
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2868 - loss: 2.0086
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2821 - loss: 2.0145
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2804 - loss: 2.0158
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2799 - loss: 2.0167
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2795 - loss: 2.0176
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2793 - loss: 2.0176
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2794 - loss: 2.0172
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2795 - loss: 2.0167
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 2.0165
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2797 - loss: 2.0163
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2798 - loss: 2.0165
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2798 - loss: 2.0169
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2797 - loss: 2.0174
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 2.0179
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2794 - loss: 2.0183
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2791 - loss: 2.0189
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 2.0193
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2787 - loss: 2.0196
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2785 - loss: 2.0198
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2784 - loss: 2.0199
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2782 - loss: 2.0200
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2780 - loss: 2.0201
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2779 - loss: 2.0203
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2778 - loss: 2.0203
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2777 - loss: 2.0203
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 2.0204
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 2.0204
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2774 - loss: 2.0205 - val_accuracy: 0.2564 - val_loss: 2.0173
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5000 - loss: 1.6038
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3324 - loss: 1.8542  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3082 - loss: 1.9159
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2996 - loss: 1.9416
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2950 - loss: 1.9544
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2917 - loss: 1.9627
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2897 - loss: 1.9680
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2879 - loss: 1.9726
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2861 - loss: 1.9772
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2846 - loss: 1.9806
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2836 - loss: 1.9832
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2829 - loss: 1.9849
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2824 - loss: 1.9863
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2818 - loss: 1.9876
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2814 - loss: 1.9887
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9893
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2809 - loss: 1.9903
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2807 - loss: 1.9913
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 1.9922
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2803 - loss: 1.9931
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 1.9940
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 1.9949
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2797 - loss: 1.9957
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 1.9964
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2794 - loss: 1.9972
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2792 - loss: 1.9977
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2791 - loss: 1.9981
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9986
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2788 - loss: 1.9990
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2786 - loss: 1.9993
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2786 - loss: 1.9994 - val_accuracy: 0.2437 - val_loss: 2.0075
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.9779
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2478 - loss: 2.0525  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2485 - loss: 2.0502
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2507 - loss: 2.0522
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2532 - loss: 2.0522
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2558 - loss: 2.0500
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0499
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2582 - loss: 2.0492
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2587 - loss: 2.0480
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2595 - loss: 2.0462
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0444
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0428
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2617 - loss: 2.0411
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2622 - loss: 2.0398
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2628 - loss: 2.0386
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2632 - loss: 2.0374
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0360
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0350
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0339
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0330
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2648 - loss: 2.0321
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0314
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2654 - loss: 2.0305
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0296
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0287
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0279
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0270
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0260
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0251
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0243
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2678 - loss: 2.0241 - val_accuracy: 0.2574 - val_loss: 2.0183
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 1.9214
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2644 - loss: 1.9366  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2609 - loss: 1.9564
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2632 - loss: 1.9663
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2653 - loss: 1.9718
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2679 - loss: 1.9745
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2700 - loss: 1.9754
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2720 - loss: 1.9760
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2730 - loss: 1.9774
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2739 - loss: 1.9782
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2749 - loss: 1.9787
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2757 - loss: 1.9796
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2766 - loss: 1.9803
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2774 - loss: 1.9808
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2782 - loss: 1.9811
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2788 - loss: 1.9813
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2792 - loss: 1.9815
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9818
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 1.9821
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2800 - loss: 1.9825
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2802 - loss: 1.9830
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2803 - loss: 1.9834
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 1.9837
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 1.9841
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 1.9844
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 1.9848
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 1.9852
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 1.9856
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 1.9860
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2807 - loss: 1.9864
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2807 - loss: 1.9866 - val_accuracy: 0.2662 - val_loss: 2.0229
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.0634
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2938 - loss: 2.0143  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2877 - loss: 2.0129
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2869 - loss: 2.0050
[1m 168/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2864 - loss: 2.0012
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2861 - loss: 1.9975
[1m 251/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2854 - loss: 1.9958
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2847 - loss: 1.9952
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2840 - loss: 1.9950
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2835 - loss: 1.9947
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2832 - loss: 1.9946
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2830 - loss: 1.9945
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2828 - loss: 1.9946
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2825 - loss: 1.9949
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2824 - loss: 1.9951
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2822 - loss: 1.9951
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2821 - loss: 1.9952
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2819 - loss: 1.9956
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2817 - loss: 1.9960
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2815 - loss: 1.9964
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2814 - loss: 1.9967
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2813 - loss: 1.9970
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9972
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9973
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9974
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9974
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9975
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9975
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9974
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2813 - loss: 1.9974
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2813 - loss: 1.9974 - val_accuracy: 0.2659 - val_loss: 1.9900
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.0472
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3094 - loss: 1.9322  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2955 - loss: 1.9557
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2882 - loss: 1.9664
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2853 - loss: 1.9717
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2839 - loss: 1.9740
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2827 - loss: 1.9762
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2825 - loss: 1.9783
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2824 - loss: 1.9807
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2822 - loss: 1.9823
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2818 - loss: 1.9834
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2813 - loss: 1.9841
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9843
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9842
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9841
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 1.9839
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9836
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9832
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9829
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2813 - loss: 1.9825
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2813 - loss: 1.9823
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2814 - loss: 1.9821
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2815 - loss: 1.9820
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2815 - loss: 1.9818
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2816 - loss: 1.9816
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2817 - loss: 1.9814
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2818 - loss: 1.9812
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2819 - loss: 1.9810
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2819 - loss: 1.9808
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2820 - loss: 1.9807
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2821 - loss: 1.9807 - val_accuracy: 0.2659 - val_loss: 1.9860
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5625 - loss: 1.7278
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3315 - loss: 1.8833  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3289 - loss: 1.8988
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3283 - loss: 1.9091
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3265 - loss: 1.9132
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3242 - loss: 1.9157
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3201 - loss: 1.9210
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3165 - loss: 1.9249
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3135 - loss: 1.9278
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3111 - loss: 1.9298
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3092 - loss: 1.9315
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3077 - loss: 1.9332
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3061 - loss: 1.9350
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3048 - loss: 1.9366
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3037 - loss: 1.9381
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3028 - loss: 1.9395
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3020 - loss: 1.9410
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3012 - loss: 1.9424
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3005 - loss: 1.9436
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2998 - loss: 1.9447
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2991 - loss: 1.9458
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2985 - loss: 1.9467
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2979 - loss: 1.9476
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2973 - loss: 1.9484
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2969 - loss: 1.9491
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2964 - loss: 1.9497
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2960 - loss: 1.9503
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2957 - loss: 1.9509
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2953 - loss: 1.9514
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2950 - loss: 1.9520
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2949 - loss: 1.9522 - val_accuracy: 0.2601 - val_loss: 2.0021
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.1622
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2765 - loss: 1.9539  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2868 - loss: 1.9531
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2881 - loss: 1.9556
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2885 - loss: 1.9540
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2890 - loss: 1.9501
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2895 - loss: 1.9481
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2897 - loss: 1.9467
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2898 - loss: 1.9461
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2898 - loss: 1.9457
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2899 - loss: 1.9459
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2900 - loss: 1.9465
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2900 - loss: 1.9473
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2901 - loss: 1.9478
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2903 - loss: 1.9482
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2905 - loss: 1.9487
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2906 - loss: 1.9494
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2906 - loss: 1.9503
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2906 - loss: 1.9512
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2905 - loss: 1.9520
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2905 - loss: 1.9527
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2904 - loss: 1.9533
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2904 - loss: 1.9539
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2903 - loss: 1.9543
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2902 - loss: 1.9547
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2901 - loss: 1.9549
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2900 - loss: 1.9552
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2899 - loss: 1.9556
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2899 - loss: 1.9559
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2898 - loss: 1.9562
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2897 - loss: 1.9564 - val_accuracy: 0.2699 - val_loss: 1.9736

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 606ms/step
[1m61/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 842us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7:55[0m 816ms/step
[1m 64/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 796us/step  
[1m137/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 740us/step
[1m209/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 725us/step
[1m279/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 724us/step
[1m354/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 714us/step
[1m424/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 714us/step
[1m496/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 712us/step
[1m570/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 707us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m70/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 731us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 65/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 792us/step
[1m133/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 764us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 26.03 [%]
Global F1 score (validation) = 23.47 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.16498946 0.15757588 0.14489302 ... 0.00511023 0.10135334 0.01601501]
 [0.19686158 0.17879094 0.15694706 ... 0.00210658 0.13773413 0.0147569 ]
 [0.16735736 0.14789283 0.13962825 ... 0.00252469 0.11108832 0.0144023 ]
 ...
 [0.20249704 0.18251596 0.17252806 ... 0.00139149 0.11876857 0.02462324]
 [0.09083767 0.09997108 0.07407612 ... 0.01760993 0.06272818 0.01262802]
 [0.13669807 0.18472953 0.11795731 ... 0.00790252 0.11223668 0.01684637]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 31.5 [%]
Global accuracy score (test) = 26.82 [%]
Global F1 score (train) = 28.37 [%]
Global F1 score (test) = 23.37 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.19      0.42      0.26       184
 CAMINAR CON MÓVIL O LIBRO       0.19      0.26      0.22       184
       CAMINAR USUAL SPEED       0.17      0.02      0.04       184
            CAMINAR ZIGZAG       0.17      0.02      0.04       184
          DE PIE BARRIENDO       0.18      0.45      0.26       184
   DE PIE DOBLANDO TOALLAS       0.12      0.07      0.09       184
    DE PIE MOVIENDO LIBROS       0.25      0.24      0.25       184
          DE PIE USANDO PC       0.27      0.81      0.40       184
        FASE REPOSO CON K5       0.61      0.62      0.61       184
INCREMENTAL CICLOERGOMETRO       0.48      0.20      0.28       184
           SENTADO LEYENDO       0.06      0.03      0.04       184
         SENTADO USANDO PC       0.08      0.02      0.03       184
      SENTADO VIENDO LA TV       0.41      0.48      0.44       184
   SUBIR Y BAJAR ESCALERAS       0.13      0.02      0.04       184
                    TROTAR       0.93      0.35      0.51       161

                  accuracy                           0.27      2737
                 macro avg       0.28      0.27      0.23      2737
              weighted avg       0.28      0.27      0.23      2737


Accuracy capturado en la ejecución 21: 26.82 [%]
F1-score capturado en la ejecución 21: 23.37 [%]

=== EJECUCIÓN 22 ===

--- TRAIN (ejecución 22) ---

--- TEST (ejecución 22) ---
2025-11-07 14:30:19.714681: 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 14:30:19.726167: 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 00:00:1762522219.739273 2990363 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762522219.743357 2990363 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762522219.753072 2990363 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522219.753088 2990363 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522219.753089 2990363 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522219.753091 2990363 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:30:19.756214: 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 00:00:1762522222.022827 2990363 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762522223.522476 2990495 service.cc:152] XLA service 0x74decc00c780 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762522223.522522 2990495 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:30:23.553821: 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 00:00:1762522223.697310 2990495 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762522225.072783 2990495 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46:47[0m 2s/step - accuracy: 0.1250 - loss: 2.8214
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0603 - loss: 3.2629  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0668 - loss: 3.2535
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0697 - loss: 3.2406
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0714 - loss: 3.2333
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0727 - loss: 3.2258
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0736 - loss: 3.2187
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0741 - loss: 3.2130
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0748 - loss: 3.2076
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0757 - loss: 3.2013
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0766 - loss: 3.1953
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0777 - loss: 3.1885
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0785 - loss: 3.1829
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0793 - loss: 3.1771
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0800 - loss: 3.1712
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0805 - loss: 3.1654
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0811 - loss: 3.1600
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0817 - loss: 3.1542
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0822 - loss: 3.1494
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0828 - loss: 3.1434
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0833 - loss: 3.1381
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0838 - loss: 3.1323
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0843 - loss: 3.1266
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0847 - loss: 3.1222
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0851 - loss: 3.1165
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0856 - loss: 3.1112
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0860 - loss: 3.1064
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0865 - loss: 3.1010
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0869 - loss: 3.0961
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0873 - loss: 3.0918
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0873 - loss: 3.0917 - val_accuracy: 0.1641 - val_loss: 2.5981
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0000e+00 - loss: 2.8364
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1081 - loss: 2.6933      
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1138 - loss: 2.7068
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1191 - loss: 2.7038
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1214 - loss: 2.6999
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1227 - loss: 2.6973
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1233 - loss: 2.6950
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1240 - loss: 2.6933
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1247 - loss: 2.6920
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1251 - loss: 2.6909
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1255 - loss: 2.6901
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1258 - loss: 2.6890
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1261 - loss: 2.6879
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1266 - loss: 2.6863
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1272 - loss: 2.6846
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1277 - loss: 2.6829
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1282 - loss: 2.6814
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1285 - loss: 2.6797
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1289 - loss: 2.6782
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1293 - loss: 2.6764
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1296 - loss: 2.6748
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1300 - loss: 2.6731
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1304 - loss: 2.6714
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1308 - loss: 2.6697
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1312 - loss: 2.6681
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1315 - loss: 2.6665
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1319 - loss: 2.6649
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1323 - loss: 2.6632
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1327 - loss: 2.6615
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1330 - loss: 2.6600
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1331 - loss: 2.6599 - val_accuracy: 0.1933 - val_loss: 2.4676
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 2.4643
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2155 - loss: 2.5109  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1941 - loss: 2.5215
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1841 - loss: 2.5262
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1785 - loss: 2.5269
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1750 - loss: 2.5271
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1730 - loss: 2.5256
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1725 - loss: 2.5238
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1725 - loss: 2.5221
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1727 - loss: 2.5204
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1729 - loss: 2.5189
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1730 - loss: 2.5179
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1730 - loss: 2.5168
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1732 - loss: 2.5154
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1734 - loss: 2.5144
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1734 - loss: 2.5134
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1736 - loss: 2.5122
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1737 - loss: 2.5111
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1738 - loss: 2.5102
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1740 - loss: 2.5093
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1741 - loss: 2.5084
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1743 - loss: 2.5075
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1745 - loss: 2.5066
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1747 - loss: 2.5057
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1748 - loss: 2.5048
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1750 - loss: 2.5039
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1751 - loss: 2.5029
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1752 - loss: 2.5021
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1754 - loss: 2.5012
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1755 - loss: 2.5003
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1755 - loss: 2.5002 - val_accuracy: 0.2011 - val_loss: 2.3782
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 2.1864
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2365 - loss: 2.3578  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2206 - loss: 2.3744
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2107 - loss: 2.3875
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2057 - loss: 2.3945
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2035 - loss: 2.3980
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2022 - loss: 2.3993
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2012 - loss: 2.3993
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2003 - loss: 2.3995
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1995 - loss: 2.3995
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1991 - loss: 2.3995
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1988 - loss: 2.3994
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1989 - loss: 2.3990
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1989 - loss: 2.3986
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1989 - loss: 2.3984
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1988 - loss: 2.3982
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1987 - loss: 2.3980
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1986 - loss: 2.3978
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1985 - loss: 2.3977
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1985 - loss: 2.3975
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1984 - loss: 2.3974
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1983 - loss: 2.3971
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1983 - loss: 2.3969
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1983 - loss: 2.3966
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1983 - loss: 2.3963
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1983 - loss: 2.3959
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1983 - loss: 2.3956
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1983 - loss: 2.3952
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1983 - loss: 2.3948
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1983 - loss: 2.3948 - val_accuracy: 0.2292 - val_loss: 2.2876
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.4325
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1830 - loss: 2.3454  
[1m  86/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1878 - loss: 2.3446
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1901 - loss: 2.3413
[1m 172/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1913 - loss: 2.3408
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1929 - loss: 2.3404
[1m 254/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1950 - loss: 2.3393
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1965 - loss: 2.3385
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1975 - loss: 2.3383
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1983 - loss: 2.3383
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1993 - loss: 2.3380
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2003 - loss: 2.3375
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2011 - loss: 2.3368
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2019 - loss: 2.3357
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2025 - loss: 2.3348
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2030 - loss: 2.3342
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2035 - loss: 2.3336
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2039 - loss: 2.3332
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2042 - loss: 2.3328
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2046 - loss: 2.3324
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2049 - loss: 2.3321
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2052 - loss: 2.3317
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2054 - loss: 2.3315
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2057 - loss: 2.3311
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2061 - loss: 2.3307
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2064 - loss: 2.3302
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2067 - loss: 2.3296
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2070 - loss: 2.3292
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2073 - loss: 2.3288
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2074 - loss: 2.3286 - val_accuracy: 0.2290 - val_loss: 2.2525
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 2.0304
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1928 - loss: 2.2623  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2021 - loss: 2.2643
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2029 - loss: 2.2715
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2020 - loss: 2.2780
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2027 - loss: 2.2803
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2030 - loss: 2.2819
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2033 - loss: 2.2828
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2038 - loss: 2.2830
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2042 - loss: 2.2834
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2046 - loss: 2.2838
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2052 - loss: 2.2837
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2057 - loss: 2.2835
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2062 - loss: 2.2832
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2066 - loss: 2.2829
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2070 - loss: 2.2825
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2073 - loss: 2.2823
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2076 - loss: 2.2820
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2079 - loss: 2.2817
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2081 - loss: 2.2814
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2084 - loss: 2.2810
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2086 - loss: 2.2807
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2088 - loss: 2.2804
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2090 - loss: 2.2802
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2091 - loss: 2.2799
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2093 - loss: 2.2796
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2094 - loss: 2.2794
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2095 - loss: 2.2792
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2096 - loss: 2.2791
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2097 - loss: 2.2789
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2097 - loss: 2.2789 - val_accuracy: 0.2233 - val_loss: 2.1743
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.2637
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1809 - loss: 2.2347  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1873 - loss: 2.2588
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1909 - loss: 2.2657
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1932 - loss: 2.2704
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1950 - loss: 2.2698
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1973 - loss: 2.2679
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1992 - loss: 2.2662
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2008 - loss: 2.2649
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2024 - loss: 2.2634
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2041 - loss: 2.2615
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2053 - loss: 2.2598
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2065 - loss: 2.2582
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2074 - loss: 2.2568
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2084 - loss: 2.2556
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2093 - loss: 2.2546
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2101 - loss: 2.2536
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2108 - loss: 2.2528
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2115 - loss: 2.2520
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2120 - loss: 2.2514
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2125 - loss: 2.2508
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2130 - loss: 2.2502
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2135 - loss: 2.2496
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2138 - loss: 2.2491
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2141 - loss: 2.2486
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2145 - loss: 2.2481
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2148 - loss: 2.2476
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2151 - loss: 2.2471
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2153 - loss: 2.2466
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2156 - loss: 2.2462
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2157 - loss: 2.2459 - val_accuracy: 0.2292 - val_loss: 2.1577
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.1875 - loss: 2.3405
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2427 - loss: 2.1803  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2347 - loss: 2.1858
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2339 - loss: 2.1875
[1m 168/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2340 - loss: 2.1896
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2342 - loss: 2.1901
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2342 - loss: 2.1911
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2341 - loss: 2.1925
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2339 - loss: 2.1938
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2339 - loss: 2.1947
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2339 - loss: 2.1951
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2338 - loss: 2.1956
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2337 - loss: 2.1960
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2336 - loss: 2.1962
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2335 - loss: 2.1962
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2334 - loss: 2.1963
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2331 - loss: 2.1965
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2329 - loss: 2.1968
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2327 - loss: 2.1971
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2325 - loss: 2.1973
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2323 - loss: 2.1975
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2322 - loss: 2.1977
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2321 - loss: 2.1979
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2319 - loss: 2.1980
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2318 - loss: 2.1981
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2316 - loss: 2.1981
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2315 - loss: 2.1982
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2314 - loss: 2.1982
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2313 - loss: 2.1982
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2312 - loss: 2.1982 - val_accuracy: 0.2315 - val_loss: 2.1284
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.2604
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2352 - loss: 2.1484  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2401 - loss: 2.1549
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2407 - loss: 2.1618
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2411 - loss: 2.1651
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2418 - loss: 2.1668
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2421 - loss: 2.1690
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2422 - loss: 2.1712
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1730
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2417 - loss: 2.1743
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2413 - loss: 2.1758
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2408 - loss: 2.1773
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2405 - loss: 2.1784
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2402 - loss: 2.1792
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2400 - loss: 2.1797
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2398 - loss: 2.1802
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2396 - loss: 2.1806
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2393 - loss: 2.1810
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2391 - loss: 2.1812
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2390 - loss: 2.1814
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2389 - loss: 2.1816
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2388 - loss: 2.1816
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2388 - loss: 2.1814
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2387 - loss: 2.1813
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2386 - loss: 2.1810
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2386 - loss: 2.1808
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2386 - loss: 2.1806
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2385 - loss: 2.1805
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2385 - loss: 2.1804
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2384 - loss: 2.1804
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2383 - loss: 2.1804 - val_accuracy: 0.2313 - val_loss: 2.1111
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.3244
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2416 - loss: 2.1271  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1298
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2427 - loss: 2.1315
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2443 - loss: 2.1322
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2447 - loss: 2.1324
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2440 - loss: 2.1342
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2430 - loss: 2.1374
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2421 - loss: 2.1403
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2416 - loss: 2.1423
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2412 - loss: 2.1435
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2408 - loss: 2.1447
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2406 - loss: 2.1459
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2406 - loss: 2.1469
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2407 - loss: 2.1475
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2407 - loss: 2.1479
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2408 - loss: 2.1484
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2409 - loss: 2.1488
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2409 - loss: 2.1492
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2410 - loss: 2.1496
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2410 - loss: 2.1500
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2410 - loss: 2.1503
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2410 - loss: 2.1505
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2410 - loss: 2.1508
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2409 - loss: 2.1510
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2408 - loss: 2.1511
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2408 - loss: 2.1512
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2408 - loss: 2.1511
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2408 - loss: 2.1510
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2408 - loss: 2.1510 - val_accuracy: 0.2568 - val_loss: 2.0693
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.2500 - loss: 2.3379
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2315 - loss: 2.1828  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2233 - loss: 2.1634
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2243 - loss: 2.1480
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2264 - loss: 2.1403
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2273 - loss: 2.1364
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2278 - loss: 2.1347
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2286 - loss: 2.1326
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2294 - loss: 2.1311
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2301 - loss: 2.1303
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2308 - loss: 2.1298
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2314 - loss: 2.1293
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2321 - loss: 2.1287
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2327 - loss: 2.1282
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2335 - loss: 2.1275
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2344 - loss: 2.1270
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2350 - loss: 2.1267
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2355 - loss: 2.1264
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2360 - loss: 2.1262
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2363 - loss: 2.1260
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2367 - loss: 2.1258
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2371 - loss: 2.1256
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2375 - loss: 2.1254
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2378 - loss: 2.1253
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2382 - loss: 2.1251
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2385 - loss: 2.1249
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2389 - loss: 2.1247
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2392 - loss: 2.1246
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2395 - loss: 2.1244
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2397 - loss: 2.1243 - val_accuracy: 0.2605 - val_loss: 2.0543
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.2824
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2440 - loss: 2.1375  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2368 - loss: 2.1435
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2336 - loss: 2.1410
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2332 - loss: 2.1391
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2341 - loss: 2.1376
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2346 - loss: 2.1378
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2348 - loss: 2.1388
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2353 - loss: 2.1404
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2357 - loss: 2.1416
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2363 - loss: 2.1415
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2367 - loss: 2.1413
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2368 - loss: 2.1414
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2370 - loss: 2.1412
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2373 - loss: 2.1407
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2376 - loss: 2.1404
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2377 - loss: 2.1401
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2378 - loss: 2.1398
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2380 - loss: 2.1394
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2381 - loss: 2.1391
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2383 - loss: 2.1387
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2384 - loss: 2.1384
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2386 - loss: 2.1380
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2388 - loss: 2.1375
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2389 - loss: 2.1370
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2390 - loss: 2.1364
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2392 - loss: 2.1358
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2393 - loss: 2.1352
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2394 - loss: 2.1347
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2396 - loss: 2.1341
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2396 - loss: 2.1339 - val_accuracy: 0.2720 - val_loss: 2.0511
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.2500 - loss: 2.0268
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2519 - loss: 2.1148  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2530 - loss: 2.1084
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2532 - loss: 2.1026
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2501 - loss: 2.1028
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2490 - loss: 2.1016
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2491 - loss: 2.1003
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2491 - loss: 2.0993
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2494 - loss: 2.0985
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2497 - loss: 2.0982
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.0979
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2505 - loss: 2.0974
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2507 - loss: 2.0971
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2508 - loss: 2.0971
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2508 - loss: 2.0972
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2507 - loss: 2.0973
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2506 - loss: 2.0975
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2505 - loss: 2.0977
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2504 - loss: 2.0977
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2503 - loss: 2.0978
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2503 - loss: 2.0978
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.0978
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.0977
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.0977
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.0976
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.0976
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2503 - loss: 2.0975
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2503 - loss: 2.0975
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2503 - loss: 2.0974
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2503 - loss: 2.0973 - val_accuracy: 0.2612 - val_loss: 2.0522
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.7775
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2609 - loss: 2.0359  
[1m  71/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2555 - loss: 2.0521
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2555 - loss: 2.0633
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2566 - loss: 2.0672
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0715
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2569 - loss: 2.0752
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2565 - loss: 2.0777
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0796
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0804
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0807
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.0809
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2557 - loss: 2.0813
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2556 - loss: 2.0814
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2555 - loss: 2.0813
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2555 - loss: 2.0813
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2555 - loss: 2.0813
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2555 - loss: 2.0813
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2556 - loss: 2.0812
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2557 - loss: 2.0812
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2558 - loss: 2.0813
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.0813
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.0813
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0813
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0813
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0815
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0815
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2562 - loss: 2.0815
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2562 - loss: 2.0815
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2562 - loss: 2.0816
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2563 - loss: 2.0816 - val_accuracy: 0.2688 - val_loss: 2.0189
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.2124
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0922  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0657
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2737 - loss: 2.0562
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2730 - loss: 2.0529
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0519
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0527
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0537
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0556
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2654 - loss: 2.0573
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0590
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0604
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0611
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2627 - loss: 2.0618
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2623 - loss: 2.0624
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2619 - loss: 2.0629
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2617 - loss: 2.0632
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2615 - loss: 2.0635
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2613 - loss: 2.0639
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0642
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0643
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0644
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2607 - loss: 2.0647
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2606 - loss: 2.0650
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2605 - loss: 2.0652
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0655
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0658
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2600 - loss: 2.0661
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0663
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2598 - loss: 2.0664 - val_accuracy: 0.2590 - val_loss: 2.0059
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 1.8259
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0060  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0207
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2625 - loss: 2.0262
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2612 - loss: 2.0283
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2601 - loss: 2.0319
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2588 - loss: 2.0358
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2580 - loss: 2.0381
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2576 - loss: 2.0395
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0409
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.0415
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0418
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.0421
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2570 - loss: 2.0424
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0427
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0433
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0438
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0444
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2574 - loss: 2.0449
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2576 - loss: 2.0452
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.0455
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2580 - loss: 2.0458
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2581 - loss: 2.0461
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2583 - loss: 2.0464
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2584 - loss: 2.0467
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2584 - loss: 2.0470
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2585 - loss: 2.0473
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2585 - loss: 2.0476
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2586 - loss: 2.0479
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2587 - loss: 2.0482
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2587 - loss: 2.0482 - val_accuracy: 0.2605 - val_loss: 2.0213
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 2.1439
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0716  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2697 - loss: 2.0591
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0545
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0480
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0444
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0434
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0435
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0436
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0435
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2701 - loss: 2.0437
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 2.0441
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2691 - loss: 2.0448
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0455
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0459
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0461
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0461
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0462
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0462
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0463
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0463
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0462
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0461
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0460
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0459
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0458
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0456
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0455
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0454
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2664 - loss: 2.0454 - val_accuracy: 0.2751 - val_loss: 1.9898
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.5650
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2527 - loss: 2.0812  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2547 - loss: 2.0602
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0603
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2587 - loss: 2.0618
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0608
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2618 - loss: 2.0596
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2624 - loss: 2.0575
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2628 - loss: 2.0558
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0549
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2634 - loss: 2.0543
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0538
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2641 - loss: 2.0533
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0529
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2647 - loss: 2.0526
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2648 - loss: 2.0525
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0524
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2648 - loss: 2.0524
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0523
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0520
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0517
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0513
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0510
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0506
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0503
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0499
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0496
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0492
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0487
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2654 - loss: 2.0482 - val_accuracy: 0.2583 - val_loss: 2.0019
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5000 - loss: 1.7675
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2506 - loss: 2.0628  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2434 - loss: 2.0679
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2440 - loss: 2.0663
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2481 - loss: 2.0592
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2506 - loss: 2.0514
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2527 - loss: 2.0451
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2541 - loss: 2.0407
[1m 333/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2549 - loss: 2.0380
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2553 - loss: 2.0365
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2558 - loss: 2.0351
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2562 - loss: 2.0341
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0336
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0332
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.0328
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2582 - loss: 2.0323
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2586 - loss: 2.0319
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2589 - loss: 2.0316
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2591 - loss: 2.0314
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2593 - loss: 2.0312
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2596 - loss: 2.0309
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0306
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2601 - loss: 2.0303
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0300
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2606 - loss: 2.0298
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2608 - loss: 2.0294
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0290
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2613 - loss: 2.0286
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2615 - loss: 2.0283
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2616 - loss: 2.0282 - val_accuracy: 0.2638 - val_loss: 2.0025
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0947
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2991 - loss: 2.0158  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2896 - loss: 2.0059
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2846 - loss: 2.0092
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2810 - loss: 2.0168
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2784 - loss: 2.0204
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2762 - loss: 2.0224
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0231
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2738 - loss: 2.0231
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2730 - loss: 2.0227
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2723 - loss: 2.0220
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2719 - loss: 2.0217
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0212
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2714 - loss: 2.0208
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2712 - loss: 2.0203
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0198
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0194
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0190
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0186
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0183
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0180
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0177
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0175
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0172
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0168
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0165
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0162
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0160
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2712 - loss: 2.0157
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2712 - loss: 2.0154
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2712 - loss: 2.0154 - val_accuracy: 0.2838 - val_loss: 1.9805
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 2.0539
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0117  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2767 - loss: 1.9992
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2787 - loss: 1.9962
[1m 173/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2783 - loss: 1.9969
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2784 - loss: 1.9963
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2780 - loss: 1.9953
[1m 300/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2776 - loss: 1.9949
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2769 - loss: 1.9960
[1m 382/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2762 - loss: 1.9971
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2757 - loss: 1.9977
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2753 - loss: 1.9986
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2749 - loss: 1.9994
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2746 - loss: 2.0001
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2742 - loss: 2.0008
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0013
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2738 - loss: 2.0018
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0022
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2734 - loss: 2.0027
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0031
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0034
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0036
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0038
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2730 - loss: 2.0038
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2730 - loss: 2.0038
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2729 - loss: 2.0039
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2728 - loss: 2.0040
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2728 - loss: 2.0040
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2727 - loss: 2.0040
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2727 - loss: 2.0039 - val_accuracy: 0.2666 - val_loss: 1.9829
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.3125 - loss: 2.0384
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3041 - loss: 1.9818  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2949 - loss: 1.9928
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2884 - loss: 1.9965
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2842 - loss: 2.0001
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2817 - loss: 2.0015
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2800 - loss: 2.0017
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2783 - loss: 2.0027
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2769 - loss: 2.0042
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2760 - loss: 2.0052
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2754 - loss: 2.0053
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0051
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0047
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0040
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0032
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0025
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0019
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0015
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0014
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0013
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0012
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2743 - loss: 2.0011
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2743 - loss: 2.0010
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2742 - loss: 2.0008
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2741 - loss: 2.0006
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0005
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0004
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0002
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0000
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0000
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2740 - loss: 2.0000 - val_accuracy: 0.2612 - val_loss: 1.9767
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3125 - loss: 1.8235
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2583 - loss: 1.9921  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2587 - loss: 1.9994
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2612 - loss: 2.0017
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0015
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2654 - loss: 2.0018
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0017
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0015
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0020
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0024
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0023
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0019
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0010
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0002
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2686 - loss: 1.9993
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2689 - loss: 1.9983
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2691 - loss: 1.9975
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2693 - loss: 1.9968
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2695 - loss: 1.9962
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2698 - loss: 1.9955
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2700 - loss: 1.9949
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 1.9943
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2704 - loss: 1.9940
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2706 - loss: 1.9936
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 1.9933
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 1.9930
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 1.9927
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 1.9925
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2715 - loss: 1.9922
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 1.9920
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2718 - loss: 1.9918 - val_accuracy: 0.2655 - val_loss: 1.9727
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.1539
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2540 - loss: 2.1202  
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0625
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0310
[1m 149/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0159
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2720 - loss: 2.0066
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2724 - loss: 2.0022
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2731 - loss: 1.9987
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2734 - loss: 1.9970
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2732 - loss: 1.9965
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2731 - loss: 1.9960
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2731 - loss: 1.9959
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 1.9958
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2735 - loss: 1.9956
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 1.9955
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2739 - loss: 1.9952
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2741 - loss: 1.9949
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2743 - loss: 1.9947
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 1.9943
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2746 - loss: 1.9940
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 1.9936
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2749 - loss: 1.9934
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2750 - loss: 1.9932
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 1.9930
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2754 - loss: 1.9929
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2755 - loss: 1.9927
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2756 - loss: 1.9925
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2758 - loss: 1.9923
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 1.9922
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2760 - loss: 1.9921
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2761 - loss: 1.9919 - val_accuracy: 0.2746 - val_loss: 1.9840
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 1.9581
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2609 - loss: 1.9622  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2854 - loss: 1.9415
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2909 - loss: 1.9371
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2931 - loss: 1.9328
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2945 - loss: 1.9309
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2953 - loss: 1.9297
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2955 - loss: 1.9302
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2954 - loss: 1.9318
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2954 - loss: 1.9331
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2953 - loss: 1.9345
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2949 - loss: 1.9365
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2945 - loss: 1.9383
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2942 - loss: 1.9397
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2940 - loss: 1.9408
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2939 - loss: 1.9418
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2939 - loss: 1.9425
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2939 - loss: 1.9431
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2938 - loss: 1.9439
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2937 - loss: 1.9448
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2937 - loss: 1.9455
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2936 - loss: 1.9463
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2934 - loss: 1.9470
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2932 - loss: 1.9479
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2930 - loss: 1.9488
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2927 - loss: 1.9496
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2924 - loss: 1.9503
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2922 - loss: 1.9509
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2919 - loss: 1.9516
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2916 - loss: 1.9522
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2916 - loss: 1.9523 - val_accuracy: 0.2592 - val_loss: 1.9800

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 656ms/step
[1m63/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 812us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:06[0m 835ms/step
[1m 69/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 741us/step  
[1m140/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 724us/step
[1m208/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 729us/step
[1m279/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 724us/step
[1m352/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 717us/step
[1m424/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 714us/step
[1m499/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 707us/step
[1m567/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 711us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m68/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 747us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 76/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 668us/step
[1m147/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 690us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 26.99 [%]
Global F1 score (validation) = 23.2 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.14080957 0.18123293 0.18031533 ... 0.00216138 0.16218409 0.02391532]
 [0.16527455 0.22909708 0.11371314 ... 0.00098725 0.21474832 0.0255783 ]
 [0.07771745 0.09646031 0.08135594 ... 0.01204278 0.06898528 0.00792141]
 ...
 [0.19844852 0.16367023 0.13448055 ... 0.00251769 0.16258515 0.02726429]
 [0.17336197 0.1818504  0.14719318 ... 0.00241616 0.16541667 0.02320942]
 [0.0714826  0.07629859 0.06328822 ... 0.01076219 0.05343363 0.00743086]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 29.34 [%]
Global accuracy score (test) = 22.54 [%]
Global F1 score (train) = 26.25 [%]
Global F1 score (test) = 19.86 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.02      0.01      0.01       184
 CAMINAR CON MÓVIL O LIBRO       0.17      0.23      0.20       184
       CAMINAR USUAL SPEED       0.33      0.02      0.03       184
            CAMINAR ZIGZAG       0.14      0.26      0.18       184
          DE PIE BARRIENDO       0.15      0.42      0.22       184
   DE PIE DOBLANDO TOALLAS       0.13      0.12      0.12       184
    DE PIE MOVIENDO LIBROS       0.18      0.10      0.13       184
          DE PIE USANDO PC       0.25      0.76      0.38       184
        FASE REPOSO CON K5       0.93      0.50      0.65       184
INCREMENTAL CICLOERGOMETRO       0.76      0.09      0.16       184
           SENTADO LEYENDO       0.00      0.00      0.00       184
         SENTADO USANDO PC       0.00      0.00      0.00       184
      SENTADO VIENDO LA TV       0.25      0.49      0.33       184
   SUBIR Y BAJAR ESCALERAS       0.24      0.13      0.17       184
                    TROTAR       0.86      0.27      0.41       161

                  accuracy                           0.23      2737
                 macro avg       0.29      0.23      0.20      2737
              weighted avg       0.29      0.23      0.20      2737


Accuracy capturado en la ejecución 22: 22.54 [%]
F1-score capturado en la ejecución 22: 19.86 [%]

=== EJECUCIÓN 23 ===

--- TRAIN (ejecución 23) ---

--- TEST (ejecución 23) ---
2025-11-07 14:31:26.874351: 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 14:31:26.885621: 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 00:00:1762522286.898611 2994086 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762522286.903001 2994086 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762522286.913174 2994086 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522286.913191 2994086 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522286.913193 2994086 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522286.913195 2994086 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:31:26.916546: 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 00:00:1762522289.185161 2994086 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762522290.684318 2994214 service.cc:152] XLA service 0x7576f8004060 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762522290.684343 2994214 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:31:30.710961: 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 00:00:1762522290.855380 2994214 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762522292.249344 2994214 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47:02[0m 2s/step - accuracy: 0.0000e+00 - loss: 3.8004
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0503 - loss: 3.2882      
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0507 - loss: 3.2670
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0539 - loss: 3.2540
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0557 - loss: 3.2426
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0573 - loss: 3.2321
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0592 - loss: 3.2220
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0608 - loss: 3.2126
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0622 - loss: 3.2042
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0636 - loss: 3.1957
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0650 - loss: 3.1878
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0663 - loss: 3.1799
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0674 - loss: 3.1725
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0685 - loss: 3.1654
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0695 - loss: 3.1590
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0706 - loss: 3.1518
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0715 - loss: 3.1448
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0726 - loss: 3.1373
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0736 - loss: 3.1308
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0745 - loss: 3.1247
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0754 - loss: 3.1186
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0763 - loss: 3.1126
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0770 - loss: 3.1072
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0778 - loss: 3.1018
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0786 - loss: 3.0966
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0793 - loss: 3.0912
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0800 - loss: 3.0860
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0807 - loss: 3.0811
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0814 - loss: 3.0764
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0814 - loss: 3.0763 - val_accuracy: 0.1697 - val_loss: 2.6069
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.0625 - loss: 3.0454
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1387 - loss: 2.7708  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1319 - loss: 2.7810
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1295 - loss: 2.7821
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1290 - loss: 2.7804
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1280 - loss: 2.7779
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1270 - loss: 2.7758
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1262 - loss: 2.7741
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1258 - loss: 2.7725
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1255 - loss: 2.7715
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1252 - loss: 2.7701
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1250 - loss: 2.7686
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1248 - loss: 2.7669
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1246 - loss: 2.7654
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1245 - loss: 2.7635
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1245 - loss: 2.7618
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1246 - loss: 2.7599
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1246 - loss: 2.7581
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1247 - loss: 2.7566
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1248 - loss: 2.7549
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1250 - loss: 2.7533
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1252 - loss: 2.7516
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1254 - loss: 2.7498
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1256 - loss: 2.7480
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1259 - loss: 2.7461
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1261 - loss: 2.7443
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1264 - loss: 2.7425
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1266 - loss: 2.7409
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1268 - loss: 2.7393
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1269 - loss: 2.7385 - val_accuracy: 0.1741 - val_loss: 2.5136
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.0000e+00 - loss: 2.7514
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1189 - loss: 2.6151      
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1333 - loss: 2.6137
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1364 - loss: 2.6102
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1387 - loss: 2.6054
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1394 - loss: 2.6034
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1397 - loss: 2.6017
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1403 - loss: 2.6005
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1409 - loss: 2.5993
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1416 - loss: 2.5984
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1423 - loss: 2.5981
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1429 - loss: 2.5973
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1436 - loss: 2.5963
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1443 - loss: 2.5951
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1449 - loss: 2.5940
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1455 - loss: 2.5927
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1461 - loss: 2.5916
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1466 - loss: 2.5904
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1472 - loss: 2.5892
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1477 - loss: 2.5881
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1482 - loss: 2.5869
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1487 - loss: 2.5858
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1491 - loss: 2.5846
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1495 - loss: 2.5835
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1498 - loss: 2.5825
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1501 - loss: 2.5815
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1504 - loss: 2.5804
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1507 - loss: 2.5793
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1510 - loss: 2.5781
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1513 - loss: 2.5771 - val_accuracy: 0.1883 - val_loss: 2.4264
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.5778
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1423 - loss: 2.5435  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1519 - loss: 2.5270
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1568 - loss: 2.5192
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1603 - loss: 2.5130
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1625 - loss: 2.5089
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1640 - loss: 2.5062
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1652 - loss: 2.5037
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1662 - loss: 2.5014
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1671 - loss: 2.4993
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1677 - loss: 2.4978
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1684 - loss: 2.4962
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1688 - loss: 2.4949
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1693 - loss: 2.4936
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1697 - loss: 2.4926
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1701 - loss: 2.4918
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1704 - loss: 2.4910
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1707 - loss: 2.4903
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1709 - loss: 2.4896
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1711 - loss: 2.4889
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1713 - loss: 2.4883
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1715 - loss: 2.4875
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1718 - loss: 2.4868
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1720 - loss: 2.4859
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1722 - loss: 2.4852
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1723 - loss: 2.4845
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1725 - loss: 2.4837
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1727 - loss: 2.4829
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1729 - loss: 2.4822
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1731 - loss: 2.4814
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1731 - loss: 2.4813 - val_accuracy: 0.2159 - val_loss: 2.3552
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.6382
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1787 - loss: 2.4388  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1818 - loss: 2.4310
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1814 - loss: 2.4308
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1829 - loss: 2.4279
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1844 - loss: 2.4235
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1860 - loss: 2.4189
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1875 - loss: 2.4150
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1886 - loss: 2.4120
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1895 - loss: 2.4094
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1902 - loss: 2.4074
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1907 - loss: 2.4060
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1912 - loss: 2.4047
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1916 - loss: 2.4037
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1920 - loss: 2.4026
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1923 - loss: 2.4016
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1924 - loss: 2.4009
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1925 - loss: 2.4003
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1925 - loss: 2.3998
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1925 - loss: 2.3992
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1925 - loss: 2.3987
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1926 - loss: 2.3980
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1926 - loss: 2.3975
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1927 - loss: 2.3968
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1927 - loss: 2.3962
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1927 - loss: 2.3957
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1928 - loss: 2.3952
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1928 - loss: 2.3947
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1929 - loss: 2.3941
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1930 - loss: 2.3936 - val_accuracy: 0.2255 - val_loss: 2.2947
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.3266
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2162 - loss: 2.3934  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2089 - loss: 2.3873
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2046 - loss: 2.3829
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2023 - loss: 2.3797
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2018 - loss: 2.3760
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2015 - loss: 2.3738
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2013 - loss: 2.3716
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2012 - loss: 2.3695
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2013 - loss: 2.3678
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2012 - loss: 2.3663
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2011 - loss: 2.3653
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2008 - loss: 2.3643
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2008 - loss: 2.3632
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2008 - loss: 2.3621
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2009 - loss: 2.3609
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2010 - loss: 2.3597
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2011 - loss: 2.3586
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2011 - loss: 2.3576
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2012 - loss: 2.3566
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2013 - loss: 2.3554
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2015 - loss: 2.3543
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2016 - loss: 2.3533
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2018 - loss: 2.3523
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2019 - loss: 2.3513
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2021 - loss: 2.3503
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2023 - loss: 2.3493
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2025 - loss: 2.3483
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2027 - loss: 2.3474
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2028 - loss: 2.3466 - val_accuracy: 0.2250 - val_loss: 2.2465
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.0625 - loss: 2.4636
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1988 - loss: 2.3247  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1991 - loss: 2.3187
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2015 - loss: 2.3117
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2041 - loss: 2.3082
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2068 - loss: 2.3063
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2090 - loss: 2.3052
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2105 - loss: 2.3043
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2118 - loss: 2.3028
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2129 - loss: 2.3011
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2136 - loss: 2.2999
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2142 - loss: 2.2988
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2149 - loss: 2.2976
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2154 - loss: 2.2965
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2159 - loss: 2.2957
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2164 - loss: 2.2951
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2167 - loss: 2.2946
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2169 - loss: 2.2942
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2171 - loss: 2.2939
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2173 - loss: 2.2935
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2175 - loss: 2.2931
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2177 - loss: 2.2927
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2179 - loss: 2.2923
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2180 - loss: 2.2918
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2182 - loss: 2.2913
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2183 - loss: 2.2909
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2184 - loss: 2.2904
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2185 - loss: 2.2899
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2186 - loss: 2.2894
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2187 - loss: 2.2890 - val_accuracy: 0.2374 - val_loss: 2.1983
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.2827
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2571 - loss: 2.2136  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2439 - loss: 2.2473
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2392 - loss: 2.2532
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2383 - loss: 2.2547
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2370 - loss: 2.2568
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2355 - loss: 2.2589
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2342 - loss: 2.2591
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2333 - loss: 2.2593
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2328 - loss: 2.2591
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2326 - loss: 2.2586
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2325 - loss: 2.2580
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2325 - loss: 2.2575
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2324 - loss: 2.2570
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2322 - loss: 2.2565
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2322 - loss: 2.2558
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2321 - loss: 2.2551
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2320 - loss: 2.2544
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2319 - loss: 2.2538
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2317 - loss: 2.2533
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2316 - loss: 2.2528
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2315 - loss: 2.2525
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2314 - loss: 2.2520
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2314 - loss: 2.2517
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2313 - loss: 2.2513
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2313 - loss: 2.2509
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2312 - loss: 2.2505
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2311 - loss: 2.2501
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2311 - loss: 2.2497
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2310 - loss: 2.2494
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2310 - loss: 2.2493 - val_accuracy: 0.2466 - val_loss: 2.1492
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.1323
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2123 - loss: 2.1748  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2142 - loss: 2.2018
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2167 - loss: 2.2174
[1m 168/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2195 - loss: 2.2222
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2213 - loss: 2.2253
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2223 - loss: 2.2281
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2228 - loss: 2.2301
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2236 - loss: 2.2312
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2246 - loss: 2.2312
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2254 - loss: 2.2309
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2263 - loss: 2.2303
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2271 - loss: 2.2295
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2279 - loss: 2.2285
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2285 - loss: 2.2279
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2290 - loss: 2.2273
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2294 - loss: 2.2268
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2299 - loss: 2.2262
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2303 - loss: 2.2257
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2307 - loss: 2.2251
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2310 - loss: 2.2246
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2312 - loss: 2.2240
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2315 - loss: 2.2235
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2317 - loss: 2.2229
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2319 - loss: 2.2223
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2321 - loss: 2.2218
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2323 - loss: 2.2214
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2324 - loss: 2.2209
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2325 - loss: 2.2205
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2326 - loss: 2.2201 - val_accuracy: 0.2468 - val_loss: 2.1279
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 1.9837
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2263 - loss: 2.1640  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2251 - loss: 2.1818
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2268 - loss: 2.1889
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2288 - loss: 2.1912
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2309 - loss: 2.1899
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2327 - loss: 2.1890
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2341 - loss: 2.1885
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2349 - loss: 2.1886
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2355 - loss: 2.1882
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2360 - loss: 2.1877
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2362 - loss: 2.1873
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2365 - loss: 2.1870
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2367 - loss: 2.1867
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2369 - loss: 2.1866
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2370 - loss: 2.1868
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2370 - loss: 2.1869
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2370 - loss: 2.1870
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2369 - loss: 2.1872
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2369 - loss: 2.1874
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2368 - loss: 2.1875
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2368 - loss: 2.1876
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2368 - loss: 2.1877
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2367 - loss: 2.1878
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2367 - loss: 2.1878
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2367 - loss: 2.1877
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2368 - loss: 2.1876
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2368 - loss: 2.1876
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2369 - loss: 2.1876
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2369 - loss: 2.1875 - val_accuracy: 0.2662 - val_loss: 2.0830
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.0748
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1911 - loss: 2.2217  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1978 - loss: 2.2239
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2046 - loss: 2.2177
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2090 - loss: 2.2135
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2137 - loss: 2.2084
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2171 - loss: 2.2048
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2200 - loss: 2.2008
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2223 - loss: 2.1975
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2241 - loss: 2.1951
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2254 - loss: 2.1933
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2266 - loss: 2.1909
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2277 - loss: 2.1884
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2286 - loss: 2.1864
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2294 - loss: 2.1846
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2302 - loss: 2.1831
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2309 - loss: 2.1817
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2316 - loss: 2.1804
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2322 - loss: 2.1792
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2329 - loss: 2.1782
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2336 - loss: 2.1771
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2342 - loss: 2.1760
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2347 - loss: 2.1751
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2352 - loss: 2.1744
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2356 - loss: 2.1737
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2360 - loss: 2.1731
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2363 - loss: 2.1725
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2365 - loss: 2.1721
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2368 - loss: 2.1716
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2371 - loss: 2.1711
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2371 - loss: 2.1710 - val_accuracy: 0.2760 - val_loss: 2.0522
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.3125
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2458 - loss: 2.1512  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2445 - loss: 2.1609
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2467 - loss: 2.1583
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2480 - loss: 2.1568
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2485 - loss: 2.1566
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2483 - loss: 2.1569
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2478 - loss: 2.1572
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2473 - loss: 2.1570
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2467 - loss: 2.1570
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2459 - loss: 2.1575
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2453 - loss: 2.1580
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2448 - loss: 2.1583
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2443 - loss: 2.1586
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2440 - loss: 2.1586
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2438 - loss: 2.1586
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2437 - loss: 2.1584
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2436 - loss: 2.1583
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2436 - loss: 2.1581
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2436 - loss: 2.1579
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2437 - loss: 2.1575
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2437 - loss: 2.1570
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2438 - loss: 2.1565
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2439 - loss: 2.1560
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2441 - loss: 2.1555
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2443 - loss: 2.1550
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2444 - loss: 2.1544
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2446 - loss: 2.1538
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2447 - loss: 2.1532
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2449 - loss: 2.1526
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2449 - loss: 2.1525 - val_accuracy: 0.2810 - val_loss: 2.0304
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 1.9770
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2799 - loss: 2.0214  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0700
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0889
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2645 - loss: 2.1016
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2631 - loss: 2.1069
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2622 - loss: 2.1107
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2616 - loss: 2.1125
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2613 - loss: 2.1133
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2610 - loss: 2.1148
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2606 - loss: 2.1164
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2603 - loss: 2.1178
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2601 - loss: 2.1185
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2598 - loss: 2.1189
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2594 - loss: 2.1194
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2591 - loss: 2.1197
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2588 - loss: 2.1200
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2584 - loss: 2.1203
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2582 - loss: 2.1206
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.1207
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2576 - loss: 2.1209
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2574 - loss: 2.1210
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2571 - loss: 2.1212
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.1212
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.1211
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.1210
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2564 - loss: 2.1209
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2562 - loss: 2.1207
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.1205
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2560 - loss: 2.1203 - val_accuracy: 0.2710 - val_loss: 2.0245
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.1706
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2691 - loss: 2.1215  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2674 - loss: 2.1191
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2644 - loss: 2.1194
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2613 - loss: 2.1225
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2590 - loss: 2.1252
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2577 - loss: 2.1264
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2563 - loss: 2.1276
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2554 - loss: 2.1281
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2550 - loss: 2.1280
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2547 - loss: 2.1273
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1268
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2539 - loss: 2.1262
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2535 - loss: 2.1255
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2533 - loss: 2.1251
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2532 - loss: 2.1247
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2531 - loss: 2.1242
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2530 - loss: 2.1235
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2530 - loss: 2.1228
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2530 - loss: 2.1220
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2529 - loss: 2.1214
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.1210
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2527 - loss: 2.1206
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2526 - loss: 2.1203
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2525 - loss: 2.1199
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2524 - loss: 2.1196
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2523 - loss: 2.1192
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2523 - loss: 2.1187
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2523 - loss: 2.1183
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2523 - loss: 2.1178 - val_accuracy: 0.2831 - val_loss: 1.9946
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0515
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2546 - loss: 2.0607  
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2534 - loss: 2.0790
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2518 - loss: 2.0945
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2509 - loss: 2.1072
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2496 - loss: 2.1142
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2498 - loss: 2.1157
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2506 - loss: 2.1165
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2512 - loss: 2.1172
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2515 - loss: 2.1167
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2520 - loss: 2.1157
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2525 - loss: 2.1147
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2530 - loss: 2.1138
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2534 - loss: 2.1132
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2538 - loss: 2.1126
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2542 - loss: 2.1120
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2546 - loss: 2.1115
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2549 - loss: 2.1109
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2551 - loss: 2.1101
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2553 - loss: 2.1095
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2555 - loss: 2.1088
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2556 - loss: 2.1082
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2557 - loss: 2.1076
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2558 - loss: 2.1071
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2558 - loss: 2.1066
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2558 - loss: 2.1062
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.1057
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.1053
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.1048
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2558 - loss: 2.1045 - val_accuracy: 0.2623 - val_loss: 2.0268
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.1822
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2318 - loss: 2.1343  
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2412 - loss: 2.1276
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2499 - loss: 2.1130
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2540 - loss: 2.1041
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2563 - loss: 2.1012
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2574 - loss: 2.0992
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2589 - loss: 2.0970
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2601 - loss: 2.0952
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0931
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2618 - loss: 2.0915
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2626 - loss: 2.0901
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2632 - loss: 2.0889
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0883
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0874
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2641 - loss: 2.0865
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2643 - loss: 2.0856
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0849
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0844
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0839
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0834
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0829
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0824
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0819
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0814
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0810
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0807
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2643 - loss: 2.0803
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2643 - loss: 2.0800
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0797
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2642 - loss: 2.0797 - val_accuracy: 0.2781 - val_loss: 1.9821
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.9618
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2723 - loss: 2.0701  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2730 - loss: 2.0712
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0771
[1m 169/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0803
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0803
[1m 253/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0787
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0771
[1m 333/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0762
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0756
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0747
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0738
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2683 - loss: 2.0728
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2684 - loss: 2.0722
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2685 - loss: 2.0720
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0719
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0718
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2688 - loss: 2.0717
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2688 - loss: 2.0713
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2690 - loss: 2.0708
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2692 - loss: 2.0703
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2695 - loss: 2.0697
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2697 - loss: 2.0692
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0688
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0683
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0679
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2701 - loss: 2.0677
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2701 - loss: 2.0674
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0672
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2703 - loss: 2.0670 - val_accuracy: 0.2936 - val_loss: 1.9840
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.6221
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0663  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0387
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0410
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0447
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0464
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2646 - loss: 2.0464
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0464
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0462
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2654 - loss: 2.0466
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2654 - loss: 2.0465
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2654 - loss: 2.0466
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0465
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0464
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0464
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0464
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0465
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0466
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0467
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0467
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0468
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0468
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0468
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0468
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0469
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0469
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0469
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0469
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0469
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2653 - loss: 2.0469 - val_accuracy: 0.3025 - val_loss: 1.9618
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.2592
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2609 - loss: 2.1249  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2648 - loss: 2.0938
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2634 - loss: 2.0800
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0715
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0684
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2635 - loss: 2.0656
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0635
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0615
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2634 - loss: 2.0592
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2632 - loss: 2.0572
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0557
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0547
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0539
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2629 - loss: 2.0533
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0525
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0518
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2632 - loss: 2.0509
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0502
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2635 - loss: 2.0495
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0488
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2638 - loss: 2.0482
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2640 - loss: 2.0475
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2643 - loss: 2.0467
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0461
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0456
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2647 - loss: 2.0450
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2648 - loss: 2.0446
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0442
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2649 - loss: 2.0439
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2650 - loss: 2.0438 - val_accuracy: 0.2877 - val_loss: 1.9540
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.4375 - loss: 1.5947
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2702 - loss: 1.8953  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2731 - loss: 1.9447
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2762 - loss: 1.9649
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2765 - loss: 1.9731
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2768 - loss: 1.9786
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2765 - loss: 1.9829
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2764 - loss: 1.9861
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2760 - loss: 1.9896
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 1.9917
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 1.9934
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2758 - loss: 1.9951
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2757 - loss: 1.9965
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2755 - loss: 1.9979
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2754 - loss: 1.9991
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0003
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0013
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0019
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0027
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0033
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0039
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0045
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0053
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0058
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2746 - loss: 2.0064
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0070
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0076
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2743 - loss: 2.0081
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2742 - loss: 2.0087
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2742 - loss: 2.0089 - val_accuracy: 0.2918 - val_loss: 1.9464
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3750 - loss: 1.8958
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2960 - loss: 2.0179  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2926 - loss: 2.0168
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2899 - loss: 2.0139
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2876 - loss: 2.0147
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2861 - loss: 2.0149
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2855 - loss: 2.0139
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2851 - loss: 2.0127
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2852 - loss: 2.0116
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2851 - loss: 2.0103
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2848 - loss: 2.0094
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2846 - loss: 2.0087
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2844 - loss: 2.0083
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2840 - loss: 2.0082
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2835 - loss: 2.0081
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2831 - loss: 2.0082
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2828 - loss: 2.0082
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2825 - loss: 2.0084
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2822 - loss: 2.0085
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2820 - loss: 2.0086
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2817 - loss: 2.0088
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2813 - loss: 2.0090
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 2.0092
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2807 - loss: 2.0094
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 2.0097
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 2.0099
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 2.0101
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 2.0103
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2794 - loss: 2.0105
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2793 - loss: 2.0106
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2792 - loss: 2.0107 - val_accuracy: 0.2816 - val_loss: 1.9578
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.3750 - loss: 1.9387
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3162 - loss: 1.9321  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3054 - loss: 1.9730
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2984 - loss: 1.9906
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2926 - loss: 2.0005
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2880 - loss: 2.0062
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2849 - loss: 2.0092
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2833 - loss: 2.0111
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2822 - loss: 2.0120
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2814 - loss: 2.0123
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 2.0123
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2807 - loss: 2.0121
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 2.0122
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 2.0123
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2800 - loss: 2.0119
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 2.0112
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2802 - loss: 2.0106
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2802 - loss: 2.0099
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2802 - loss: 2.0094
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 2.0091
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2800 - loss: 2.0088
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 2.0085
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 2.0082
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2798 - loss: 2.0080
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2797 - loss: 2.0079
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 2.0077
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 2.0075
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 2.0073
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2795 - loss: 2.0071 - val_accuracy: 0.2873 - val_loss: 1.9584
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.4391
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2634 - loss: 2.0467  
[1m  71/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2592 - loss: 2.0310
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2615 - loss: 2.0199
[1m 150/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2628 - loss: 2.0138
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2647 - loss: 2.0089
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0046
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0017
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2679 - loss: 1.9995
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2690 - loss: 1.9980
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2698 - loss: 1.9973
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 1.9972
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2706 - loss: 1.9973
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 1.9974
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 1.9975
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 1.9978
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2719 - loss: 1.9980
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2723 - loss: 1.9982
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2726 - loss: 1.9983
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2730 - loss: 1.9984
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2733 - loss: 1.9984
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 1.9983
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2739 - loss: 1.9981
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2743 - loss: 1.9979
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 1.9976
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2751 - loss: 1.9974
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2754 - loss: 1.9972
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2758 - loss: 1.9971
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 1.9970
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2764 - loss: 1.9968
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2764 - loss: 1.9968 - val_accuracy: 0.2881 - val_loss: 1.9384
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 20ms/step - accuracy: 0.2500 - loss: 2.0426
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2985 - loss: 1.9682  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2954 - loss: 1.9652
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2947 - loss: 1.9704
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2936 - loss: 1.9749
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2925 - loss: 1.9775
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2911 - loss: 1.9788
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2896 - loss: 1.9797
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2880 - loss: 1.9809
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2870 - loss: 1.9816
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2864 - loss: 1.9823
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2862 - loss: 1.9822
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2860 - loss: 1.9821
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2858 - loss: 1.9820
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2857 - loss: 1.9820
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2856 - loss: 1.9822
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2855 - loss: 1.9824
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2855 - loss: 1.9825
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2856 - loss: 1.9826
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2856 - loss: 1.9827
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2856 - loss: 1.9828
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2855 - loss: 1.9830
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2854 - loss: 1.9831
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2852 - loss: 1.9833
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2851 - loss: 1.9834
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2850 - loss: 1.9835
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2848 - loss: 1.9835
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2847 - loss: 1.9836
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2846 - loss: 1.9837
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2845 - loss: 1.9838
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2845 - loss: 1.9838 - val_accuracy: 0.2623 - val_loss: 1.9802
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.1720
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2472 - loss: 2.0464  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2622 - loss: 2.0360
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2695 - loss: 2.0274
[1m 168/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2757 - loss: 2.0159
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2791 - loss: 2.0088
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2815 - loss: 2.0039
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2831 - loss: 2.0010
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2841 - loss: 1.9990
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2849 - loss: 1.9970
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2855 - loss: 1.9952
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2858 - loss: 1.9941
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2860 - loss: 1.9931
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2862 - loss: 1.9923
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2863 - loss: 1.9917
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2864 - loss: 1.9911
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2867 - loss: 1.9903
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2869 - loss: 1.9895
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2871 - loss: 1.9889
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2872 - loss: 1.9883
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2873 - loss: 1.9878
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2873 - loss: 1.9874
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2874 - loss: 1.9870
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2874 - loss: 1.9866
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2874 - loss: 1.9863
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2874 - loss: 1.9861
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2874 - loss: 1.9859
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2874 - loss: 1.9857
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2874 - loss: 1.9854
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2874 - loss: 1.9853 - val_accuracy: 0.2857 - val_loss: 1.9513

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 640ms/step
[1m64/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 800us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7:50[0m 807ms/step
[1m 63/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 814us/step  
[1m138/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 736us/step
[1m209/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 728us/step
[1m279/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 725us/step
[1m348/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 726us/step
[1m415/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 731us/step
[1m484/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 730us/step
[1m557/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 725us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m75/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 682us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 70/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 732us/step
[1m140/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 724us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 25.92 [%]
Global F1 score (validation) = 23.06 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[1.6127878e-01 2.0054364e-01 2.1253033e-01 ... 7.8078121e-04
  1.3708229e-01 2.1501424e-02]
 [1.7482498e-01 1.8293720e-01 2.0301692e-01 ... 4.6555382e-05
  2.2387081e-01 4.9413826e-02]
 [1.6233616e-01 1.3497613e-01 1.6504893e-01 ... 1.6895069e-03
  1.3292408e-01 1.6699579e-02]
 ...
 [1.5347603e-01 1.6409507e-01 1.6821821e-01 ... 2.4301936e-03
  1.3133328e-01 2.0350318e-02]
 [1.5287620e-01 1.5497650e-01 1.2391715e-01 ... 3.7895280e-03
  1.4771353e-01 1.3352648e-02]
 [9.1403387e-02 1.1968487e-01 8.7602071e-02 ... 1.1261610e-02
  7.4692890e-02 8.9498078e-03]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 30.18 [%]
Global accuracy score (test) = 22.32 [%]
Global F1 score (train) = 27.87 [%]
Global F1 score (test) = 20.33 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.10      0.03      0.04       184
 CAMINAR CON MÓVIL O LIBRO       0.19      0.16      0.17       184
       CAMINAR USUAL SPEED       0.11      0.02      0.04       184
            CAMINAR ZIGZAG       0.09      0.19      0.12       184
          DE PIE BARRIENDO       0.13      0.45      0.20       184
   DE PIE DOBLANDO TOALLAS       0.19      0.14      0.16       184
    DE PIE MOVIENDO LIBROS       0.27      0.20      0.23       184
          DE PIE USANDO PC       0.28      0.88      0.43       184
        FASE REPOSO CON K5       0.78      0.54      0.64       184
INCREMENTAL CICLOERGOMETRO       0.67      0.04      0.08       184
           SENTADO LEYENDO       0.25      0.21      0.23       184
         SENTADO USANDO PC       0.05      0.02      0.03       184
      SENTADO VIENDO LA TV       0.20      0.12      0.15       184
   SUBIR Y BAJAR ESCALERAS       0.26      0.11      0.15       184
                    TROTAR       0.95      0.24      0.38       161

                  accuracy                           0.22      2737
                 macro avg       0.30      0.22      0.20      2737
              weighted avg       0.29      0.22      0.20      2737


Accuracy capturado en la ejecución 23: 22.32 [%]
F1-score capturado en la ejecución 23: 20.33 [%]

=== EJECUCIÓN 24 ===

--- TRAIN (ejecución 24) ---

--- TEST (ejecución 24) ---
2025-11-07 14:32:33.796410: 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 14:32:33.807527: 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 00:00:1762522353.821044 2997817 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762522353.825134 2997817 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762522353.835248 2997817 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522353.835264 2997817 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522353.835266 2997817 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522353.835274 2997817 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:32:33.838420: 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 00:00:1762522356.105439 2997817 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762522357.618155 2997947 service.cc:152] XLA service 0x7f829800c8b0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762522357.618200 2997947 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:32:37.654404: 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 00:00:1762522357.807144 2997947 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762522359.224999 2997947 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m48:11[0m 2s/step - accuracy: 0.0000e+00 - loss: 3.2789
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0401 - loss: 3.2006      
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0527 - loss: 3.2050
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0570 - loss: 3.2009
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0605 - loss: 3.1923
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0633 - loss: 3.1826
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0654 - loss: 3.1737
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0672 - loss: 3.1646
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0684 - loss: 3.1568
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0695 - loss: 3.1493
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0706 - loss: 3.1413
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0715 - loss: 3.1342
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0722 - loss: 3.1270
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0728 - loss: 3.1207
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0735 - loss: 3.1141
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0741 - loss: 3.1075
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0747 - loss: 3.1015
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0753 - loss: 3.0955
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0759 - loss: 3.0892
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0764 - loss: 3.0837
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0769 - loss: 3.0789
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0774 - loss: 3.0740
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0779 - loss: 3.0687
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0784 - loss: 3.0636
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0790 - loss: 3.0590
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0795 - loss: 3.0543
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0800 - loss: 3.0499
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0804 - loss: 3.0455
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0809 - loss: 3.0408
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0813 - loss: 3.0368
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0815 - loss: 3.0357
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0815 - loss: 3.0356 - val_accuracy: 0.0977 - val_loss: 2.6540
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.6985
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1017 - loss: 2.7464  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1003 - loss: 2.7450
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0992 - loss: 2.7439
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0993 - loss: 2.7412
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0990 - loss: 2.7405
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0995 - loss: 2.7384
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1004 - loss: 2.7359
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1013 - loss: 2.7335
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1023 - loss: 2.7310
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1033 - loss: 2.7284
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1042 - loss: 2.7257
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1050 - loss: 2.7229
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1058 - loss: 2.7201
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1065 - loss: 2.7176
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1072 - loss: 2.7151
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1078 - loss: 2.7129
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1085 - loss: 2.7108
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1091 - loss: 2.7088
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1097 - loss: 2.7067
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1104 - loss: 2.7047
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1110 - loss: 2.7026
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1116 - loss: 2.7004
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1122 - loss: 2.6984
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1126 - loss: 2.6968
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1132 - loss: 2.6949
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1137 - loss: 2.6930
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1142 - loss: 2.6913
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1147 - loss: 2.6896
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1152 - loss: 2.6882 - val_accuracy: 0.1574 - val_loss: 2.5055
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 2.7442
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1384 - loss: 2.6023  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1462 - loss: 2.5808
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1499 - loss: 2.5739
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1516 - loss: 2.5704
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1525 - loss: 2.5668
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1533 - loss: 2.5641
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1537 - loss: 2.5612
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1541 - loss: 2.5591
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1546 - loss: 2.5570
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1548 - loss: 2.5552
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1551 - loss: 2.5533
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1554 - loss: 2.5518
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1555 - loss: 2.5503
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1557 - loss: 2.5490
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1559 - loss: 2.5476
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1561 - loss: 2.5463
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1564 - loss: 2.5452
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1567 - loss: 2.5441
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1569 - loss: 2.5430
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1571 - loss: 2.5420
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1573 - loss: 2.5409
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1575 - loss: 2.5399
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1578 - loss: 2.5390
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1580 - loss: 2.5382
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1582 - loss: 2.5374
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1584 - loss: 2.5365
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1587 - loss: 2.5357
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1589 - loss: 2.5348
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1590 - loss: 2.5345 - val_accuracy: 0.1948 - val_loss: 2.4216
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.6832
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1618 - loss: 2.5095  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1648 - loss: 2.4999
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1669 - loss: 2.4916
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1693 - loss: 2.4826
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1708 - loss: 2.4767
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1717 - loss: 2.4724
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1724 - loss: 2.4692
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1728 - loss: 2.4667
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1731 - loss: 2.4653
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1737 - loss: 2.4642
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1741 - loss: 2.4634
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1745 - loss: 2.4625
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1747 - loss: 2.4615
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1749 - loss: 2.4606
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1751 - loss: 2.4597
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1754 - loss: 2.4586
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1756 - loss: 2.4578
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1759 - loss: 2.4569
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1761 - loss: 2.4561
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1763 - loss: 2.4553
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1765 - loss: 2.4545
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1767 - loss: 2.4537
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1770 - loss: 2.4529
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1773 - loss: 2.4520
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1775 - loss: 2.4512
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1777 - loss: 2.4505
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1779 - loss: 2.4497
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1781 - loss: 2.4489
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1782 - loss: 2.4482
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1783 - loss: 2.4481 - val_accuracy: 0.2068 - val_loss: 2.3352
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.1250 - loss: 2.3434
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2100 - loss: 2.3443  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2093 - loss: 2.3558
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2070 - loss: 2.3611
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2063 - loss: 2.3621
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2054 - loss: 2.3628
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2046 - loss: 2.3630
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2039 - loss: 2.3630
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2036 - loss: 2.3623
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2035 - loss: 2.3613
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2033 - loss: 2.3606
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2031 - loss: 2.3602
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2027 - loss: 2.3601
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2024 - loss: 2.3601
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2020 - loss: 2.3602
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2015 - loss: 2.3603
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2011 - loss: 2.3602
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2008 - loss: 2.3602
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2006 - loss: 2.3600
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2004 - loss: 2.3597
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2003 - loss: 2.3593
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2002 - loss: 2.3591
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2001 - loss: 2.3588
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1999 - loss: 2.3586
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1998 - loss: 2.3583
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1997 - loss: 2.3580
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1996 - loss: 2.3578
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1995 - loss: 2.3576
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1995 - loss: 2.3573
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1994 - loss: 2.3571
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1994 - loss: 2.3571 - val_accuracy: 0.2148 - val_loss: 2.2619
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.7097
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1843 - loss: 2.3595  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1873 - loss: 2.3498
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1893 - loss: 2.3433
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1922 - loss: 2.3373
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1938 - loss: 2.3332
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1954 - loss: 2.3295
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1963 - loss: 2.3279
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1971 - loss: 2.3266
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1980 - loss: 2.3253
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1987 - loss: 2.3241
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1992 - loss: 2.3234
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1998 - loss: 2.3226
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2003 - loss: 2.3220
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2009 - loss: 2.3212
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2014 - loss: 2.3204
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2019 - loss: 2.3198
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2023 - loss: 2.3193
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2026 - loss: 2.3189
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2029 - loss: 2.3185
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2031 - loss: 2.3182
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2033 - loss: 2.3177
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2037 - loss: 2.3171
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2039 - loss: 2.3167
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2041 - loss: 2.3163
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2043 - loss: 2.3159
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2045 - loss: 2.3155
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2047 - loss: 2.3151
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2048 - loss: 2.3147
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2050 - loss: 2.3144
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2050 - loss: 2.3144 - val_accuracy: 0.2161 - val_loss: 2.2345
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 2.6805
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2003 - loss: 2.2971  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2010 - loss: 2.2933
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2035 - loss: 2.2848
[1m 168/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2047 - loss: 2.2791
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2051 - loss: 2.2764
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2055 - loss: 2.2748
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2058 - loss: 2.2740
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2060 - loss: 2.2736
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2062 - loss: 2.2731
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2064 - loss: 2.2725
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2066 - loss: 2.2719
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2070 - loss: 2.2712
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2072 - loss: 2.2705
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2075 - loss: 2.2698
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2077 - loss: 2.2692
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2078 - loss: 2.2688
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2080 - loss: 2.2683
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2082 - loss: 2.2677
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2083 - loss: 2.2673
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2085 - loss: 2.2668
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2086 - loss: 2.2664
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2086 - loss: 2.2659
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2087 - loss: 2.2656
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2087 - loss: 2.2652
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2087 - loss: 2.2648
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2087 - loss: 2.2644
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2088 - loss: 2.2641
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2088 - loss: 2.2637
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2089 - loss: 2.2634 - val_accuracy: 0.2287 - val_loss: 2.1713
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.6723
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2261 - loss: 2.2964  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2175 - loss: 2.2665
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2143 - loss: 2.2564
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2135 - loss: 2.2501
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2134 - loss: 2.2469
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2129 - loss: 2.2468
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2125 - loss: 2.2463
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2124 - loss: 2.2450
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2124 - loss: 2.2440
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2124 - loss: 2.2437
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2124 - loss: 2.2435
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2125 - loss: 2.2433
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2125 - loss: 2.2431
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2126 - loss: 2.2429
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2128 - loss: 2.2426
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2129 - loss: 2.2424
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2131 - loss: 2.2421
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2133 - loss: 2.2416
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2134 - loss: 2.2411
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2136 - loss: 2.2406
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2138 - loss: 2.2400
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2140 - loss: 2.2393
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2141 - loss: 2.2387
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2144 - loss: 2.2380
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2146 - loss: 2.2374
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2147 - loss: 2.2369
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2149 - loss: 2.2365
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2150 - loss: 2.2360
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2151 - loss: 2.2356 - val_accuracy: 0.2524 - val_loss: 2.1319
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0479
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2239 - loss: 2.1874  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2196 - loss: 2.2133
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2203 - loss: 2.2194
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2217 - loss: 2.2185
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2226 - loss: 2.2167
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2229 - loss: 2.2150
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2236 - loss: 2.2126
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2240 - loss: 2.2105
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2243 - loss: 2.2091
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2245 - loss: 2.2085
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2246 - loss: 2.2082
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2246 - loss: 2.2082
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2245 - loss: 2.2082
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2245 - loss: 2.2082
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2244 - loss: 2.2081
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2243 - loss: 2.2079
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2242 - loss: 2.2077
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2243 - loss: 2.2074
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2243 - loss: 2.2069
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2243 - loss: 2.2064
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2243 - loss: 2.2060
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2243 - loss: 2.2056
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2243 - loss: 2.2053
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2243 - loss: 2.2049
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2243 - loss: 2.2045
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2243 - loss: 2.2042
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2244 - loss: 2.2039
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2244 - loss: 2.2036
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2244 - loss: 2.2034 - val_accuracy: 0.2586 - val_loss: 2.1104
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.1517
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2359 - loss: 2.1659  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2269 - loss: 2.1797
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2216 - loss: 2.1840
[1m 171/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2189 - loss: 2.1889
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2184 - loss: 2.1905
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2190 - loss: 2.1898
[1m 301/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2194 - loss: 2.1893
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2198 - loss: 2.1881
[1m 387/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2203 - loss: 2.1865
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2208 - loss: 2.1854
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2212 - loss: 2.1844
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2216 - loss: 2.1836
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2218 - loss: 2.1830
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2220 - loss: 2.1824
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2223 - loss: 2.1817
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2225 - loss: 2.1811
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2229 - loss: 2.1804
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2231 - loss: 2.1797
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2233 - loss: 2.1792
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2236 - loss: 2.1786
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2238 - loss: 2.1782
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2240 - loss: 2.1778
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2242 - loss: 2.1775
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2244 - loss: 2.1771
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2246 - loss: 2.1768
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2248 - loss: 2.1765
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2249 - loss: 2.1762
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2251 - loss: 2.1759
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2251 - loss: 2.1758 - val_accuracy: 0.2668 - val_loss: 2.0865
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.0950
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2438 - loss: 2.1517  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2378 - loss: 2.1580
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2351 - loss: 2.1598
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2344 - loss: 2.1572
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2341 - loss: 2.1558
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2342 - loss: 2.1547
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2341 - loss: 2.1542
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2339 - loss: 2.1539
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2338 - loss: 2.1537
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2338 - loss: 2.1536
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2338 - loss: 2.1537
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2339 - loss: 2.1533
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2339 - loss: 2.1528
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2339 - loss: 2.1523
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2339 - loss: 2.1517
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2339 - loss: 2.1510
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2339 - loss: 2.1504
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2338 - loss: 2.1496
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2338 - loss: 2.1489
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2337 - loss: 2.1482
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2337 - loss: 2.1475
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2337 - loss: 2.1470
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2337 - loss: 2.1466
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2337 - loss: 2.1463
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2336 - loss: 2.1460
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2336 - loss: 2.1458
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2335 - loss: 2.1456
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2335 - loss: 2.1455
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2334 - loss: 2.1454 - val_accuracy: 0.2575 - val_loss: 2.0492
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 1.7926
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2545 - loss: 2.0928  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2591 - loss: 2.1054
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2585 - loss: 2.1130
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2547 - loss: 2.1185
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2518 - loss: 2.1214
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2502 - loss: 2.1230
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2487 - loss: 2.1237
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2478 - loss: 2.1241
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2474 - loss: 2.1242
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2468 - loss: 2.1248
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2461 - loss: 2.1249
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1250
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1251
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2447 - loss: 2.1254
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2444 - loss: 2.1255
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2442 - loss: 2.1254
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2440 - loss: 2.1253
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2439 - loss: 2.1250
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2439 - loss: 2.1248
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2438 - loss: 2.1246
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2438 - loss: 2.1243
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2438 - loss: 2.1241
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2438 - loss: 2.1240
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2438 - loss: 2.1239
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2438 - loss: 2.1239
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2438 - loss: 2.1239
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2437 - loss: 2.1238
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2437 - loss: 2.1238
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2436 - loss: 2.1238
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2436 - loss: 2.1238 - val_accuracy: 0.2651 - val_loss: 2.0516
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.5367
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2470 - loss: 2.1400  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2429 - loss: 2.1395
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2425 - loss: 2.1272
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2442 - loss: 2.1203
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2458 - loss: 2.1159
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2464 - loss: 2.1128
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2468 - loss: 2.1105
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2473 - loss: 2.1090
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2475 - loss: 2.1081
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2476 - loss: 2.1076
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2474 - loss: 2.1078
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2471 - loss: 2.1082
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2468 - loss: 2.1085
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2466 - loss: 2.1087
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2464 - loss: 2.1087
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2462 - loss: 2.1086
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2460 - loss: 2.1087
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1087
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.1087
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1088
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2449 - loss: 2.1088
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2447 - loss: 2.1088
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2445 - loss: 2.1088
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2443 - loss: 2.1087
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2442 - loss: 2.1085
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2441 - loss: 2.1083
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2441 - loss: 2.1082
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2440 - loss: 2.1080
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2439 - loss: 2.1079 - val_accuracy: 0.2651 - val_loss: 2.0182
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.7978
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2625 - loss: 2.0746  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2618 - loss: 2.0812
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0856
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2537 - loss: 2.0917
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2511 - loss: 2.0964
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2487 - loss: 2.1007
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2471 - loss: 2.1033
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2464 - loss: 2.1040
[1m 381/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2460 - loss: 2.1047
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2459 - loss: 2.1048
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1051
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2456 - loss: 2.1053
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2453 - loss: 2.1056
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1056
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1056
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1056
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1053
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2452 - loss: 2.1049
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2453 - loss: 2.1046
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.1043
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1039
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1035
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2458 - loss: 2.1032
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2458 - loss: 2.1029
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2458 - loss: 2.1027
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2458 - loss: 2.1024
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2458 - loss: 2.1022
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2458 - loss: 2.1020 - val_accuracy: 0.2413 - val_loss: 2.0649
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.2070
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0505  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0497
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0535
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0557
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2558 - loss: 2.0566
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2543 - loss: 2.0581
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2530 - loss: 2.0602
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2520 - loss: 2.0624
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2512 - loss: 2.0648
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2507 - loss: 2.0664
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.0680
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2498 - loss: 2.0692
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2496 - loss: 2.0701
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2494 - loss: 2.0709
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2493 - loss: 2.0715
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2492 - loss: 2.0718
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2492 - loss: 2.0721
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2492 - loss: 2.0724
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2492 - loss: 2.0727
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2493 - loss: 2.0729
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2494 - loss: 2.0731
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2495 - loss: 2.0733
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2497 - loss: 2.0736
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2498 - loss: 2.0738
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2499 - loss: 2.0740
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2500 - loss: 2.0742
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2501 - loss: 2.0743
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2501 - loss: 2.0745
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2502 - loss: 2.0746 - val_accuracy: 0.2601 - val_loss: 2.0168
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 1.7827
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2566 - loss: 2.0618  
[1m  89/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2487 - loss: 2.0884
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2525 - loss: 2.0877
[1m 177/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2523 - loss: 2.0896
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2528 - loss: 2.0901
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2527 - loss: 2.0903
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2524 - loss: 2.0898
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2520 - loss: 2.0892
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2517 - loss: 2.0883
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2517 - loss: 2.0873
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2517 - loss: 2.0865
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2516 - loss: 2.0865
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2512 - loss: 2.0865
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2510 - loss: 2.0864
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2507 - loss: 2.0864
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2505 - loss: 2.0862
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2504 - loss: 2.0860
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.0857
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2501 - loss: 2.0854
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2501 - loss: 2.0851
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2500 - loss: 2.0847
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2500 - loss: 2.0843
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2500 - loss: 2.0840
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2500 - loss: 2.0837
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2501 - loss: 2.0834
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.0829
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2503 - loss: 2.0825
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2504 - loss: 2.0821
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2504 - loss: 2.0819 - val_accuracy: 0.2620 - val_loss: 2.0108
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.1660
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2429 - loss: 2.0879  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2413 - loss: 2.0827
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2409 - loss: 2.0861
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2416 - loss: 2.0841
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2422 - loss: 2.0824
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2431 - loss: 2.0801
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2437 - loss: 2.0784
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2441 - loss: 2.0770
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2446 - loss: 2.0750
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.0730
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2462 - loss: 2.0712
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2471 - loss: 2.0697
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2477 - loss: 2.0688
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2482 - loss: 2.0679
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2485 - loss: 2.0672
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2488 - loss: 2.0662
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2490 - loss: 2.0656
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2493 - loss: 2.0651
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2494 - loss: 2.0647
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2496 - loss: 2.0643
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2497 - loss: 2.0639
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2497 - loss: 2.0636
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2498 - loss: 2.0634
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2499 - loss: 2.0631
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2500 - loss: 2.0628
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2501 - loss: 2.0625
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.0622
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2504 - loss: 2.0619
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2505 - loss: 2.0616
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2505 - loss: 2.0614 - val_accuracy: 0.2768 - val_loss: 1.9933
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 1.6023
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2522 - loss: 1.9461  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2470 - loss: 1.9897
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2433 - loss: 2.0163
[1m 149/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2433 - loss: 2.0247
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2442 - loss: 2.0306
[1m 226/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2464 - loss: 2.0335
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2480 - loss: 2.0349
[1m 304/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2494 - loss: 2.0359
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2502 - loss: 2.0367
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2513 - loss: 2.0370
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2523 - loss: 2.0373
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2530 - loss: 2.0374
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2536 - loss: 2.0373
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2541 - loss: 2.0373
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2544 - loss: 2.0373
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2549 - loss: 2.0372
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2553 - loss: 2.0373
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2556 - loss: 2.0374
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.0376
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2562 - loss: 2.0376
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.0375
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0375
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0374
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0373
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2574 - loss: 2.0373
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2576 - loss: 2.0373
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2577 - loss: 2.0372
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.0372
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2579 - loss: 2.0372
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2580 - loss: 2.0371 - val_accuracy: 0.2653 - val_loss: 1.9883
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.0625 - loss: 1.9464
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2462 - loss: 2.0256  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2538 - loss: 2.0153
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0155
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2565 - loss: 2.0151
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2587 - loss: 2.0130
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0129
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2613 - loss: 2.0121
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2619 - loss: 2.0125
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2622 - loss: 2.0134
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2625 - loss: 2.0149
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2628 - loss: 2.0160
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0170
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0177
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0185
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0194
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0203
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0212
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0219
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0223
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2629 - loss: 2.0228
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2628 - loss: 2.0232
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2627 - loss: 2.0235
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2626 - loss: 2.0238
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2625 - loss: 2.0240
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2625 - loss: 2.0240
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2625 - loss: 2.0240
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2624 - loss: 2.0241
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2624 - loss: 2.0240
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2624 - loss: 2.0240
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2624 - loss: 2.0241 - val_accuracy: 0.2642 - val_loss: 1.9914
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.3064
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2288 - loss: 2.0445  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2334 - loss: 2.0395
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2400 - loss: 2.0347
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2430 - loss: 2.0325
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2446 - loss: 2.0288
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2457 - loss: 2.0262
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2466 - loss: 2.0251
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2471 - loss: 2.0250
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2474 - loss: 2.0253
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2476 - loss: 2.0255
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2477 - loss: 2.0261
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2477 - loss: 2.0267
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2478 - loss: 2.0271
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2479 - loss: 2.0275
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2481 - loss: 2.0278
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2484 - loss: 2.0281
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2486 - loss: 2.0283
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2489 - loss: 2.0286
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2492 - loss: 2.0288
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2496 - loss: 2.0288
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2499 - loss: 2.0288
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.0289
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2505 - loss: 2.0289
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2509 - loss: 2.0289
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2512 - loss: 2.0289
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2516 - loss: 2.0288
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2519 - loss: 2.0286
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2522 - loss: 2.0283
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2525 - loss: 2.0281
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2526 - loss: 2.0281 - val_accuracy: 0.2627 - val_loss: 1.9887
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.3308
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2859 - loss: 2.0158  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2784 - loss: 2.0209
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2780 - loss: 2.0237
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2777 - loss: 2.0239
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2773 - loss: 2.0228
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2768 - loss: 2.0223
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2760 - loss: 2.0212
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0205
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2743 - loss: 2.0198
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2738 - loss: 2.0194
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2734 - loss: 2.0190
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0186
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2729 - loss: 2.0186
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2726 - loss: 2.0187
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2724 - loss: 2.0185
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2723 - loss: 2.0181
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0177
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0174
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0171
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2720 - loss: 2.0170
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2719 - loss: 2.0169
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0168
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0167
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0166
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2714 - loss: 2.0164
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2712 - loss: 2.0163
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0161
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0159
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0158
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2708 - loss: 2.0158 - val_accuracy: 0.2553 - val_loss: 1.9728
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.0964
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2608 - loss: 1.9292  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2729 - loss: 1.9447
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2755 - loss: 1.9550
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2750 - loss: 1.9622
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2741 - loss: 1.9674
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2730 - loss: 1.9732
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2720 - loss: 1.9785
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2711 - loss: 1.9828
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2701 - loss: 1.9862
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2691 - loss: 1.9888
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2684 - loss: 1.9910
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2678 - loss: 1.9928
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2673 - loss: 1.9943
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 1.9955
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2667 - loss: 1.9965
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 1.9972
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 1.9977
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 1.9981
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 1.9985
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 1.9989
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 1.9993
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 1.9996
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 1.9999
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0002
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0005
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0007
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0009
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0010
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0011
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2662 - loss: 2.0012 - val_accuracy: 0.2738 - val_loss: 1.9633
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 1.7080
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2869 - loss: 1.9408  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2837 - loss: 1.9635
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2815 - loss: 1.9685
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9735
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2792 - loss: 1.9774
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2786 - loss: 1.9807
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2781 - loss: 1.9831
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2775 - loss: 1.9847
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2771 - loss: 1.9860
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2768 - loss: 1.9872
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2764 - loss: 1.9879
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 1.9884
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2754 - loss: 1.9889
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2750 - loss: 1.9894
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2746 - loss: 1.9897
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2742 - loss: 1.9900
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2738 - loss: 1.9901
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2733 - loss: 1.9905
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2730 - loss: 1.9909
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2727 - loss: 1.9913
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2724 - loss: 1.9916
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2721 - loss: 1.9919
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2720 - loss: 1.9920
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2719 - loss: 1.9920
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2718 - loss: 1.9921
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 1.9920
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 1.9920
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 1.9920
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 1.9919
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2716 - loss: 1.9919 - val_accuracy: 0.2664 - val_loss: 1.9589
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.0640
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2141 - loss: 2.0138  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2333 - loss: 2.0105
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2418 - loss: 2.0096
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2459 - loss: 2.0122
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2487 - loss: 2.0134
[1m 251/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2515 - loss: 2.0129
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2538 - loss: 2.0114
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2557 - loss: 2.0102
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0094
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2582 - loss: 2.0085
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2592 - loss: 2.0078
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2598 - loss: 2.0074
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0069
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2607 - loss: 2.0067
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0066
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2615 - loss: 2.0062
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2617 - loss: 2.0059
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2620 - loss: 2.0056
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2621 - loss: 2.0054
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2621 - loss: 2.0052
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2623 - loss: 2.0049
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2624 - loss: 2.0045
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2625 - loss: 2.0041
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2626 - loss: 2.0038
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2627 - loss: 2.0035
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2627 - loss: 2.0032
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2628 - loss: 2.0030
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2629 - loss: 2.0027
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2629 - loss: 2.0026 - val_accuracy: 0.2698 - val_loss: 1.9610
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 19ms/step - accuracy: 0.3125 - loss: 1.9312
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0048  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2712 - loss: 1.9971
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2681 - loss: 1.9984
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2670 - loss: 1.9962
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2667 - loss: 1.9956
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2664 - loss: 1.9957
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2663 - loss: 1.9955
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2666 - loss: 1.9950
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2673 - loss: 1.9941
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 1.9935
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 1.9932
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2681 - loss: 1.9928
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2684 - loss: 1.9922
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2688 - loss: 1.9914
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2692 - loss: 1.9906
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 1.9899
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2700 - loss: 1.9891
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 1.9883
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 1.9874
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 1.9867
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 1.9863
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2715 - loss: 1.9859
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 1.9855
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2718 - loss: 1.9852
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2719 - loss: 1.9849
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2721 - loss: 1.9846
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2722 - loss: 1.9844
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2723 - loss: 1.9843
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2723 - loss: 1.9842
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2723 - loss: 1.9842 - val_accuracy: 0.2777 - val_loss: 1.9547

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 636ms/step
[1m63/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 808us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:00[0m 824ms/step
[1m 61/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 843us/step  
[1m124/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 820us/step
[1m191/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 799us/step
[1m250/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 815us/step
[1m319/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 797us/step
[1m385/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 791us/step
[1m457/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 777us/step
[1m525/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 772us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m62/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 831us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 57/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 895us/step
[1m117/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 864us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 28.57 [%]
Global F1 score (validation) = 24.09 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.15327251 0.20569207 0.15109424 ... 0.00544876 0.12379927 0.01455801]
 [0.12818441 0.17253348 0.18990111 ... 0.00662829 0.15831172 0.02132217]
 [0.14824536 0.23158887 0.1793668  ... 0.00080843 0.15883298 0.02225862]
 ...
 [0.15124348 0.21847147 0.17479093 ... 0.00243728 0.13367383 0.01951138]
 [0.11695591 0.24344967 0.2219811  ... 0.00145463 0.16834167 0.03752171]
 [0.18001753 0.22072774 0.16696815 ... 0.00129826 0.15538561 0.02472503]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 30.89 [%]
Global accuracy score (test) = 26.6 [%]
Global F1 score (train) = 27.4 [%]
Global F1 score (test) = 23.02 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.00      0.00      0.00       184
 CAMINAR CON MÓVIL O LIBRO       0.18      0.80      0.30       184
       CAMINAR USUAL SPEED       0.07      0.03      0.04       184
            CAMINAR ZIGZAG       0.00      0.00      0.00       184
          DE PIE BARRIENDO       0.18      0.30      0.23       184
   DE PIE DOBLANDO TOALLAS       0.29      0.37      0.32       184
    DE PIE MOVIENDO LIBROS       0.27      0.07      0.10       184
          DE PIE USANDO PC       0.27      0.69      0.39       184
        FASE REPOSO CON K5       0.90      0.58      0.71       184
INCREMENTAL CICLOERGOMETRO       0.48      0.21      0.29       184
           SENTADO LEYENDO       0.24      0.38      0.29       184
         SENTADO USANDO PC       0.16      0.05      0.07       184
      SENTADO VIENDO LA TV       0.32      0.23      0.27       184
   SUBIR Y BAJAR ESCALERAS       0.23      0.06      0.09       184
                    TROTAR       0.85      0.22      0.35       161

                  accuracy                           0.27      2737
                 macro avg       0.30      0.27      0.23      2737
              weighted avg       0.29      0.27      0.23      2737


Accuracy capturado en la ejecución 24: 26.6 [%]
F1-score capturado en la ejecución 24: 23.02 [%]

=== EJECUCIÓN 25 ===

--- TRAIN (ejecución 25) ---

--- TEST (ejecución 25) ---
2025-11-07 14:33:40.776111: 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 14:33:40.787541: 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 00:00:1762522420.801038 3001564 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762522420.805021 3001564 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762522420.815201 3001564 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522420.815216 3001564 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522420.815217 3001564 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522420.815219 3001564 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:33:40.818178: 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 00:00:1762522423.064047 3001564 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762522424.545453 3001681 service.cc:152] XLA service 0x763d3c01f140 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762522424.545481 3001681 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:33:44.572127: 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 00:00:1762522424.716475 3001681 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762522426.135818 3001681 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47:29[0m 2s/step - accuracy: 0.0625 - loss: 3.3599
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0542 - loss: 3.2710  
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0532 - loss: 3.2632
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0555 - loss: 3.2398
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0588 - loss: 3.2176
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0611 - loss: 3.2032
[1m 227/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0628 - loss: 3.1924
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0645 - loss: 3.1815
[1m 305/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0662 - loss: 3.1704
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0676 - loss: 3.1601
[1m 386/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0688 - loss: 3.1510
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0700 - loss: 3.1415
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0711 - loss: 3.1333
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0722 - loss: 3.1247
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0732 - loss: 3.1167
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0741 - loss: 3.1095
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0751 - loss: 3.1021
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0760 - loss: 3.0943
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0769 - loss: 3.0875
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0777 - loss: 3.0811
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0786 - loss: 3.0740
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0794 - loss: 3.0679
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0801 - loss: 3.0618
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0808 - loss: 3.0563
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0815 - loss: 3.0510
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0822 - loss: 3.0452
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0828 - loss: 3.0403
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0835 - loss: 3.0348
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0842 - loss: 3.0295
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0848 - loss: 3.0250
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0852 - loss: 3.0227
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0852 - loss: 3.0225 - val_accuracy: 0.1919 - val_loss: 2.5417
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0000e+00 - loss: 2.7823
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1304 - loss: 2.6469      
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1367 - loss: 2.6531
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1401 - loss: 2.6548
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1419 - loss: 2.6548
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1428 - loss: 2.6544
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1433 - loss: 2.6542
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1440 - loss: 2.6534
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1445 - loss: 2.6525
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1448 - loss: 2.6514
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1452 - loss: 2.6499
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1454 - loss: 2.6487
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1458 - loss: 2.6472
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1461 - loss: 2.6456
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1464 - loss: 2.6442
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1466 - loss: 2.6428
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1468 - loss: 2.6415
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1470 - loss: 2.6402
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1472 - loss: 2.6388
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1474 - loss: 2.6375
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1475 - loss: 2.6362
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1477 - loss: 2.6349
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1478 - loss: 2.6337
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1480 - loss: 2.6323
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1482 - loss: 2.6311
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1485 - loss: 2.6299
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1487 - loss: 2.6286
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1490 - loss: 2.6275
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1493 - loss: 2.6262
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1495 - loss: 2.6251 - val_accuracy: 0.2154 - val_loss: 2.4290
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.7653
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1548 - loss: 2.5063  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1557 - loss: 2.5171
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1601 - loss: 2.5128
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1626 - loss: 2.5108
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1645 - loss: 2.5085
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1660 - loss: 2.5060
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1673 - loss: 2.5041
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1682 - loss: 2.5031
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1690 - loss: 2.5019
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1696 - loss: 2.5010
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1702 - loss: 2.4998
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1707 - loss: 2.4990
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1713 - loss: 2.4980
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1719 - loss: 2.4971
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1725 - loss: 2.4963
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1731 - loss: 2.4955
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1738 - loss: 2.4945
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1745 - loss: 2.4934
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1751 - loss: 2.4925
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1756 - loss: 2.4915
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1761 - loss: 2.4905
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1765 - loss: 2.4896
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1770 - loss: 2.4887
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1774 - loss: 2.4876
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1777 - loss: 2.4867
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1780 - loss: 2.4857
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1783 - loss: 2.4847
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1786 - loss: 2.4836
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1788 - loss: 2.4829
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1789 - loss: 2.4827 - val_accuracy: 0.2326 - val_loss: 2.3245
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 2.1648
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2202 - loss: 2.3908  
[1m  71/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2194 - loss: 2.3863
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2185 - loss: 2.3884
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2171 - loss: 2.3918
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2150 - loss: 2.3958
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2123 - loss: 2.3986
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2102 - loss: 2.4000
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2091 - loss: 2.4003
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2084 - loss: 2.4001
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2079 - loss: 2.3992
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2074 - loss: 2.3984
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2071 - loss: 2.3975
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2069 - loss: 2.3963
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2066 - loss: 2.3956
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2063 - loss: 2.3948
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2060 - loss: 2.3941
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2059 - loss: 2.3934
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2057 - loss: 2.3927
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2056 - loss: 2.3919
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2055 - loss: 2.3913
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2053 - loss: 2.3906
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2052 - loss: 2.3900
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2051 - loss: 2.3894
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2051 - loss: 2.3889
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2051 - loss: 2.3884
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2051 - loss: 2.3879
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2051 - loss: 2.3872
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2052 - loss: 2.3866
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2052 - loss: 2.3861
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2052 - loss: 2.3860 - val_accuracy: 0.2263 - val_loss: 2.2665
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.4679
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2026 - loss: 2.3541  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1985 - loss: 2.3378
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1965 - loss: 2.3339
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1952 - loss: 2.3341
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1951 - loss: 2.3352
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1961 - loss: 2.3347
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1971 - loss: 2.3342
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1977 - loss: 2.3344
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1984 - loss: 2.3345
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1990 - loss: 2.3345
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1995 - loss: 2.3343
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1998 - loss: 2.3341
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2003 - loss: 2.3338
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2006 - loss: 2.3334
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2009 - loss: 2.3330
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2012 - loss: 2.3327
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2014 - loss: 2.3325
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2016 - loss: 2.3323
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2018 - loss: 2.3320
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2020 - loss: 2.3317
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2023 - loss: 2.3314
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2025 - loss: 2.3310
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2027 - loss: 2.3306
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2030 - loss: 2.3303
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2031 - loss: 2.3300
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2033 - loss: 2.3297
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2034 - loss: 2.3295
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2036 - loss: 2.3293
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2038 - loss: 2.3291
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2038 - loss: 2.3290 - val_accuracy: 0.2474 - val_loss: 2.1906
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.2749
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2163 - loss: 2.2637  
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2100 - loss: 2.2876
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2078 - loss: 2.2962
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2062 - loss: 2.2999
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2058 - loss: 2.3007
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2055 - loss: 2.3016
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2056 - loss: 2.3017
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2059 - loss: 2.3012
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2068 - loss: 2.2997
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2081 - loss: 2.2976
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2092 - loss: 2.2952
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2101 - loss: 2.2932
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2109 - loss: 2.2916
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2117 - loss: 2.2901
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2126 - loss: 2.2886
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2132 - loss: 2.2873
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2137 - loss: 2.2864
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2142 - loss: 2.2856
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2145 - loss: 2.2850
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2149 - loss: 2.2845
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2153 - loss: 2.2838
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2156 - loss: 2.2833
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2159 - loss: 2.2827
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2161 - loss: 2.2822
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2164 - loss: 2.2817
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2166 - loss: 2.2812
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2168 - loss: 2.2809
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2169 - loss: 2.2805
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2171 - loss: 2.2802
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2171 - loss: 2.2801 - val_accuracy: 0.2368 - val_loss: 2.1750
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.8017
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2513 - loss: 2.2332  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2347 - loss: 2.2458
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2302 - loss: 2.2527
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2267 - loss: 2.2600
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2248 - loss: 2.2623
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2241 - loss: 2.2629
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2245 - loss: 2.2616
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2248 - loss: 2.2608
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2249 - loss: 2.2601
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2248 - loss: 2.2595
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2247 - loss: 2.2587
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2248 - loss: 2.2578
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2251 - loss: 2.2568
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2252 - loss: 2.2560
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2252 - loss: 2.2553
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2253 - loss: 2.2548
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2253 - loss: 2.2544
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2253 - loss: 2.2540
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2254 - loss: 2.2536
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2254 - loss: 2.2531
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2254 - loss: 2.2526
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2254 - loss: 2.2521
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2254 - loss: 2.2516
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2255 - loss: 2.2511
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2256 - loss: 2.2506
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2257 - loss: 2.2502
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2258 - loss: 2.2497
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2259 - loss: 2.2493
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.2260 - loss: 2.2489
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2260 - loss: 2.2489 - val_accuracy: 0.2490 - val_loss: 2.1362
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.2688
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2395 - loss: 2.2178  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2416 - loss: 2.2039
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2395 - loss: 2.2061
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2401 - loss: 2.2052
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2402 - loss: 2.2052
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2394 - loss: 2.2062
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2387 - loss: 2.2067
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2383 - loss: 2.2075
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2377 - loss: 2.2087
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2371 - loss: 2.2098
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2368 - loss: 2.2105
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2364 - loss: 2.2110
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2362 - loss: 2.2114
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2359 - loss: 2.2119
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2357 - loss: 2.2122
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2355 - loss: 2.2124
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2353 - loss: 2.2125
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2351 - loss: 2.2127
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2349 - loss: 2.2127
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2348 - loss: 2.2127
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2347 - loss: 2.2127
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2345 - loss: 2.2128
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2344 - loss: 2.2127
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2344 - loss: 2.2126
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2344 - loss: 2.2123
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2344 - loss: 2.2120
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2344 - loss: 2.2117
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2345 - loss: 2.2114
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2345 - loss: 2.2111
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2345 - loss: 2.2109 - val_accuracy: 0.2483 - val_loss: 2.1111
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.3831
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2535 - loss: 2.2216  
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2483 - loss: 2.2140
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2469 - loss: 2.2002
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2470 - loss: 2.1936
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2466 - loss: 2.1909
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2464 - loss: 2.1890
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2461 - loss: 2.1878
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2456 - loss: 2.1868
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1863
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2446 - loss: 2.1860
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2440 - loss: 2.1858
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2433 - loss: 2.1855
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2426 - loss: 2.1852
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2420 - loss: 2.1849
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2416 - loss: 2.1847
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2411 - loss: 2.1845
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2408 - loss: 2.1843
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2405 - loss: 2.1840
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2403 - loss: 2.1837
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2402 - loss: 2.1832
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2400 - loss: 2.1829
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2399 - loss: 2.1826
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2398 - loss: 2.1824
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2396 - loss: 2.1823
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2395 - loss: 2.1822
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2394 - loss: 2.1820
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2394 - loss: 2.1819
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2393 - loss: 2.1818
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2393 - loss: 2.1817
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2392 - loss: 2.1816 - val_accuracy: 0.2477 - val_loss: 2.0723
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.3143
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2113 - loss: 2.1999  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2265 - loss: 2.1911
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2315 - loss: 2.1919
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2352 - loss: 2.1928
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2370 - loss: 2.1921
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2376 - loss: 2.1914
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2381 - loss: 2.1904
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2384 - loss: 2.1893
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2387 - loss: 2.1879
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2392 - loss: 2.1859
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2395 - loss: 2.1844
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2396 - loss: 2.1834
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2398 - loss: 2.1824
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2401 - loss: 2.1811
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2404 - loss: 2.1799
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2406 - loss: 2.1787
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2409 - loss: 2.1778
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2411 - loss: 2.1770
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2413 - loss: 2.1762
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2415 - loss: 2.1753
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2417 - loss: 2.1746
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2420 - loss: 2.1737
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2422 - loss: 2.1730
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2424 - loss: 2.1723
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2426 - loss: 2.1716
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2429 - loss: 2.1708
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2431 - loss: 2.1701
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2433 - loss: 2.1695
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2436 - loss: 2.1688
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2437 - loss: 2.1686 - val_accuracy: 0.2611 - val_loss: 2.0530
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 25ms/step - accuracy: 0.1875 - loss: 2.2523
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2688 - loss: 2.1175  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2622 - loss: 2.1232
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2568 - loss: 2.1220
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2534 - loss: 2.1208
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2513 - loss: 2.1210
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2501 - loss: 2.1216
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2497 - loss: 2.1222
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2494 - loss: 2.1231
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2493 - loss: 2.1240
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2493 - loss: 2.1248
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2492 - loss: 2.1251
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2491 - loss: 2.1251
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2492 - loss: 2.1252
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2493 - loss: 2.1252
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2493 - loss: 2.1252
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2494 - loss: 2.1251
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2494 - loss: 2.1250
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2493 - loss: 2.1250
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2492 - loss: 2.1251
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2491 - loss: 2.1251
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2489 - loss: 2.1252
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2488 - loss: 2.1252
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2487 - loss: 2.1253
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2487 - loss: 2.1254
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2486 - loss: 2.1254
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2486 - loss: 2.1254
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2486 - loss: 2.1253
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2487 - loss: 2.1252
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2486 - loss: 2.1252 - val_accuracy: 0.2660 - val_loss: 2.0420
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.1416
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2408 - loss: 2.1565  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1481
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2482 - loss: 2.1465
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2491 - loss: 2.1414
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2512 - loss: 2.1353
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2518 - loss: 2.1309
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2526 - loss: 2.1276
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2525 - loss: 2.1260
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2521 - loss: 2.1248
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2519 - loss: 2.1240
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2518 - loss: 2.1235
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2515 - loss: 2.1234
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.1233
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2511 - loss: 2.1232
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2510 - loss: 2.1231
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2509 - loss: 2.1229
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2509 - loss: 2.1226
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2512 - loss: 2.1220
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2514 - loss: 2.1213
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2515 - loss: 2.1207
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2516 - loss: 2.1201
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2516 - loss: 2.1196
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2516 - loss: 2.1191
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2516 - loss: 2.1186
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2516 - loss: 2.1180
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2516 - loss: 2.1174
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2516 - loss: 2.1168
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2517 - loss: 2.1163
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2517 - loss: 2.1158
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2517 - loss: 2.1157 - val_accuracy: 0.2648 - val_loss: 2.0106
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.8470
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2986 - loss: 2.0167  
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2866 - loss: 2.0335
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2796 - loss: 2.0497
[1m 148/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0634
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0713
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2697 - loss: 2.0778
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0810
[1m 307/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0831
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0851
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2647 - loss: 2.0869
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2636 - loss: 2.0886
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0895
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2625 - loss: 2.0902
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2621 - loss: 2.0908
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2616 - loss: 2.0913
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0917
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2607 - loss: 2.0921
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0925
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2598 - loss: 2.0928
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2596 - loss: 2.0930
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2594 - loss: 2.0930
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2592 - loss: 2.0930
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2591 - loss: 2.0930
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2590 - loss: 2.0929
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2590 - loss: 2.0929
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2589 - loss: 2.0928
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2588 - loss: 2.0927
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2588 - loss: 2.0927
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2588 - loss: 2.0926
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2588 - loss: 2.0926 - val_accuracy: 0.2744 - val_loss: 2.0259
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.2500 - loss: 2.0561
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2539 - loss: 2.1084  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2548 - loss: 2.1148
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2561 - loss: 2.1084
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2560 - loss: 2.1051
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2561 - loss: 2.1019
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2565 - loss: 2.1000
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2570 - loss: 2.0981
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2577 - loss: 2.0961
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2585 - loss: 2.0946
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2591 - loss: 2.0931
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2595 - loss: 2.0920
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2598 - loss: 2.0913
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0905
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2601 - loss: 2.0896
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0888
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2605 - loss: 2.0881
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2606 - loss: 2.0875
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2607 - loss: 2.0869
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2608 - loss: 2.0864
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0860
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0857
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0853
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0850
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2612 - loss: 2.0847
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2613 - loss: 2.0844
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2614 - loss: 2.0841
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2615 - loss: 2.0837
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2616 - loss: 2.0833
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2617 - loss: 2.0831 - val_accuracy: 0.2718 - val_loss: 1.9867
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.9025
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2915 - loss: 2.0130  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2924 - loss: 2.0183
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2886 - loss: 2.0265
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2836 - loss: 2.0328
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2815 - loss: 2.0366
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2801 - loss: 2.0405
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2788 - loss: 2.0444
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2776 - loss: 2.0475
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2763 - loss: 2.0504
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2754 - loss: 2.0525
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0538
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2739 - loss: 2.0547
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2733 - loss: 2.0555
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2728 - loss: 2.0561
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2723 - loss: 2.0565
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0570
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2714 - loss: 2.0572
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0575
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0577
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0579
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2701 - loss: 2.0580
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0583
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 2.0584
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0585
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2692 - loss: 2.0585
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2690 - loss: 2.0587
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2688 - loss: 2.0588
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0589
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2685 - loss: 2.0590 - val_accuracy: 0.2699 - val_loss: 1.9882
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5000 - loss: 1.6945
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3093 - loss: 1.9755  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2925 - loss: 2.0055
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2832 - loss: 2.0248
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2786 - loss: 2.0332
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2765 - loss: 2.0379
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0405
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2737 - loss: 2.0419
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2725 - loss: 2.0434
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0454
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0469
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2697 - loss: 2.0478
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2690 - loss: 2.0487
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2683 - loss: 2.0494
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0497
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2673 - loss: 2.0500
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0502
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0503
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0503
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0502
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0500
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0499
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0498
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0498
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0498
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0497
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0496
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0496
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0496
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2661 - loss: 2.0496 - val_accuracy: 0.2796 - val_loss: 2.0072
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.8964
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3181 - loss: 1.9590  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3084 - loss: 1.9808
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3019 - loss: 1.9943
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2972 - loss: 2.0010
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2941 - loss: 2.0051
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2914 - loss: 2.0082
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2890 - loss: 2.0116
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2870 - loss: 2.0149
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2857 - loss: 2.0167
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2845 - loss: 2.0181
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2834 - loss: 2.0195
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2825 - loss: 2.0204
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2820 - loss: 2.0212
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2814 - loss: 2.0222
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2808 - loss: 2.0232
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2802 - loss: 2.0239
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2798 - loss: 2.0245
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 2.0250
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2792 - loss: 2.0254
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2789 - loss: 2.0258
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2786 - loss: 2.0262
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2783 - loss: 2.0266
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2779 - loss: 2.0270
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2775 - loss: 2.0274
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2772 - loss: 2.0277
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2768 - loss: 2.0281
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2765 - loss: 2.0284
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2762 - loss: 2.0287
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2759 - loss: 2.0289 - val_accuracy: 0.2755 - val_loss: 1.9775
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.1471
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3085 - loss: 2.0690  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2944 - loss: 2.0610
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2881 - loss: 2.0579
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2833 - loss: 2.0558
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2803 - loss: 2.0548
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2796 - loss: 2.0526
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2788 - loss: 2.0507
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2781 - loss: 2.0493
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2775 - loss: 2.0479
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2769 - loss: 2.0463
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2764 - loss: 2.0444
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0427
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2758 - loss: 2.0409
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2757 - loss: 2.0395
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2754 - loss: 2.0383
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0375
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0367
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0359
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0355
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0352
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0348
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0345
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2743 - loss: 2.0341
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2742 - loss: 2.0337
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2742 - loss: 2.0334
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2741 - loss: 2.0330
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0327
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2738 - loss: 2.0324
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2738 - loss: 2.0320
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2738 - loss: 2.0320 - val_accuracy: 0.2736 - val_loss: 1.9500
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.7843
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2944 - loss: 1.9970  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2776 - loss: 2.0171
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2712 - loss: 2.0304
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2688 - loss: 2.0354
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2680 - loss: 2.0362
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2684 - loss: 2.0350
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0332
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2688 - loss: 2.0312
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0298
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0290
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0286
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2690 - loss: 2.0285
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0284
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 2.0282
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0280
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2701 - loss: 2.0276
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0273
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0269
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0266
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0263
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0259
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0254
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2705 - loss: 2.0247
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2706 - loss: 2.0242
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0237
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0233
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0229
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0225
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0222
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2710 - loss: 2.0222 - val_accuracy: 0.2818 - val_loss: 1.9502
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 1.6913
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2691 - loss: 1.9258  
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2771 - loss: 1.9544
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2763 - loss: 1.9746
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2739 - loss: 1.9880
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2720 - loss: 1.9947
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0003
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2696 - loss: 2.0034
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0051
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0061
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2692 - loss: 2.0069
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0074
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 2.0075
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0075
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0076
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0076
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0077
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0079
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2719 - loss: 2.0082
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0085
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2724 - loss: 2.0086
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2727 - loss: 2.0087
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2729 - loss: 2.0088
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2730 - loss: 2.0090
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0089
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0088
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2733 - loss: 2.0088
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2734 - loss: 2.0087
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2735 - loss: 2.0085
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0085
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2736 - loss: 2.0085 - val_accuracy: 0.2753 - val_loss: 1.9476
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.0335
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2818 - loss: 2.0331  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2779 - loss: 2.0386
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0386
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0378
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2734 - loss: 2.0349
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0316
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2733 - loss: 2.0276
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2734 - loss: 2.0244
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2734 - loss: 2.0218
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2733 - loss: 2.0202
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2734 - loss: 2.0187
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2733 - loss: 2.0174
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0160
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0150
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2730 - loss: 2.0140
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2730 - loss: 2.0131
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0124
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0119
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0114
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0110
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0107
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2733 - loss: 2.0103
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2734 - loss: 2.0098
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2735 - loss: 2.0095
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2735 - loss: 2.0092
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0089
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 2.0087
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2737 - loss: 2.0085
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2738 - loss: 2.0083
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2738 - loss: 2.0082 - val_accuracy: 0.2866 - val_loss: 1.9728
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.5747
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2628 - loss: 2.0235  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0239
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0234
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0201
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0176
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2689 - loss: 2.0158
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2692 - loss: 2.0144
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2697 - loss: 2.0133
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2701 - loss: 2.0126
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0112
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0098
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0083
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2727 - loss: 2.0071
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0059
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0048
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2741 - loss: 2.0037
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0030
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0023
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0019
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2751 - loss: 2.0014
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2753 - loss: 2.0009
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2755 - loss: 2.0004
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2756 - loss: 2.0001
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2757 - loss: 1.9998
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2758 - loss: 1.9994
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 1.9991
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 1.9988
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2760 - loss: 1.9986
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2760 - loss: 1.9984
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2760 - loss: 1.9983 - val_accuracy: 0.2746 - val_loss: 1.9315
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 1.8115
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3225 - loss: 1.8787  
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3142 - loss: 1.9147
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3101 - loss: 1.9330
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3082 - loss: 1.9403
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3056 - loss: 1.9483
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3031 - loss: 1.9549
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3002 - loss: 1.9593
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2975 - loss: 1.9622
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2961 - loss: 1.9640
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2948 - loss: 1.9656
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2936 - loss: 1.9669
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2927 - loss: 1.9677
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2919 - loss: 1.9686
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2913 - loss: 1.9695
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2907 - loss: 1.9702
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2903 - loss: 1.9707
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2899 - loss: 1.9713
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2896 - loss: 1.9719
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2892 - loss: 1.9724
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2889 - loss: 1.9729
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2887 - loss: 1.9732
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2885 - loss: 1.9735
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2882 - loss: 1.9739
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2880 - loss: 1.9743
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2878 - loss: 1.9746
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2876 - loss: 1.9748
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2873 - loss: 1.9751
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2871 - loss: 1.9753
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2870 - loss: 1.9754 - val_accuracy: 0.2842 - val_loss: 1.9408
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.2243
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3066 - loss: 1.9864  
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2951 - loss: 1.9788
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2935 - loss: 1.9686
[1m 150/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2924 - loss: 1.9634
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2908 - loss: 1.9640
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2898 - loss: 1.9649
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2893 - loss: 1.9649
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2886 - loss: 1.9650
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2878 - loss: 1.9655
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2872 - loss: 1.9659
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2866 - loss: 1.9666
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2861 - loss: 1.9671
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2857 - loss: 1.9678
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2853 - loss: 1.9684
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2850 - loss: 1.9690
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2848 - loss: 1.9696
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2845 - loss: 1.9699
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2844 - loss: 1.9701
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2843 - loss: 1.9702
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2842 - loss: 1.9703
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2842 - loss: 1.9704
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2841 - loss: 1.9704
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2840 - loss: 1.9704
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2840 - loss: 1.9704
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2840 - loss: 1.9703
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2841 - loss: 1.9701
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2841 - loss: 1.9700
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2840 - loss: 1.9699
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2840 - loss: 1.9699
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2839 - loss: 1.9699 - val_accuracy: 0.2760 - val_loss: 1.9332
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 1.8703
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2929 - loss: 2.0084  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2880 - loss: 1.9949
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2838 - loss: 1.9907
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2824 - loss: 1.9866
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2826 - loss: 1.9854
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2828 - loss: 1.9852
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2828 - loss: 1.9854
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2830 - loss: 1.9854
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2834 - loss: 1.9851
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2837 - loss: 1.9846
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2840 - loss: 1.9837
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2842 - loss: 1.9831
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2843 - loss: 1.9826
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2844 - loss: 1.9822
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2845 - loss: 1.9816
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2845 - loss: 1.9811
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2845 - loss: 1.9806
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2845 - loss: 1.9801
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2845 - loss: 1.9796
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2845 - loss: 1.9791
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2846 - loss: 1.9786
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2846 - loss: 1.9782
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2846 - loss: 1.9778
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2846 - loss: 1.9774
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2846 - loss: 1.9770
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2846 - loss: 1.9765
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2847 - loss: 1.9762
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2847 - loss: 1.9758
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2847 - loss: 1.9754
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2847 - loss: 1.9753 - val_accuracy: 0.2809 - val_loss: 1.9377

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 634ms/step
[1m66/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 771us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:06[0m 835ms/step
[1m 60/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 849us/step  
[1m126/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 806us/step
[1m197/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 770us/step
[1m271/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 746us/step
[1m342/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 740us/step
[1m407/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 745us/step
[1m477/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 741us/step
[1m549/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 736us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m68/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 748us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[1m 73/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 695us/step
[1m142/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 712us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 27.77 [%]
Global F1 score (validation) = 25.23 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.08838382 0.17465958 0.08673821 ... 0.00533591 0.10069768 0.00964239]
 [0.08937785 0.15826532 0.07432386 ... 0.00607252 0.09420428 0.00900943]
 [0.10783415 0.17018722 0.12477858 ... 0.00237444 0.22648932 0.0259431 ]
 ...
 [0.17721036 0.1988952  0.13012603 ... 0.00198308 0.18038057 0.03698805]
 [0.08279279 0.1385552  0.09469949 ... 0.0042839  0.11526641 0.0078867 ]
 [0.09556071 0.16236763 0.09573498 ... 0.00447809 0.11795332 0.00599347]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 30.99 [%]
Global accuracy score (test) = 25.06 [%]
Global F1 score (train) = 27.82 [%]
Global F1 score (test) = 21.61 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.00      0.00      0.00       184
 CAMINAR CON MÓVIL O LIBRO       0.18      0.59      0.28       184
       CAMINAR USUAL SPEED       0.04      0.01      0.01       184
            CAMINAR ZIGZAG       0.11      0.08      0.09       184
          DE PIE BARRIENDO       0.21      0.40      0.28       184
   DE PIE DOBLANDO TOALLAS       0.21      0.18      0.20       184
    DE PIE MOVIENDO LIBROS       0.22      0.18      0.20       184
          DE PIE USANDO PC       0.24      0.74      0.36       184
        FASE REPOSO CON K5       0.52      0.62      0.57       184
INCREMENTAL CICLOERGOMETRO       0.38      0.08      0.13       184
           SENTADO LEYENDO       0.16      0.09      0.12       184
         SENTADO USANDO PC       0.06      0.01      0.01       184
      SENTADO VIENDO LA TV       0.31      0.25      0.28       184
   SUBIR Y BAJAR ESCALERAS       0.21      0.19      0.20       184
                    TROTAR       0.97      0.37      0.53       161

                  accuracy                           0.25      2737
                 macro avg       0.26      0.25      0.22      2737
              weighted avg       0.25      0.25      0.21      2737


Accuracy capturado en la ejecución 25: 25.06 [%]
F1-score capturado en la ejecución 25: 21.61 [%]

=== EJECUCIÓN 26 ===

--- TRAIN (ejecución 26) ---

--- TEST (ejecución 26) ---
2025-11-07 14:34:48.157946: 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 14:34:48.169618: 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 00:00:1762522488.182964 3005313 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762522488.187049 3005313 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762522488.196780 3005313 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522488.196796 3005313 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522488.196798 3005313 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522488.196799 3005313 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:34:48.199910: 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 00:00:1762522490.479195 3005313 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762522491.996776 3005454 service.cc:152] XLA service 0x74066800ca80 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762522491.996801 3005454 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:34:52.023848: 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 00:00:1762522492.174313 3005454 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762522493.596972 3005454 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47:54[0m 2s/step - accuracy: 0.0000e+00 - loss: 3.1685
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0536 - loss: 3.2046      
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0605 - loss: 3.2104
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0644 - loss: 3.1971
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0668 - loss: 3.1834
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0687 - loss: 3.1699
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0704 - loss: 3.1567
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0718 - loss: 3.1457
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0730 - loss: 3.1363
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0743 - loss: 3.1264
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0752 - loss: 3.1179
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0761 - loss: 3.1096
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0770 - loss: 3.1014
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0778 - loss: 3.0929
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0786 - loss: 3.0855
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0793 - loss: 3.0781
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0800 - loss: 3.0712
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0807 - loss: 3.0640
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0814 - loss: 3.0570
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0821 - loss: 3.0506
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0827 - loss: 3.0450
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0834 - loss: 3.0387
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0840 - loss: 3.0331
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0846 - loss: 3.0275
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0852 - loss: 3.0218
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0858 - loss: 3.0163
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0863 - loss: 3.0113
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0868 - loss: 3.0060
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0873 - loss: 3.0008
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0876 - loss: 2.9981
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0876 - loss: 2.9980 - val_accuracy: 0.1652 - val_loss: 2.5948
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.9505
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1158 - loss: 2.7333  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1232 - loss: 2.6983
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1238 - loss: 2.6892
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1252 - loss: 2.6849
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1262 - loss: 2.6825
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1275 - loss: 2.6804
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1285 - loss: 2.6784
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1295 - loss: 2.6766
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1305 - loss: 2.6743
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1313 - loss: 2.6721
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1323 - loss: 2.6697
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1335 - loss: 2.6674
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1346 - loss: 2.6650
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1358 - loss: 2.6625
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1368 - loss: 2.6601
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1378 - loss: 2.6578
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1385 - loss: 2.6558
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1393 - loss: 2.6537
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1400 - loss: 2.6515
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1406 - loss: 2.6495
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1411 - loss: 2.6480
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1417 - loss: 2.6462
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1423 - loss: 2.6444
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1428 - loss: 2.6429
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1433 - loss: 2.6412
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1439 - loss: 2.6396
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1444 - loss: 2.6379
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1449 - loss: 2.6364
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1453 - loss: 2.6349
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1458 - loss: 2.6334
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1458 - loss: 2.6332 - val_accuracy: 0.1808 - val_loss: 2.4881
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 2.5984
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1862 - loss: 2.5266  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1783 - loss: 2.5246
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1780 - loss: 2.5201
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1779 - loss: 2.5199
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1770 - loss: 2.5202
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1767 - loss: 2.5207
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1761 - loss: 2.5214
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1755 - loss: 2.5221
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1752 - loss: 2.5223
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1751 - loss: 2.5219
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1753 - loss: 2.5213
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1754 - loss: 2.5207
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1755 - loss: 2.5201
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1757 - loss: 2.5195
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1758 - loss: 2.5189
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1760 - loss: 2.5182
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1761 - loss: 2.5175
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1763 - loss: 2.5168
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1765 - loss: 2.5160
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1766 - loss: 2.5151
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1768 - loss: 2.5141
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1769 - loss: 2.5131
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1771 - loss: 2.5122
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1773 - loss: 2.5112
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1774 - loss: 2.5104
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1776 - loss: 2.5095
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1777 - loss: 2.5088
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1777 - loss: 2.5082
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1778 - loss: 2.5075
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1779 - loss: 2.5071 - val_accuracy: 0.1896 - val_loss: 2.4084
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.3769
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2093 - loss: 2.4227  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2050 - loss: 2.4203
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1998 - loss: 2.4278
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1970 - loss: 2.4337
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1946 - loss: 2.4393
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1928 - loss: 2.4432
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1916 - loss: 2.4461
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1906 - loss: 2.4476
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1900 - loss: 2.4480
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1898 - loss: 2.4478
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1897 - loss: 2.4476
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1896 - loss: 2.4471
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1896 - loss: 2.4465
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1896 - loss: 2.4460
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1895 - loss: 2.4454
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1895 - loss: 2.4448
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1895 - loss: 2.4442
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1895 - loss: 2.4435
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1896 - loss: 2.4428
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1897 - loss: 2.4421
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1898 - loss: 2.4413
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1899 - loss: 2.4405
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1901 - loss: 2.4397
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1902 - loss: 2.4389
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1904 - loss: 2.4381
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1906 - loss: 2.4373
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1908 - loss: 2.4365
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1909 - loss: 2.4357
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1910 - loss: 2.4353 - val_accuracy: 0.1835 - val_loss: 2.3287
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.8463
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1710 - loss: 2.4948  
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1775 - loss: 2.4583
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1823 - loss: 2.4373
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1857 - loss: 2.4221
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1877 - loss: 2.4123
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1900 - loss: 2.4030
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1923 - loss: 2.3963
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1946 - loss: 2.3911
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1963 - loss: 2.3872
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1976 - loss: 2.3839
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1986 - loss: 2.3812
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1994 - loss: 2.3787
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2000 - loss: 2.3770
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2005 - loss: 2.3757
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2011 - loss: 2.3746
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2015 - loss: 2.3735
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2019 - loss: 2.3724
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2024 - loss: 2.3712
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2028 - loss: 2.3701
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2032 - loss: 2.3690
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2035 - loss: 2.3680
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2038 - loss: 2.3670
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2041 - loss: 2.3660
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2044 - loss: 2.3651
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2047 - loss: 2.3641
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2050 - loss: 2.3632
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2052 - loss: 2.3624
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2054 - loss: 2.3615
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2056 - loss: 2.3608 - val_accuracy: 0.2159 - val_loss: 2.2531
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.3201
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2255 - loss: 2.3609  
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2167 - loss: 2.3511
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2137 - loss: 2.3417
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2114 - loss: 2.3372
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2097 - loss: 2.3349
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2085 - loss: 2.3335
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2083 - loss: 2.3309
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2079 - loss: 2.3293
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2081 - loss: 2.3279
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2084 - loss: 2.3265
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2088 - loss: 2.3251
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2093 - loss: 2.3240
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2098 - loss: 2.3230
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2103 - loss: 2.3221
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2107 - loss: 2.3211
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2111 - loss: 2.3202
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2115 - loss: 2.3194
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2118 - loss: 2.3185
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2120 - loss: 2.3177
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2123 - loss: 2.3169
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2125 - loss: 2.3162
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2127 - loss: 2.3154
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2129 - loss: 2.3147
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2130 - loss: 2.3141
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2131 - loss: 2.3135
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2133 - loss: 2.3129
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2134 - loss: 2.3122
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2135 - loss: 2.3116
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2137 - loss: 2.3110
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2137 - loss: 2.3107 - val_accuracy: 0.2228 - val_loss: 2.2141
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.5195
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2204 - loss: 2.2804  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2234 - loss: 2.2767
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2240 - loss: 2.2774
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2245 - loss: 2.2755
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2253 - loss: 2.2744
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2257 - loss: 2.2735
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2261 - loss: 2.2720
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2263 - loss: 2.2714
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2263 - loss: 2.2713
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2264 - loss: 2.2706
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2264 - loss: 2.2699
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2265 - loss: 2.2691
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2265 - loss: 2.2683
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2266 - loss: 2.2677
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2267 - loss: 2.2669
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2269 - loss: 2.2661
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2270 - loss: 2.2655
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2271 - loss: 2.2650
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2272 - loss: 2.2645
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2273 - loss: 2.2640
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2274 - loss: 2.2634
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2275 - loss: 2.2629
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2276 - loss: 2.2625
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2277 - loss: 2.2621
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2278 - loss: 2.2616
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2278 - loss: 2.2613
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2279 - loss: 2.2609
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2279 - loss: 2.2605
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2279 - loss: 2.2602
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2279 - loss: 2.2601 - val_accuracy: 0.2139 - val_loss: 2.1966
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.3125 - loss: 1.9879
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2323 - loss: 2.2374  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2302 - loss: 2.2320
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2271 - loss: 2.2367
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2251 - loss: 2.2390
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2258 - loss: 2.2364
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2264 - loss: 2.2341
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2265 - loss: 2.2330
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2266 - loss: 2.2318
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2267 - loss: 2.2312
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2271 - loss: 2.2307
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2275 - loss: 2.2301
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2279 - loss: 2.2296
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2281 - loss: 2.2293
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2291
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2290
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2289
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2288
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2286
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2285
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2284
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2283
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2282
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2281
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2280
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2278
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2276
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2275
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2273
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2271
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2282 - loss: 2.2269
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2282 - loss: 2.2268 - val_accuracy: 0.2340 - val_loss: 2.1349
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.4055
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1789 - loss: 2.2497  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1931 - loss: 2.2353
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2035 - loss: 2.2301
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2109 - loss: 2.2279
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2165 - loss: 2.2236
[1m 249/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2210 - loss: 2.2188
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2237 - loss: 2.2149
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2253 - loss: 2.2125
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2272 - loss: 2.2104
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2286 - loss: 2.2086
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2299 - loss: 2.2069
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2310 - loss: 2.2054
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2319 - loss: 2.2041
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2327 - loss: 2.2031
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2333 - loss: 2.2023
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2338 - loss: 2.2015
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2342 - loss: 2.2008
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2345 - loss: 2.2003
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2348 - loss: 2.1998
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2351 - loss: 2.1993
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2355 - loss: 2.1989
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2358 - loss: 2.1985
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2360 - loss: 2.1981
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2363 - loss: 2.1977
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2365 - loss: 2.1974
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2366 - loss: 2.1972
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2368 - loss: 2.1969
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2370 - loss: 2.1967
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2371 - loss: 2.1966 - val_accuracy: 0.2278 - val_loss: 2.1402
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 20ms/step - accuracy: 0.3750 - loss: 2.0576
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2618 - loss: 2.2307  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2671 - loss: 2.1985
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2696 - loss: 2.1842
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2670 - loss: 2.1803
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2649 - loss: 2.1802
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2628 - loss: 2.1791
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2610 - loss: 2.1781
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2594 - loss: 2.1779
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2579 - loss: 2.1781
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.1781
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2553 - loss: 2.1780
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1779
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2533 - loss: 2.1779
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2523 - loss: 2.1779
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2516 - loss: 2.1779
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2509 - loss: 2.1779
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2504 - loss: 2.1778
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2500 - loss: 2.1777
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2497 - loss: 2.1776
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2493 - loss: 2.1776
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2490 - loss: 2.1777
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2487 - loss: 2.1778
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2485 - loss: 2.1777
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2483 - loss: 2.1776
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2481 - loss: 2.1774
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2479 - loss: 2.1771
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2478 - loss: 2.1769
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2477 - loss: 2.1767
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2476 - loss: 2.1764
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2476 - loss: 2.1764 - val_accuracy: 0.2407 - val_loss: 2.0821
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.2187
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2459 - loss: 2.1745  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2497 - loss: 2.1709
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2524 - loss: 2.1630
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2530 - loss: 2.1578
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2534 - loss: 2.1557
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1526
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2547 - loss: 2.1501
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2550 - loss: 2.1480
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2548 - loss: 2.1468
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2546 - loss: 2.1463
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2544 - loss: 2.1457
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2540 - loss: 2.1455
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2536 - loss: 2.1452
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2533 - loss: 2.1450
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2530 - loss: 2.1449
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.1448
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2526 - loss: 2.1448
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2524 - loss: 2.1450
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2520 - loss: 2.1452
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2517 - loss: 2.1454
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2515 - loss: 2.1454
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.1454
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2511 - loss: 2.1454
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2509 - loss: 2.1453
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2508 - loss: 2.1452
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2506 - loss: 2.1451
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2504 - loss: 2.1451
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2503 - loss: 2.1449
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.1448
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2502 - loss: 2.1448 - val_accuracy: 0.2464 - val_loss: 2.0775
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.0698
[1m  30/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2407 - loss: 2.0421  
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2319 - loss: 2.0831
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2336 - loss: 2.0956
[1m 148/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2373 - loss: 2.1006
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2395 - loss: 2.1047
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2409 - loss: 2.1080
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2416 - loss: 2.1113
[1m 307/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2418 - loss: 2.1149
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2422 - loss: 2.1178
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2428 - loss: 2.1200
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2432 - loss: 2.1223
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2436 - loss: 2.1242
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2439 - loss: 2.1260
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2440 - loss: 2.1275
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2441 - loss: 2.1289
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2442 - loss: 2.1301
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2442 - loss: 2.1309
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2443 - loss: 2.1315
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2444 - loss: 2.1319
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2446 - loss: 2.1323
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2447 - loss: 2.1328
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2447 - loss: 2.1332
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2447 - loss: 2.1335
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2447 - loss: 2.1339
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2447 - loss: 2.1341
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2448 - loss: 2.1342
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2448 - loss: 2.1343
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2449 - loss: 2.1343
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2450 - loss: 2.1342
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2450 - loss: 2.1342 - val_accuracy: 0.2366 - val_loss: 2.0704
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.9407
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2296 - loss: 2.0919  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2337 - loss: 2.1122
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2372 - loss: 2.1155
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2384 - loss: 2.1193
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2397 - loss: 2.1219
[1m 251/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2408 - loss: 2.1246
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2416 - loss: 2.1252
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2425 - loss: 2.1246
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2433 - loss: 2.1239
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2443 - loss: 2.1229
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1220
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2456 - loss: 2.1212
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2461 - loss: 2.1206
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2465 - loss: 2.1199
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2469 - loss: 2.1192
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2472 - loss: 2.1185
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2475 - loss: 2.1179
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2477 - loss: 2.1174
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2480 - loss: 2.1168
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2483 - loss: 2.1161
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2485 - loss: 2.1155
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2488 - loss: 2.1148
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2489 - loss: 2.1143
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2491 - loss: 2.1137
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2493 - loss: 2.1131
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2494 - loss: 2.1125
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2495 - loss: 2.1120
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2497 - loss: 2.1116
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2498 - loss: 2.1113 - val_accuracy: 0.2381 - val_loss: 2.0483
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.1875 - loss: 2.3512
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2497 - loss: 2.1106  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1050
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2570 - loss: 2.1025
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2574 - loss: 2.1009
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2561 - loss: 2.1018
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2550 - loss: 2.1025
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2545 - loss: 2.1020
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1015
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2540 - loss: 2.1014
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2537 - loss: 2.1013
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2533 - loss: 2.1014
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2530 - loss: 2.1013
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.1013
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2526 - loss: 2.1010
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2524 - loss: 2.1007
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2522 - loss: 2.1005
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2521 - loss: 2.1002
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2520 - loss: 2.1001
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2519 - loss: 2.1000
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2518 - loss: 2.0999
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2518 - loss: 2.0998
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2518 - loss: 2.0996
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2519 - loss: 2.0994
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2519 - loss: 2.0992
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2520 - loss: 2.0991
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2520 - loss: 2.0988
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2521 - loss: 2.0985
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2522 - loss: 2.0983
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2523 - loss: 2.0981 - val_accuracy: 0.2390 - val_loss: 2.0532
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.7590
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2444 - loss: 2.1575  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2492 - loss: 2.1184
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2505 - loss: 2.1108
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2507 - loss: 2.1081
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2515 - loss: 2.1064
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2528 - loss: 2.1037
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2539 - loss: 2.1016
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2542 - loss: 2.1007
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2545 - loss: 2.0995
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2550 - loss: 2.0978
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2552 - loss: 2.0962
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2554 - loss: 2.0947
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2556 - loss: 2.0935
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2558 - loss: 2.0923
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.0916
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0908
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0902
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0896
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.0889
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2566 - loss: 2.0884
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0880
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0876
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0872
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.0868
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.0865
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.0862
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2569 - loss: 2.0858
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2570 - loss: 2.0855
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0852
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2571 - loss: 2.0851 - val_accuracy: 0.2479 - val_loss: 2.0277
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.2774
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2849 - loss: 2.0795  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0818
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2578 - loss: 2.0815
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2553 - loss: 2.0807
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2556 - loss: 2.0803
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0822
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2566 - loss: 2.0828
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2574 - loss: 2.0818
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2582 - loss: 2.0805
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2586 - loss: 2.0796
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2590 - loss: 2.0790
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2594 - loss: 2.0781
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2598 - loss: 2.0770
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0762
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2607 - loss: 2.0757
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0752
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2613 - loss: 2.0750
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2616 - loss: 2.0749
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2618 - loss: 2.0747
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2620 - loss: 2.0745
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2622 - loss: 2.0744
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2624 - loss: 2.0742
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2626 - loss: 2.0739
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2628 - loss: 2.0736
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0734
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0733
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2632 - loss: 2.0732
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0731
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2634 - loss: 2.0730
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2634 - loss: 2.0729 - val_accuracy: 0.2549 - val_loss: 2.0067
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.1244
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2776 - loss: 1.9864  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0021
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2695 - loss: 2.0072
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0092
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2697 - loss: 2.0133
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2689 - loss: 2.0175
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0208
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0228
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0247
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0264
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0281
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2673 - loss: 2.0298
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0315
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0330
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0342
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2669 - loss: 2.0353
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0363
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0369
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0375
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0380
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0387
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0393
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2666 - loss: 2.0398
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0403
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0407
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0411
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0415
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0419
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2664 - loss: 2.0423 - val_accuracy: 0.2586 - val_loss: 1.9982
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.1474
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2432 - loss: 2.1022  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2512 - loss: 2.0897
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0848
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0810
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2586 - loss: 2.0795
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2596 - loss: 2.0771
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0753
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2607 - loss: 2.0732
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0713
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2613 - loss: 2.0697
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2617 - loss: 2.0684
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2621 - loss: 2.0670
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2624 - loss: 2.0657
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2628 - loss: 2.0643
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0628
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2635 - loss: 2.0615
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0605
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2640 - loss: 2.0596
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2643 - loss: 2.0588
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2646 - loss: 2.0580
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2648 - loss: 2.0573
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0568
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0562
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2654 - loss: 2.0557
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0553
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0549
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0545
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0541
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0537
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2659 - loss: 2.0535 - val_accuracy: 0.2514 - val_loss: 1.9918
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.8563
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3031 - loss: 1.9889  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2940 - loss: 2.0018
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2929 - loss: 2.0003
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2905 - loss: 2.0046
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2875 - loss: 2.0096
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2863 - loss: 2.0117
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2857 - loss: 2.0135
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2851 - loss: 2.0145
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2846 - loss: 2.0150
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2838 - loss: 2.0155
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2833 - loss: 2.0158
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2831 - loss: 2.0157
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2831 - loss: 2.0160
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2830 - loss: 2.0161
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2829 - loss: 2.0163
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2828 - loss: 2.0165
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2825 - loss: 2.0169
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2823 - loss: 2.0171
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2821 - loss: 2.0175
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2818 - loss: 2.0178
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2816 - loss: 2.0183
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2814 - loss: 2.0187
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2811 - loss: 2.0191
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2809 - loss: 2.0194
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2807 - loss: 2.0198
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2805 - loss: 2.0202
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2803 - loss: 2.0206
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 2.0209
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2800 - loss: 2.0211 - val_accuracy: 0.2588 - val_loss: 1.9994
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.1476
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0197  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2723 - loss: 2.0165
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0114
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0080
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2771 - loss: 2.0054
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2782 - loss: 2.0044
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2787 - loss: 2.0044
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2788 - loss: 2.0050
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2784 - loss: 2.0060
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2776 - loss: 2.0074
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2769 - loss: 2.0088
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2765 - loss: 2.0098
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0108
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 2.0116
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2758 - loss: 2.0122
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2757 - loss: 2.0128
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2755 - loss: 2.0132
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2754 - loss: 2.0136
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0140
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0143
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2751 - loss: 2.0144
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2751 - loss: 2.0146
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0147
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0148
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0149
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0151
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0152
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0154
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2746 - loss: 2.0156 - val_accuracy: 0.2627 - val_loss: 1.9753
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.8413
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2948 - loss: 1.9518  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2769 - loss: 1.9814
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2737 - loss: 1.9863
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2727 - loss: 1.9916
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2715 - loss: 1.9940
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2714 - loss: 1.9944
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2715 - loss: 1.9946
[1m 305/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2714 - loss: 1.9950
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2715 - loss: 1.9958
[1m 381/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2716 - loss: 1.9965
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2718 - loss: 1.9969
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2720 - loss: 1.9975
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2721 - loss: 1.9981
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2722 - loss: 1.9988
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2724 - loss: 1.9993
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2726 - loss: 1.9998
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2728 - loss: 2.0001
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2729 - loss: 2.0004
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0007
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0011
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0015
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0018
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0021
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2733 - loss: 2.0023
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2733 - loss: 2.0026
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0029
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0031
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0033
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0035
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0038
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2732 - loss: 2.0038 - val_accuracy: 0.2570 - val_loss: 1.9701
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.1023
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2723 - loss: 2.0229  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2760 - loss: 2.0211
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2786 - loss: 2.0226
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2799 - loss: 2.0233
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2803 - loss: 2.0235
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2815 - loss: 2.0217
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2824 - loss: 2.0201
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2830 - loss: 2.0182
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2833 - loss: 2.0165
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2836 - loss: 2.0146
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2838 - loss: 2.0132
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2837 - loss: 2.0123
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2835 - loss: 2.0117
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2833 - loss: 2.0113
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2830 - loss: 2.0109
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2827 - loss: 2.0105
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2825 - loss: 2.0101
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2822 - loss: 2.0097
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2820 - loss: 2.0094
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2818 - loss: 2.0091
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2816 - loss: 2.0088
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2815 - loss: 2.0084
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2814 - loss: 2.0080
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2813 - loss: 2.0077
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2813 - loss: 2.0073
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2813 - loss: 2.0071
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2813 - loss: 2.0067
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2813 - loss: 2.0064
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2813 - loss: 2.0061
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2813 - loss: 2.0060 - val_accuracy: 0.2672 - val_loss: 1.9641
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 1.9542
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2518 - loss: 2.0332  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0227
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2629 - loss: 2.0121
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0090
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0080
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0082
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0086
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2728 - loss: 2.0087
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2730 - loss: 2.0089
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2733 - loss: 2.0084
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2736 - loss: 2.0074
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2739 - loss: 2.0065
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0057
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2741 - loss: 2.0052
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2742 - loss: 2.0050
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2742 - loss: 2.0049
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2743 - loss: 2.0047
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0047
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2746 - loss: 2.0045
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0042
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2751 - loss: 2.0039
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2753 - loss: 2.0037
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2755 - loss: 2.0034
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2757 - loss: 2.0031
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2758 - loss: 2.0028
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 2.0026
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2760 - loss: 2.0023
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 2.0021
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2762 - loss: 2.0018
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2762 - loss: 2.0018 - val_accuracy: 0.2572 - val_loss: 1.9837
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.0270
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3358 - loss: 1.9447  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3168 - loss: 1.9540
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3093 - loss: 1.9637
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3054 - loss: 1.9676
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3021 - loss: 1.9728
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2993 - loss: 1.9768
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2972 - loss: 1.9772
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2956 - loss: 1.9773
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2945 - loss: 1.9772
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2936 - loss: 1.9772
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2929 - loss: 1.9773
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2922 - loss: 1.9774
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2917 - loss: 1.9772
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2912 - loss: 1.9770
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2907 - loss: 1.9769
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2902 - loss: 1.9769
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2898 - loss: 1.9770
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2894 - loss: 1.9771
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2891 - loss: 1.9771
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2887 - loss: 1.9772
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2884 - loss: 1.9773
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2880 - loss: 1.9774
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2877 - loss: 1.9773
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2874 - loss: 1.9774
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2871 - loss: 1.9776
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2868 - loss: 1.9777
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2866 - loss: 1.9779
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2864 - loss: 1.9780
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2862 - loss: 1.9780
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2861 - loss: 1.9781 - val_accuracy: 0.2673 - val_loss: 1.9422
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.6341
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2685 - loss: 1.9496  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2770 - loss: 1.9703
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2789 - loss: 1.9801
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2797 - loss: 1.9849
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2813 - loss: 1.9851
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2820 - loss: 1.9848
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2824 - loss: 1.9846
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2827 - loss: 1.9848
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2829 - loss: 1.9846
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2828 - loss: 1.9848
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2825 - loss: 1.9851
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2822 - loss: 1.9851
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2821 - loss: 1.9849
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2820 - loss: 1.9849
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2818 - loss: 1.9849
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2816 - loss: 1.9847
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2815 - loss: 1.9844
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2815 - loss: 1.9842
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2815 - loss: 1.9840
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2814 - loss: 1.9839
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2815 - loss: 1.9838
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2815 - loss: 1.9837
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2815 - loss: 1.9836
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2816 - loss: 1.9834
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2816 - loss: 1.9833
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2817 - loss: 1.9833
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2818 - loss: 1.9831
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2819 - loss: 1.9829
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2820 - loss: 1.9827
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2820 - loss: 1.9827 - val_accuracy: 0.2668 - val_loss: 1.9386

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 649ms/step
[1m66/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 771us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:02[0m 827ms/step
[1m 62/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 820us/step  
[1m130/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 778us/step
[1m204/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 744us/step
[1m274/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 737us/step
[1m344/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 733us/step
[1m404/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 749us/step
[1m478/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 739us/step
[1m551/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 732us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m63/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 814us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 74/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 689us/step
[1m148/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 686us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 28.09 [%]
Global F1 score (validation) = 25.83 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[1.51006028e-01 1.93067014e-01 1.48667380e-01 ... 1.39257894e-03
  1.44503206e-01 2.99002901e-02]
 [1.34845272e-01 1.72751561e-01 1.39607057e-01 ... 2.20439001e-03
  1.61037594e-01 2.86971275e-02]
 [1.10931709e-01 1.16470955e-01 1.24672100e-01 ... 7.08652614e-03
  1.38035119e-01 1.61805693e-02]
 ...
 [1.69447750e-01 1.73425511e-01 1.51989132e-01 ... 2.28406140e-03
  1.76038504e-01 2.93711089e-02]
 [1.69569597e-01 2.13081196e-01 1.81881085e-01 ... 1.71062857e-04
  1.90124243e-01 7.08509833e-02]
 [8.46691281e-02 1.08566292e-01 8.47242251e-02 ... 8.82262085e-03
  8.95733535e-02 1.22585045e-02]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 31.3 [%]
Global accuracy score (test) = 27.11 [%]
Global F1 score (train) = 29.1 [%]
Global F1 score (test) = 25.58 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.09      0.03      0.05       184
 CAMINAR CON MÓVIL O LIBRO       0.13      0.27      0.17       184
       CAMINAR USUAL SPEED       0.10      0.04      0.06       184
            CAMINAR ZIGZAG       0.19      0.29      0.23       184
          DE PIE BARRIENDO       0.22      0.66      0.33       184
   DE PIE DOBLANDO TOALLAS       0.17      0.07      0.10       184
    DE PIE MOVIENDO LIBROS       0.18      0.17      0.17       184
          DE PIE USANDO PC       0.35      0.70      0.47       184
        FASE REPOSO CON K5       0.96      0.62      0.76       184
INCREMENTAL CICLOERGOMETRO       0.00      0.00      0.00       184
           SENTADO LEYENDO       0.19      0.25      0.22       184
         SENTADO USANDO PC       0.19      0.17      0.18       184
      SENTADO VIENDO LA TV       0.57      0.34      0.43       184
   SUBIR Y BAJAR ESCALERAS       0.23      0.08      0.12       184
                    TROTAR       1.00      0.38      0.55       161

                  accuracy                           0.27      2737
                 macro avg       0.30      0.27      0.26      2737
              weighted avg       0.30      0.27      0.25      2737


Accuracy capturado en la ejecución 26: 27.11 [%]
F1-score capturado en la ejecución 26: 25.58 [%]

=== EJECUCIÓN 27 ===

--- TRAIN (ejecución 27) ---

--- TEST (ejecución 27) ---
2025-11-07 14:35:55.631390: 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 14:35:55.643354: 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 00:00:1762522555.657497 3009049 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762522555.661922 3009049 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762522555.672423 3009049 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522555.672444 3009049 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522555.672445 3009049 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522555.672447 3009049 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:35:55.675816: 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 00:00:1762522557.973160 3009049 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762522559.462796 3009185 service.cc:152] XLA service 0x7701ac00b8a0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762522559.462830 3009185 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:35:59.493454: 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 00:00:1762522559.642535 3009185 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762522561.057687 3009185 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47:30[0m 2s/step - accuracy: 0.0625 - loss: 3.5135
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0632 - loss: 3.2945  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0666 - loss: 3.2313
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0671 - loss: 3.2045
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0682 - loss: 3.1820
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0698 - loss: 3.1643
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0714 - loss: 3.1496
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0728 - loss: 3.1375
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0740 - loss: 3.1266
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0750 - loss: 3.1170
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0759 - loss: 3.1083
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0766 - loss: 3.1005
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0774 - loss: 3.0929
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0780 - loss: 3.0862
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0786 - loss: 3.0789
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0791 - loss: 3.0723
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0796 - loss: 3.0661
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0800 - loss: 3.0602
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0805 - loss: 3.0543
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0810 - loss: 3.0484
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0815 - loss: 3.0425
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0820 - loss: 3.0369
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0824 - loss: 3.0324
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0828 - loss: 3.0282
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0832 - loss: 3.0236
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0837 - loss: 3.0190
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0841 - loss: 3.0145
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0845 - loss: 3.0102
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0850 - loss: 3.0057
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0853 - loss: 3.0018
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0854 - loss: 3.0010
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0854 - loss: 3.0009 - val_accuracy: 0.1434 - val_loss: 2.5761
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.1250 - loss: 2.7295
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1025 - loss: 2.7280  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1067 - loss: 2.7319
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1102 - loss: 2.7284
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1136 - loss: 2.7229
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1162 - loss: 2.7186
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1178 - loss: 2.7159
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1185 - loss: 2.7144
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1190 - loss: 2.7133
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1194 - loss: 2.7126
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1197 - loss: 2.7118
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1200 - loss: 2.7109
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1202 - loss: 2.7099
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1205 - loss: 2.7087
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1209 - loss: 2.7076
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1213 - loss: 2.7064
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1217 - loss: 2.7050
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1221 - loss: 2.7035
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1226 - loss: 2.7020
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1231 - loss: 2.7003
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1238 - loss: 2.6984
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1243 - loss: 2.6965
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1249 - loss: 2.6948
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1254 - loss: 2.6931
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1259 - loss: 2.6915
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1264 - loss: 2.6899
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1269 - loss: 2.6883
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1274 - loss: 2.6866
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1279 - loss: 2.6849
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1283 - loss: 2.6833
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1286 - loss: 2.6823 - val_accuracy: 0.1848 - val_loss: 2.4646
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.4047
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1644 - loss: 2.5060  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1630 - loss: 2.5181
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1638 - loss: 2.5224
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1640 - loss: 2.5254
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1647 - loss: 2.5286
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1656 - loss: 2.5304
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1667 - loss: 2.5312
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1673 - loss: 2.5316
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1678 - loss: 2.5320
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1683 - loss: 2.5321
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1687 - loss: 2.5321
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1691 - loss: 2.5320
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1695 - loss: 2.5317
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1699 - loss: 2.5315
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1701 - loss: 2.5312
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1703 - loss: 2.5308
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1704 - loss: 2.5305
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1706 - loss: 2.5301
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1708 - loss: 2.5296
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1709 - loss: 2.5292
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1710 - loss: 2.5288
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1711 - loss: 2.5284
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1712 - loss: 2.5280
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1714 - loss: 2.5275
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1715 - loss: 2.5270
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1716 - loss: 2.5265
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1717 - loss: 2.5259
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1719 - loss: 2.5254
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1721 - loss: 2.5247
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1722 - loss: 2.5243 - val_accuracy: 0.2161 - val_loss: 2.3815
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.1250 - loss: 2.5995
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1825 - loss: 2.5221  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1875 - loss: 2.4914
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1898 - loss: 2.4746
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1888 - loss: 2.4675
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1874 - loss: 2.4652
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1861 - loss: 2.4639
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1853 - loss: 2.4623
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1847 - loss: 2.4607
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1840 - loss: 2.4595
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1836 - loss: 2.4581
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1833 - loss: 2.4572
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1831 - loss: 2.4566
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1831 - loss: 2.4560
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1832 - loss: 2.4553
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1834 - loss: 2.4543
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1836 - loss: 2.4532
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1838 - loss: 2.4523
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1840 - loss: 2.4515
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1842 - loss: 2.4506
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1844 - loss: 2.4497
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1846 - loss: 2.4488
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1848 - loss: 2.4479
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1851 - loss: 2.4470
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1854 - loss: 2.4460
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1856 - loss: 2.4451
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1859 - loss: 2.4443
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1862 - loss: 2.4434
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1865 - loss: 2.4425
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1868 - loss: 2.4415
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1869 - loss: 2.4412 - val_accuracy: 0.2342 - val_loss: 2.2911
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.2528
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2187 - loss: 2.3469  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2131 - loss: 2.3546
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2113 - loss: 2.3576
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2086 - loss: 2.3611
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2064 - loss: 2.3636
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2053 - loss: 2.3640
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2051 - loss: 2.3638
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2053 - loss: 2.3632
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2057 - loss: 2.3626
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2061 - loss: 2.3620
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2065 - loss: 2.3613
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2068 - loss: 2.3609
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2069 - loss: 2.3605
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2070 - loss: 2.3602
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2070 - loss: 2.3599
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2070 - loss: 2.3596
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2069 - loss: 2.3594
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2069 - loss: 2.3591
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2070 - loss: 2.3586
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2070 - loss: 2.3581
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2071 - loss: 2.3576
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2072 - loss: 2.3571
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2072 - loss: 2.3566
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2073 - loss: 2.3562
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2073 - loss: 2.3557
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2074 - loss: 2.3552
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2074 - loss: 2.3548
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2075 - loss: 2.3544
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2075 - loss: 2.3543 - val_accuracy: 0.2488 - val_loss: 2.2225
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.0625 - loss: 2.7315
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1997 - loss: 2.3739  
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2027 - loss: 2.3643
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2093 - loss: 2.3525
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2118 - loss: 2.3451
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2122 - loss: 2.3404
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2120 - loss: 2.3375
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2123 - loss: 2.3346
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2130 - loss: 2.3314
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2137 - loss: 2.3288
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2141 - loss: 2.3270
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2143 - loss: 2.3252
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2145 - loss: 2.3236
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2146 - loss: 2.3223
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2148 - loss: 2.3213
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2148 - loss: 2.3203
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2149 - loss: 2.3195
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2150 - loss: 2.3186
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2150 - loss: 2.3181
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2150 - loss: 2.3175
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2151 - loss: 2.3169
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2152 - loss: 2.3163
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2152 - loss: 2.3158
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2152 - loss: 2.3152
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2153 - loss: 2.3147
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2153 - loss: 2.3143
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2153 - loss: 2.3138
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2153 - loss: 2.3134
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2154 - loss: 2.3129
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2154 - loss: 2.3124
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2155 - loss: 2.3123 - val_accuracy: 0.2414 - val_loss: 2.1764
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.2500 - loss: 2.2354
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2360 - loss: 2.2666  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2268 - loss: 2.2674
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2251 - loss: 2.2649
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2253 - loss: 2.2619
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2247 - loss: 2.2606
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2240 - loss: 2.2602
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2234 - loss: 2.2610
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2229 - loss: 2.2614
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2226 - loss: 2.2613
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2223 - loss: 2.2614
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2222 - loss: 2.2615
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2224 - loss: 2.2611
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2226 - loss: 2.2608
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2228 - loss: 2.2609
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2229 - loss: 2.2608
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2231 - loss: 2.2606
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2233 - loss: 2.2604
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2235 - loss: 2.2602
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2236 - loss: 2.2600
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2238 - loss: 2.2598
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2239 - loss: 2.2597
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2240 - loss: 2.2595
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2241 - loss: 2.2593
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2242 - loss: 2.2589
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2243 - loss: 2.2587
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2245 - loss: 2.2585
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2246 - loss: 2.2582
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2247 - loss: 2.2579
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2248 - loss: 2.2576
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2248 - loss: 2.2575 - val_accuracy: 0.2498 - val_loss: 2.1327
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.3843
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2682 - loss: 2.2119  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2484 - loss: 2.2238
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2407 - loss: 2.2338
[1m 169/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2360 - loss: 2.2411
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2335 - loss: 2.2447
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2317 - loss: 2.2466
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2305 - loss: 2.2468
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2297 - loss: 2.2461
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2294 - loss: 2.2451
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2290 - loss: 2.2441
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2289 - loss: 2.2430
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2290 - loss: 2.2418
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2290 - loss: 2.2405
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2292 - loss: 2.2392
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2292 - loss: 2.2381
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2293 - loss: 2.2370
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2293 - loss: 2.2359
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2294 - loss: 2.2347
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2296 - loss: 2.2337
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2298 - loss: 2.2326
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2300 - loss: 2.2317
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2302 - loss: 2.2309
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2303 - loss: 2.2301
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2305 - loss: 2.2293
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2307 - loss: 2.2286
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2308 - loss: 2.2280
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2309 - loss: 2.2275
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2310 - loss: 2.2269
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2311 - loss: 2.2264
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2311 - loss: 2.2264 - val_accuracy: 0.2666 - val_loss: 2.0947
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.2500 - loss: 2.2995
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2582 - loss: 2.1611  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2488 - loss: 2.1686
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2463 - loss: 2.1722
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2461 - loss: 2.1746
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2466 - loss: 2.1749
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2473 - loss: 2.1746
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2482 - loss: 2.1738
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2483 - loss: 2.1736
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2480 - loss: 2.1740
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2479 - loss: 2.1736
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2478 - loss: 2.1734
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2477 - loss: 2.1733
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2475 - loss: 2.1733
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2474 - loss: 2.1733
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2472 - loss: 2.1731
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2471 - loss: 2.1730
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2470 - loss: 2.1728
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2468 - loss: 2.1728
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2467 - loss: 2.1727
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2466 - loss: 2.1726
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2465 - loss: 2.1726
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2464 - loss: 2.1725
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2463 - loss: 2.1725
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2462 - loss: 2.1727
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2462 - loss: 2.1728
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2461 - loss: 2.1728
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2460 - loss: 2.1728
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2460 - loss: 2.1729
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2459 - loss: 2.1729
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2459 - loss: 2.1729 - val_accuracy: 0.2746 - val_loss: 2.0704
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.0625 - loss: 2.4642
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2525 - loss: 2.1376  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2645 - loss: 2.1455
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2649 - loss: 2.1477
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2639 - loss: 2.1473
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2618 - loss: 2.1493
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2598 - loss: 2.1515
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2584 - loss: 2.1526
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2576 - loss: 2.1527
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2566 - loss: 2.1529
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2556 - loss: 2.1534
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.1538
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2542 - loss: 2.1542
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2536 - loss: 2.1546
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2531 - loss: 2.1549
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2526 - loss: 2.1552
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2523 - loss: 2.1554
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2520 - loss: 2.1556
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2518 - loss: 2.1556
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2515 - loss: 2.1557
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.1557
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2511 - loss: 2.1558
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2510 - loss: 2.1558
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2508 - loss: 2.1558
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2507 - loss: 2.1557
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2506 - loss: 2.1557
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2506 - loss: 2.1556
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2505 - loss: 2.1555
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2504 - loss: 2.1554
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2504 - loss: 2.1554 - val_accuracy: 0.2668 - val_loss: 2.0596
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5000 - loss: 1.8584
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2870 - loss: 2.0562  
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0976
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2589 - loss: 2.1106
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2538 - loss: 2.1203
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2507 - loss: 2.1263
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2498 - loss: 2.1280
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2495 - loss: 2.1278
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2497 - loss: 2.1275
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2499 - loss: 2.1276
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.1281
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.1286
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2504 - loss: 2.1290
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2507 - loss: 2.1294
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2508 - loss: 2.1298
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2509 - loss: 2.1302
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2511 - loss: 2.1304
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2512 - loss: 2.1307
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.1309
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.1310
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.1311
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2514 - loss: 2.1311
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2515 - loss: 2.1311
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2515 - loss: 2.1312
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2516 - loss: 2.1311
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2517 - loss: 2.1311
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2517 - loss: 2.1310
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2517 - loss: 2.1309
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2518 - loss: 2.1308
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2519 - loss: 2.1307
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2520 - loss: 2.1306 - val_accuracy: 0.2651 - val_loss: 2.0439
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 1.9520
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2431 - loss: 2.1539  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1538
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2446 - loss: 2.1484
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2464 - loss: 2.1427
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2481 - loss: 2.1393
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2491 - loss: 2.1370
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2500 - loss: 2.1346
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2507 - loss: 2.1327
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2513 - loss: 2.1308
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2519 - loss: 2.1291
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2524 - loss: 2.1279
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2527 - loss: 2.1270
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2529 - loss: 2.1263
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2533 - loss: 2.1254
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2536 - loss: 2.1246
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2539 - loss: 2.1240
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2541 - loss: 2.1233
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2542 - loss: 2.1228
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1223
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1218
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2544 - loss: 2.1214
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1212
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1209
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1207
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1204
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1201
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1198
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1194
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.1191
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2543 - loss: 2.1191 - val_accuracy: 0.2753 - val_loss: 2.0160
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.5625 - loss: 1.8793
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2632 - loss: 2.1273  
[1m  69/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2537 - loss: 2.1138
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2474 - loss: 2.1122
[1m 146/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2468 - loss: 2.1076
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2473 - loss: 2.1047
[1m 225/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2478 - loss: 2.1022
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2481 - loss: 2.0999
[1m 303/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2490 - loss: 2.0975
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2494 - loss: 2.0962
[1m 383/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2497 - loss: 2.0953
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2499 - loss: 2.0949
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2502 - loss: 2.0950
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2504 - loss: 2.0949
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2506 - loss: 2.0946
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2509 - loss: 2.0941
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2511 - loss: 2.0940
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2511 - loss: 2.0940
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2511 - loss: 2.0941
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2511 - loss: 2.0941
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2512 - loss: 2.0940
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.0939
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.0936
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2514 - loss: 2.0935
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.0934
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2514 - loss: 2.0933
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2514 - loss: 2.0932
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2515 - loss: 2.0931
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2515 - loss: 2.0929
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2516 - loss: 2.0928
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2517 - loss: 2.0927
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2517 - loss: 2.0927 - val_accuracy: 0.2784 - val_loss: 2.0133
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 1.8610
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2681 - loss: 2.0550  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0611
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0601
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0625
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2705 - loss: 2.0641
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0648
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0643
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0639
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0643
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0646
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0650
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0651
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0652
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0652
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0652
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0653
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0657
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0659
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0661
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2706 - loss: 2.0661
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2706 - loss: 2.0661
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2705 - loss: 2.0662
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0663
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0664
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0664
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0666
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2697 - loss: 2.0667
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2695 - loss: 2.0669
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0669
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2693 - loss: 2.0670 - val_accuracy: 0.2757 - val_loss: 1.9910
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 1.8958
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0287  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2766 - loss: 2.0474
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2779 - loss: 2.0467
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2797 - loss: 2.0431
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2795 - loss: 2.0425
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2782 - loss: 2.0426
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2765 - loss: 2.0442
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0462
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2735 - loss: 2.0482
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2724 - loss: 2.0501
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0515
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0529
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2701 - loss: 2.0542
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2695 - loss: 2.0553
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2690 - loss: 2.0563
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2686 - loss: 2.0571
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2683 - loss: 2.0576
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2680 - loss: 2.0580
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0584
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0586
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2673 - loss: 2.0588
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0588
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0588
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0589
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0588
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0586
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0585
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0583
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2667 - loss: 2.0583 - val_accuracy: 0.2820 - val_loss: 1.9867
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.0625 - loss: 2.4467
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2258 - loss: 2.1437  
[1m  70/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2420 - loss: 2.1135
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2482 - loss: 2.0987
[1m 149/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2530 - loss: 2.0875
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2577 - loss: 2.0782
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2615 - loss: 2.0708
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0665
[1m 307/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0636
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0605
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2680 - loss: 2.0577
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0554
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0535
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0523
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0510
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0495
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0484
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0476
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2714 - loss: 2.0468
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0461
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0454
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2719 - loss: 2.0448
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2720 - loss: 2.0443
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0438
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0433
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0429
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0427
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0425
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0423
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2720 - loss: 2.0422
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2720 - loss: 2.0421 - val_accuracy: 0.2766 - val_loss: 1.9762
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.7809
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2763 - loss: 1.9759  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2741 - loss: 2.0003
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2764 - loss: 2.0074
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2760 - loss: 2.0138
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2757 - loss: 2.0178
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2754 - loss: 2.0193
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2754 - loss: 2.0215
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2755 - loss: 2.0232
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2755 - loss: 2.0245
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2753 - loss: 2.0258
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2751 - loss: 2.0272
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0288
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0298
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0306
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0312
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2746 - loss: 2.0316
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0321
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0324
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2743 - loss: 2.0326
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2742 - loss: 2.0327
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2742 - loss: 2.0327
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2742 - loss: 2.0326
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2741 - loss: 2.0326
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2741 - loss: 2.0325
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2741 - loss: 2.0323
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2741 - loss: 2.0322
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0322
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0322
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2740 - loss: 2.0322
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2740 - loss: 2.0322 - val_accuracy: 0.2864 - val_loss: 1.9688
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.1590
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0301  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0211
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0280
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2701 - loss: 2.0296
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2706 - loss: 2.0292
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0284
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0286
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2726 - loss: 2.0285
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2730 - loss: 2.0279
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2734 - loss: 2.0274
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2739 - loss: 2.0268
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2743 - loss: 2.0266
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0264
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0263
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0261
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0259
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0257
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2744 - loss: 2.0255
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0253
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2746 - loss: 2.0250
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0247
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0245
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0242
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0240
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2751 - loss: 2.0237
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0235
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0233
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2753 - loss: 2.0232
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2753 - loss: 2.0231
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2753 - loss: 2.0231 - val_accuracy: 0.2938 - val_loss: 1.9667
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 1.9420
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2851 - loss: 1.9746  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2759 - loss: 2.0041
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0098
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2743 - loss: 2.0129
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0136
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2753 - loss: 2.0136
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2754 - loss: 2.0142
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2754 - loss: 2.0146
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0147
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0145
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0143
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0142
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2751 - loss: 2.0141
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0139
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0137
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0132
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0127
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0123
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0120
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0117
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0116
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2748 - loss: 2.0116
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0116
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0116
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2751 - loss: 2.0116
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0117
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2753 - loss: 2.0116
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2754 - loss: 2.0116
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2755 - loss: 2.0116
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2755 - loss: 2.0116 - val_accuracy: 0.2834 - val_loss: 1.9536
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.3125 - loss: 1.9022
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3176 - loss: 1.9236  
[1m  71/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3043 - loss: 1.9457
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2991 - loss: 1.9584
[1m 150/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2953 - loss: 1.9665
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2931 - loss: 1.9727
[1m 226/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2915 - loss: 1.9775
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2899 - loss: 1.9825
[1m 304/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2886 - loss: 1.9860
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2877 - loss: 1.9883
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2871 - loss: 1.9901
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2865 - loss: 1.9915
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2858 - loss: 1.9933
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2852 - loss: 1.9947
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2849 - loss: 1.9959
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2845 - loss: 1.9966
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2843 - loss: 1.9971
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2841 - loss: 1.9975
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2839 - loss: 1.9978
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2837 - loss: 1.9980
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2835 - loss: 1.9982
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2834 - loss: 1.9984
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2833 - loss: 1.9985
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2832 - loss: 1.9987
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2831 - loss: 1.9989
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2830 - loss: 1.9990
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2829 - loss: 1.9993
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2828 - loss: 1.9995
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2827 - loss: 1.9996
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2826 - loss: 1.9997
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2825 - loss: 1.9997 - val_accuracy: 0.2770 - val_loss: 1.9824
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3750 - loss: 2.0951
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3126 - loss: 1.9650  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2980 - loss: 1.9920
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2903 - loss: 2.0031
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2860 - loss: 2.0084
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2835 - loss: 2.0114
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2823 - loss: 2.0112
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2817 - loss: 2.0108
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2811 - loss: 2.0106
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2805 - loss: 2.0110
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2802 - loss: 2.0105
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 2.0102
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2802 - loss: 2.0098
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2803 - loss: 2.0094
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 2.0088
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 2.0083
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2808 - loss: 2.0076
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2810 - loss: 2.0067
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2812 - loss: 2.0061
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2813 - loss: 2.0054
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2815 - loss: 2.0048
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2818 - loss: 2.0042
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2820 - loss: 2.0037
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2822 - loss: 2.0031
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2824 - loss: 2.0026
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2825 - loss: 2.0022
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2827 - loss: 2.0018
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2827 - loss: 2.0014
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2828 - loss: 2.0011
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2828 - loss: 2.0008
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2828 - loss: 2.0008 - val_accuracy: 0.2955 - val_loss: 1.9425
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.2264
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2719 - loss: 1.9823  
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2801 - loss: 1.9729
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2876 - loss: 1.9651
[1m 169/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2916 - loss: 1.9602
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2934 - loss: 1.9576
[1m 251/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2946 - loss: 1.9559
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2950 - loss: 1.9556
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2952 - loss: 1.9561
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2953 - loss: 1.9563
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2952 - loss: 1.9568
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2949 - loss: 1.9574
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2945 - loss: 1.9583
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2942 - loss: 1.9590
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2940 - loss: 1.9600
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2936 - loss: 1.9610
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2933 - loss: 1.9617
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2930 - loss: 1.9626
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2927 - loss: 1.9632
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2923 - loss: 1.9639
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2919 - loss: 1.9647
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2916 - loss: 1.9656
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2913 - loss: 1.9662
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2910 - loss: 1.9668
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2907 - loss: 1.9673
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2904 - loss: 1.9678
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2902 - loss: 1.9683
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2899 - loss: 1.9687
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2897 - loss: 1.9691
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2895 - loss: 1.9696
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2894 - loss: 1.9696 - val_accuracy: 0.2746 - val_loss: 1.9580
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.1295
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2667 - loss: 2.0036  
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2792 - loss: 1.9963
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2822 - loss: 1.9909
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2830 - loss: 1.9901
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2828 - loss: 1.9900
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2832 - loss: 1.9890
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2837 - loss: 1.9871
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2839 - loss: 1.9854
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2839 - loss: 1.9847
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2841 - loss: 1.9836
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2841 - loss: 1.9828
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2842 - loss: 1.9822
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2842 - loss: 1.9816
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2844 - loss: 1.9805
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2846 - loss: 1.9795
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2848 - loss: 1.9784
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2849 - loss: 1.9776
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2851 - loss: 1.9767
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2852 - loss: 1.9760
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2852 - loss: 1.9755
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2853 - loss: 1.9751
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2853 - loss: 1.9747
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2853 - loss: 1.9745
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2854 - loss: 1.9742
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2854 - loss: 1.9741
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2853 - loss: 1.9740
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2853 - loss: 1.9739
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2852 - loss: 1.9738
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2851 - loss: 1.9738
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2850 - loss: 1.9737 - val_accuracy: 0.2918 - val_loss: 1.9422
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.1945
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2952 - loss: 1.9734  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2922 - loss: 1.9699
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2893 - loss: 1.9674
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2880 - loss: 1.9672
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2880 - loss: 1.9660
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2883 - loss: 1.9644
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2887 - loss: 1.9627
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2888 - loss: 1.9624
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2891 - loss: 1.9626
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2897 - loss: 1.9626
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2898 - loss: 1.9633
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2899 - loss: 1.9639
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2900 - loss: 1.9643
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2898 - loss: 1.9651
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2897 - loss: 1.9660
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2895 - loss: 1.9667
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2895 - loss: 1.9672
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2895 - loss: 1.9676
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2894 - loss: 1.9680
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2894 - loss: 1.9683
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2893 - loss: 1.9686
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2892 - loss: 1.9688
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2891 - loss: 1.9690
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2890 - loss: 1.9691
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2889 - loss: 1.9692
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2888 - loss: 1.9692
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2887 - loss: 1.9693
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2885 - loss: 1.9694
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2884 - loss: 1.9694
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2883 - loss: 1.9695 - val_accuracy: 0.2862 - val_loss: 1.9230
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 1.8574
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2745 - loss: 1.9004  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2812 - loss: 1.9293
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2833 - loss: 1.9343
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2847 - loss: 1.9356
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2851 - loss: 1.9380
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2849 - loss: 1.9412
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2842 - loss: 1.9438
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2836 - loss: 1.9452
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2834 - loss: 1.9464
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2831 - loss: 1.9477
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2827 - loss: 1.9490
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2825 - loss: 1.9498
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2824 - loss: 1.9504
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2822 - loss: 1.9513
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2820 - loss: 1.9518
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2820 - loss: 1.9522
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2820 - loss: 1.9525
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2820 - loss: 1.9528
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2821 - loss: 1.9531
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2823 - loss: 1.9534
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2824 - loss: 1.9535
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2827 - loss: 1.9535
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2829 - loss: 1.9535
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2832 - loss: 1.9534
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2834 - loss: 1.9532
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2837 - loss: 1.9529
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2839 - loss: 1.9527
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2841 - loss: 1.9526
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2841 - loss: 1.9526 - val_accuracy: 0.2875 - val_loss: 1.9324

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 638ms/step
[1m69/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 739us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:11[0m 843ms/step
[1m 69/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 743us/step  
[1m142/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 716us/step
[1m214/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 714us/step
[1m281/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 724us/step
[1m356/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 713us/step
[1m429/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 709us/step
[1m498/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 713us/step
[1m567/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 715us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m59/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 865us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 69/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 744us/step
[1m137/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 744us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 26.68 [%]
Global F1 score (validation) = 23.27 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[1.6645338e-01 1.5529245e-01 1.6053286e-01 ... 5.6682988e-03
  1.0525788e-01 2.1228811e-02]
 [1.9963594e-01 1.9629292e-01 2.0442832e-01 ... 2.2062357e-03
  1.1770077e-01 2.1966640e-02]
 [1.4779705e-01 1.5971944e-01 1.5692526e-01 ... 4.8361653e-03
  1.2636325e-01 2.3462985e-02]
 ...
 [2.0176798e-01 1.3909476e-01 1.8577752e-01 ... 3.7226186e-05
  1.6452950e-01 9.0631835e-02]
 [2.2352111e-01 1.8620615e-01 1.5864815e-01 ... 3.8260725e-04
  1.6977379e-01 3.7942424e-02]
 [1.6098192e-01 1.7141348e-01 1.2836961e-01 ... 3.8354932e-03
  1.4408964e-01 2.7597371e-02]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 31.7 [%]
Global accuracy score (test) = 26.01 [%]
Global F1 score (train) = 28.25 [%]
Global F1 score (test) = 23.1 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.19      0.13      0.15       184
 CAMINAR CON MÓVIL O LIBRO       0.17      0.15      0.16       184
       CAMINAR USUAL SPEED       0.21      0.30      0.25       184
            CAMINAR ZIGZAG       0.16      0.24      0.19       184
          DE PIE BARRIENDO       0.18      0.40      0.25       184
   DE PIE DOBLANDO TOALLAS       0.00      0.00      0.00       184
    DE PIE MOVIENDO LIBROS       0.18      0.33      0.23       184
          DE PIE USANDO PC       0.26      0.76      0.39       184
        FASE REPOSO CON K5       0.71      0.62      0.67       184
INCREMENTAL CICLOERGOMETRO       0.50      0.08      0.13       184
           SENTADO LEYENDO       0.31      0.05      0.09       184
         SENTADO USANDO PC       0.05      0.02      0.03       184
      SENTADO VIENDO LA TV       0.34      0.48      0.40       184
   SUBIR Y BAJAR ESCALERAS       0.08      0.01      0.02       184
                    TROTAR       0.93      0.33      0.49       161

                  accuracy                           0.26      2737
                 macro avg       0.29      0.26      0.23      2737
              weighted avg       0.28      0.26      0.23      2737


Accuracy capturado en la ejecución 27: 26.01 [%]
F1-score capturado en la ejecución 27: 23.1 [%]

=== EJECUCIÓN 28 ===

--- TRAIN (ejecución 28) ---

--- TEST (ejecución 28) ---
2025-11-07 14:37:03.220245: 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 14:37:03.231747: 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 00:00:1762522623.246048 3012817 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762522623.250464 3012817 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762522623.260938 3012817 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522623.260957 3012817 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522623.260959 3012817 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522623.260961 3012817 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:37:03.264293: 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 00:00:1762522625.531268 3012817 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762522627.042245 3012928 service.cc:152] XLA service 0x78320c01f530 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762522627.042276 3012928 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:37:07.075869: 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 00:00:1762522627.232902 3012928 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762522628.642770 3012928 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47:44[0m 2s/step - accuracy: 0.0625 - loss: 3.8958
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0543 - loss: 3.3098  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0623 - loss: 3.2505
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0651 - loss: 3.2188
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0674 - loss: 3.1938
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0698 - loss: 3.1724
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0719 - loss: 3.1558
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0735 - loss: 3.1409
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0750 - loss: 3.1278
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0760 - loss: 3.1181
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0767 - loss: 3.1092
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0775 - loss: 3.1010
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0783 - loss: 3.0930
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0790 - loss: 3.0861
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0799 - loss: 3.0786
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0806 - loss: 3.0721
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0813 - loss: 3.0663
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0819 - loss: 3.0610
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0826 - loss: 3.0550
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0832 - loss: 3.0502
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0837 - loss: 3.0453
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0842 - loss: 3.0410
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0848 - loss: 3.0360
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0853 - loss: 3.0319
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0859 - loss: 3.0276
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0864 - loss: 3.0236
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0870 - loss: 3.0196
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0875 - loss: 3.0157
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0880 - loss: 3.0117
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0883 - loss: 3.0092
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0883 - loss: 3.0091 - val_accuracy: 0.1369 - val_loss: 2.6244
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.2500 - loss: 2.6536
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1243 - loss: 2.8083  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1232 - loss: 2.7911
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1237 - loss: 2.7794
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1228 - loss: 2.7717
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1220 - loss: 2.7667
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1210 - loss: 2.7643
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1205 - loss: 2.7617
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1204 - loss: 2.7592
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1205 - loss: 2.7561
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1208 - loss: 2.7527
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1213 - loss: 2.7492
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1216 - loss: 2.7463
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1219 - loss: 2.7436
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1221 - loss: 2.7412
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1223 - loss: 2.7389
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1224 - loss: 2.7367
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1226 - loss: 2.7345
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1228 - loss: 2.7326
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1230 - loss: 2.7307
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1232 - loss: 2.7288
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1236 - loss: 2.7267
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1239 - loss: 2.7247
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1242 - loss: 2.7227
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1246 - loss: 2.7206
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1250 - loss: 2.7185
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1255 - loss: 2.7165
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1259 - loss: 2.7146
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1263 - loss: 2.7126 - val_accuracy: 0.2072 - val_loss: 2.4930
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 20ms/step - accuracy: 0.3125 - loss: 2.7278
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1538 - loss: 2.6346  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1572 - loss: 2.6078
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1572 - loss: 2.5975
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1588 - loss: 2.5871
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1604 - loss: 2.5804
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1609 - loss: 2.5761
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1613 - loss: 2.5722
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1617 - loss: 2.5688
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1620 - loss: 2.5657
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1622 - loss: 2.5627
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1626 - loss: 2.5598
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1628 - loss: 2.5575
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1630 - loss: 2.5555
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1630 - loss: 2.5538
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1630 - loss: 2.5522
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1630 - loss: 2.5507
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1632 - loss: 2.5492
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1634 - loss: 2.5476
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1637 - loss: 2.5460
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1640 - loss: 2.5446
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1643 - loss: 2.5430
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1646 - loss: 2.5414
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1649 - loss: 2.5402
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1652 - loss: 2.5388
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1655 - loss: 2.5373
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1657 - loss: 2.5362
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1660 - loss: 2.5349
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1662 - loss: 2.5336
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1665 - loss: 2.5324
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1665 - loss: 2.5321 - val_accuracy: 0.2087 - val_loss: 2.3760
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.6564
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1771 - loss: 2.4696  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1799 - loss: 2.4598
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1794 - loss: 2.4538
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1792 - loss: 2.4512
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1796 - loss: 2.4503
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1800 - loss: 2.4491
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1806 - loss: 2.4468
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1812 - loss: 2.4452
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1820 - loss: 2.4433
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1826 - loss: 2.4418
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1832 - loss: 2.4404
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1837 - loss: 2.4393
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1841 - loss: 2.4381
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1844 - loss: 2.4370
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1847 - loss: 2.4359
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1851 - loss: 2.4349
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1854 - loss: 2.4340
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1856 - loss: 2.4331
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1858 - loss: 2.4323
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1860 - loss: 2.4315
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1862 - loss: 2.4307
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1864 - loss: 2.4301
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1866 - loss: 2.4294
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1867 - loss: 2.4287
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1869 - loss: 2.4280
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1870 - loss: 2.4274
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1872 - loss: 2.4267
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1874 - loss: 2.4260
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1875 - loss: 2.4254 - val_accuracy: 0.2072 - val_loss: 2.2992
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.2488
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1754 - loss: 2.4400  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1772 - loss: 2.4201
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1788 - loss: 2.4088
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1808 - loss: 2.4007
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1818 - loss: 2.3971
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1827 - loss: 2.3941
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1838 - loss: 2.3916
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1847 - loss: 2.3887
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1856 - loss: 2.3862
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1864 - loss: 2.3841
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1871 - loss: 2.3824
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1877 - loss: 2.3808
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1883 - loss: 2.3792
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1889 - loss: 2.3777
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1894 - loss: 2.3763
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1898 - loss: 2.3749
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1902 - loss: 2.3735
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1905 - loss: 2.3723
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1908 - loss: 2.3711
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1912 - loss: 2.3699
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1914 - loss: 2.3690
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1916 - loss: 2.3680
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1918 - loss: 2.3672
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1920 - loss: 2.3664
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1922 - loss: 2.3658
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1923 - loss: 2.3652
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1924 - loss: 2.3645
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1926 - loss: 2.3639
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1926 - loss: 2.3636 - val_accuracy: 0.2361 - val_loss: 2.2252
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.3513
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2006 - loss: 2.3156  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2061 - loss: 2.3080
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2081 - loss: 2.3085
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2083 - loss: 2.3102
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2087 - loss: 2.3108
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2082 - loss: 2.3114
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2078 - loss: 2.3123
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2077 - loss: 2.3123
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2080 - loss: 2.3114
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2082 - loss: 2.3103
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2083 - loss: 2.3094
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2084 - loss: 2.3086
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2085 - loss: 2.3079
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2087 - loss: 2.3074
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2089 - loss: 2.3070
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2090 - loss: 2.3066
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2092 - loss: 2.3062
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2094 - loss: 2.3058
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2095 - loss: 2.3053
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2097 - loss: 2.3049
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2098 - loss: 2.3044
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2099 - loss: 2.3041
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2099 - loss: 2.3036
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2100 - loss: 2.3033
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2101 - loss: 2.3029
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2101 - loss: 2.3025
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2102 - loss: 2.3021
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2103 - loss: 2.3016
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2104 - loss: 2.3012 - val_accuracy: 0.2315 - val_loss: 2.1768
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.3732
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1999 - loss: 2.3076  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2018 - loss: 2.3046
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2047 - loss: 2.2986
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2078 - loss: 2.2937
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2094 - loss: 2.2903
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2104 - loss: 2.2877
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2111 - loss: 2.2852
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2119 - loss: 2.2824
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2128 - loss: 2.2797
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2136 - loss: 2.2769
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2142 - loss: 2.2747
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2147 - loss: 2.2729
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2151 - loss: 2.2714
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2155 - loss: 2.2700
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2159 - loss: 2.2687
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2162 - loss: 2.2676
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2164 - loss: 2.2668
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2167 - loss: 2.2660
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2169 - loss: 2.2654
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2171 - loss: 2.2648
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2172 - loss: 2.2643
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2174 - loss: 2.2639
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2175 - loss: 2.2636
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2176 - loss: 2.2633
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2177 - loss: 2.2631
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2178 - loss: 2.2628
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2179 - loss: 2.2626
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2180 - loss: 2.2622
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2181 - loss: 2.2620 - val_accuracy: 0.2509 - val_loss: 2.1313
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.0178
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2382 - loss: 2.1690  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2310 - loss: 2.1746
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2258 - loss: 2.1804
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2239 - loss: 2.1872
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2233 - loss: 2.1919
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2228 - loss: 2.1957
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2227 - loss: 2.1980
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2229 - loss: 2.1991
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2229 - loss: 2.2005
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2230 - loss: 2.2016
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2230 - loss: 2.2032
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2230 - loss: 2.2046
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2229 - loss: 2.2059
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2229 - loss: 2.2071
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2229 - loss: 2.2081
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2229 - loss: 2.2092
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2229 - loss: 2.2101
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2229 - loss: 2.2109
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2229 - loss: 2.2116
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2229 - loss: 2.2122
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2229 - loss: 2.2127
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2229 - loss: 2.2130
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2230 - loss: 2.2133
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2230 - loss: 2.2135
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2231 - loss: 2.2137
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2231 - loss: 2.2138
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2231 - loss: 2.2139
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2231 - loss: 2.2140
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2232 - loss: 2.2141 - val_accuracy: 0.2448 - val_loss: 2.1092
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.1250 - loss: 2.4072
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1897 - loss: 2.2520  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2152 - loss: 2.2217
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2213 - loss: 2.2152
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2224 - loss: 2.2140
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2227 - loss: 2.2135
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2231 - loss: 2.2138
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2243 - loss: 2.2129
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2254 - loss: 2.2121
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2262 - loss: 2.2112
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2267 - loss: 2.2104
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2273 - loss: 2.2093
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2279 - loss: 2.2080
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2284 - loss: 2.2072
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2288 - loss: 2.2065
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2292 - loss: 2.2057
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2294 - loss: 2.2049
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2297 - loss: 2.2042
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2300 - loss: 2.2033
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2303 - loss: 2.2025
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2306 - loss: 2.2016
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2309 - loss: 2.2008
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2312 - loss: 2.2000
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2314 - loss: 2.1994
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2315 - loss: 2.1989
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2316 - loss: 2.1984
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2317 - loss: 2.1979
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2318 - loss: 2.1977
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2318 - loss: 2.1974
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.2318 - loss: 2.1972
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2319 - loss: 2.1972 - val_accuracy: 0.2583 - val_loss: 2.0648
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 20ms/step - accuracy: 0.3125 - loss: 1.9398
[1m  44/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2373 - loss: 2.2043  
[1m  86/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2377 - loss: 2.1879
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2379 - loss: 2.1807
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2362 - loss: 2.1805
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2351 - loss: 2.1804
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2348 - loss: 2.1788
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2349 - loss: 2.1773
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2350 - loss: 2.1764
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2352 - loss: 2.1757
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2354 - loss: 2.1751
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2358 - loss: 2.1740
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2362 - loss: 2.1730
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2365 - loss: 2.1721
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2366 - loss: 2.1713
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2366 - loss: 2.1708
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2367 - loss: 2.1706
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2367 - loss: 2.1703
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2367 - loss: 2.1701
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2367 - loss: 2.1698
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2367 - loss: 2.1696
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2368 - loss: 2.1694
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2368 - loss: 2.1692
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2368 - loss: 2.1691
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2368 - loss: 2.1691
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2368 - loss: 2.1690
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2368 - loss: 2.1690
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2368 - loss: 2.1689
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2368 - loss: 2.1689
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2368 - loss: 2.1689
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2368 - loss: 2.1689 - val_accuracy: 0.2611 - val_loss: 2.0426
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.1253
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2994 - loss: 2.0754  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2763 - loss: 2.1158
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2636 - loss: 2.1340
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2570 - loss: 2.1415
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2533 - loss: 2.1450
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2508 - loss: 2.1472
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2494 - loss: 2.1488
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2479 - loss: 2.1502
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2466 - loss: 2.1509
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1508
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2449 - loss: 2.1507
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2442 - loss: 2.1504
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2438 - loss: 2.1502
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2434 - loss: 2.1498
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2431 - loss: 2.1495
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2429 - loss: 2.1492
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2426 - loss: 2.1490
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2424 - loss: 2.1489
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2423 - loss: 2.1487
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2421 - loss: 2.1485
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2420 - loss: 2.1482
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1479
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1476
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1473
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2419 - loss: 2.1470
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2418 - loss: 2.1468
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2418 - loss: 2.1465
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2417 - loss: 2.1464
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2417 - loss: 2.1463 - val_accuracy: 0.2446 - val_loss: 2.0540
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3750 - loss: 1.9627
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2718 - loss: 2.0680  
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2630 - loss: 2.1035
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2555 - loss: 2.1221
[1m 147/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2517 - loss: 2.1319
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2506 - loss: 2.1361
[1m 227/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2494 - loss: 2.1386
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2480 - loss: 2.1403
[1m 307/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2471 - loss: 2.1410
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2468 - loss: 2.1403
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2465 - loss: 2.1396
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2463 - loss: 2.1388
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2461 - loss: 2.1378
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2460 - loss: 2.1368
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2459 - loss: 2.1356
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2459 - loss: 2.1345
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2459 - loss: 2.1336
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2459 - loss: 2.1327
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2459 - loss: 2.1320
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2459 - loss: 2.1314
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2458 - loss: 2.1306
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2458 - loss: 2.1300
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1295
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1290
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1285
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2456 - loss: 2.1281
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2456 - loss: 2.1279
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2456 - loss: 2.1278
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1277
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2455 - loss: 2.1276 - val_accuracy: 0.2668 - val_loss: 2.0108
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.1875 - loss: 2.0268
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2424 - loss: 2.0424  
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2478 - loss: 2.0585
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2498 - loss: 2.0704
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2508 - loss: 2.0765
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2509 - loss: 2.0807
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2509 - loss: 2.0833
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2505 - loss: 2.0866
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2501 - loss: 2.0896
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2494 - loss: 2.0924
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2487 - loss: 2.0948
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2481 - loss: 2.0973
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2478 - loss: 2.0989
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2476 - loss: 2.1000
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2475 - loss: 2.1010
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2473 - loss: 2.1018
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2471 - loss: 2.1026
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2470 - loss: 2.1032
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2468 - loss: 2.1038
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2466 - loss: 2.1042
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2465 - loss: 2.1047
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2463 - loss: 2.1052
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2462 - loss: 2.1056
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2460 - loss: 2.1060
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2459 - loss: 2.1062
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2458 - loss: 2.1064
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1065
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2456 - loss: 2.1067
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2456 - loss: 2.1069
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2455 - loss: 2.1070
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2455 - loss: 2.1071 - val_accuracy: 0.2564 - val_loss: 2.0197
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.8461
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2410 - loss: 2.1281  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2432 - loss: 2.1331
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2431 - loss: 2.1343
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2432 - loss: 2.1300
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2445 - loss: 2.1263
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2451 - loss: 2.1232
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2457 - loss: 2.1206
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2464 - loss: 2.1183
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2470 - loss: 2.1161
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2477 - loss: 2.1142
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2483 - loss: 2.1127
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2487 - loss: 2.1114
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2490 - loss: 2.1104
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2492 - loss: 2.1093
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2494 - loss: 2.1083
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2497 - loss: 2.1076
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2498 - loss: 2.1069
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2501 - loss: 2.1063
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2503 - loss: 2.1055
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2506 - loss: 2.1049
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2507 - loss: 2.1044
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2508 - loss: 2.1041
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2509 - loss: 2.1038
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2509 - loss: 2.1036
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2510 - loss: 2.1033
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2510 - loss: 2.1029
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2511 - loss: 2.1026
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2511 - loss: 2.1022
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2511 - loss: 2.1019 - val_accuracy: 0.2770 - val_loss: 2.0002
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0000e+00 - loss: 2.1795
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2337 - loss: 2.1051      
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2465 - loss: 2.0972
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2491 - loss: 2.0931
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2504 - loss: 2.0917
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2510 - loss: 2.0899
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2519 - loss: 2.0869
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2521 - loss: 2.0853
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2519 - loss: 2.0851
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2517 - loss: 2.0849
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2515 - loss: 2.0850
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2514 - loss: 2.0850
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.0850
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2512 - loss: 2.0851
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2511 - loss: 2.0854
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2510 - loss: 2.0857
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2510 - loss: 2.0858
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2511 - loss: 2.0856
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2511 - loss: 2.0854
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2512 - loss: 2.0851
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.0849
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2514 - loss: 2.0846
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2514 - loss: 2.0844
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2515 - loss: 2.0842
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2515 - loss: 2.0839
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2516 - loss: 2.0838
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2516 - loss: 2.0837
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2516 - loss: 2.0838
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2516 - loss: 2.0838
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2516 - loss: 2.0838
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2516 - loss: 2.0838 - val_accuracy: 0.2657 - val_loss: 1.9998
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.3184
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2196 - loss: 2.1058  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2296 - loss: 2.0980
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2341 - loss: 2.1006
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2371 - loss: 2.1014
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2387 - loss: 2.1007
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2392 - loss: 2.1012
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2397 - loss: 2.1015
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2402 - loss: 2.1017
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2404 - loss: 2.1013
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2406 - loss: 2.1007
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2411 - loss: 2.0996
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2418 - loss: 2.0985
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2425 - loss: 2.0975
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2432 - loss: 2.0966
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2437 - loss: 2.0958
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2441 - loss: 2.0950
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2446 - loss: 2.0942
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2450 - loss: 2.0934
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2454 - loss: 2.0927
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2458 - loss: 2.0922
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2461 - loss: 2.0917
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2465 - loss: 2.0911
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2468 - loss: 2.0904
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2471 - loss: 2.0898
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2474 - loss: 2.0892
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2476 - loss: 2.0885
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2479 - loss: 2.0879
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2481 - loss: 2.0873
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2483 - loss: 2.0869 - val_accuracy: 0.2884 - val_loss: 1.9671
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.0176
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2618 - loss: 2.0163  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2577 - loss: 2.0404
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2583 - loss: 2.0450
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0465
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0460
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0467
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2565 - loss: 2.0469
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0474
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0482
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2557 - loss: 2.0492
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2552 - loss: 2.0506
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2547 - loss: 2.0518
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2544 - loss: 2.0524
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2542 - loss: 2.0529
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2539 - loss: 2.0535
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2538 - loss: 2.0540
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2535 - loss: 2.0545
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2532 - loss: 2.0552
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2530 - loss: 2.0557
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2529 - loss: 2.0562
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.0565
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.0568
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.0571
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.0574
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.0577
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2528 - loss: 2.0579
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2529 - loss: 2.0580
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2529 - loss: 2.0582
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2529 - loss: 2.0583
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2529 - loss: 2.0584 - val_accuracy: 0.2749 - val_loss: 1.9802
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.4150
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2843 - loss: 1.9691  
[1m  86/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2614 - loss: 2.0030
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2539 - loss: 2.0199
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2505 - loss: 2.0291
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2500 - loss: 2.0334
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2506 - loss: 2.0357
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2511 - loss: 2.0368
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2513 - loss: 2.0380
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2514 - loss: 2.0390
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2515 - loss: 2.0402
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2515 - loss: 2.0411
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2514 - loss: 2.0423
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.0435
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2511 - loss: 2.0442
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2509 - loss: 2.0449
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2507 - loss: 2.0452
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2505 - loss: 2.0456
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2504 - loss: 2.0458
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2504 - loss: 2.0459
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2505 - loss: 2.0460
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2506 - loss: 2.0460
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2507 - loss: 2.0459
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2509 - loss: 2.0458
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2511 - loss: 2.0456
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2512 - loss: 2.0454
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2514 - loss: 2.0453
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2515 - loss: 2.0452
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2516 - loss: 2.0451
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2517 - loss: 2.0449 - val_accuracy: 0.2784 - val_loss: 1.9685
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.2128
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2500 - loss: 2.0469  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2606 - loss: 2.0487
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2606 - loss: 2.0522
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2600 - loss: 2.0519
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2602 - loss: 2.0506
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2608 - loss: 2.0492
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2616 - loss: 2.0472
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2625 - loss: 2.0443
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2632 - loss: 2.0420
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0405
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2646 - loss: 2.0390
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0377
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2654 - loss: 2.0370
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0363
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0358
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0356
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0355
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0355
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0355
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0356
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0357
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2648 - loss: 2.0358
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2646 - loss: 2.0359
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2643 - loss: 2.0359
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2641 - loss: 2.0359
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2640 - loss: 2.0359
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2638 - loss: 2.0358
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0359
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2635 - loss: 2.0359
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2635 - loss: 2.0360 - val_accuracy: 0.2881 - val_loss: 1.9522
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.8468
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2870 - loss: 1.9254  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2748 - loss: 1.9594
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2685 - loss: 1.9747
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2647 - loss: 1.9850
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2634 - loss: 1.9908
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2622 - loss: 1.9963
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2613 - loss: 2.0005
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0038
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0066
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2612 - loss: 2.0088
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2613 - loss: 2.0110
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2612 - loss: 2.0128
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0143
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0157
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0167
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0174
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0180
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0186
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0192
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0199
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0206
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0212
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0217
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0222
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0228
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0232
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0236
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0239
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0242
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2610 - loss: 2.0243 - val_accuracy: 0.2932 - val_loss: 1.9388
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.1945
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2973 - loss: 1.9745  
[1m  70/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2853 - loss: 1.9827
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2823 - loss: 1.9852
[1m 150/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2803 - loss: 1.9890
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2785 - loss: 1.9932
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2772 - loss: 1.9964
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2763 - loss: 1.9984
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2756 - loss: 1.9997
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0010
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2745 - loss: 2.0021
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2742 - loss: 2.0028
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2738 - loss: 2.0035
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2735 - loss: 2.0042
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0045
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2729 - loss: 2.0048
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2726 - loss: 2.0051
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2723 - loss: 2.0054
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0057
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2719 - loss: 2.0061
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0063
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0065
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2714 - loss: 2.0068
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2712 - loss: 2.0071
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0074
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0077
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2706 - loss: 2.0079
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2705 - loss: 2.0082
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0085
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2701 - loss: 2.0088
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2700 - loss: 2.0089 - val_accuracy: 0.2942 - val_loss: 1.9346
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 20ms/step - accuracy: 0.3750 - loss: 1.7891
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2907 - loss: 1.9790  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2851 - loss: 1.9895
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2806 - loss: 1.9999
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2783 - loss: 2.0067
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2768 - loss: 2.0098
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0124
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2743 - loss: 2.0142
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2737 - loss: 2.0151
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2733 - loss: 2.0150
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2731 - loss: 2.0145
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2730 - loss: 2.0141
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2729 - loss: 2.0135
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2728 - loss: 2.0134
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2725 - loss: 2.0134
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2723 - loss: 2.0133
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0134
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2721 - loss: 2.0135
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2720 - loss: 2.0137
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0140
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0143
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2717 - loss: 2.0145
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0147
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2714 - loss: 2.0149
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2714 - loss: 2.0150
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0150
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2712 - loss: 2.0150
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0150
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0150
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0149
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2709 - loss: 2.0148 - val_accuracy: 0.2914 - val_loss: 1.9492
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.0677
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2471 - loss: 2.1252  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2540 - loss: 2.0891
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2584 - loss: 2.0700
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2608 - loss: 2.0543
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2624 - loss: 2.0440
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0364
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2644 - loss: 2.0330
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0291
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0264
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0245
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2654 - loss: 2.0225
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0203
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0184
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2658 - loss: 2.0165
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2660 - loss: 2.0149
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0135
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0122
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0111
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0102
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0096
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0091
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0087
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0084
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0080
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0076
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0074
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0070
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0068
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2664 - loss: 2.0066
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2664 - loss: 2.0065 - val_accuracy: 0.2879 - val_loss: 1.9530
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.1198
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2740 - loss: 1.9806  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2871 - loss: 1.9559
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2869 - loss: 1.9525
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2845 - loss: 1.9539
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2829 - loss: 1.9564
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2822 - loss: 1.9583
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2817 - loss: 1.9600
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2813 - loss: 1.9611
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2809 - loss: 1.9620
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2806 - loss: 1.9629
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2804 - loss: 1.9640
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2802 - loss: 1.9649
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 1.9661
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 1.9672
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2790 - loss: 1.9684
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2786 - loss: 1.9694
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2783 - loss: 1.9706
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2779 - loss: 1.9715
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2777 - loss: 1.9722
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2774 - loss: 1.9730
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2772 - loss: 1.9738
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2770 - loss: 1.9745
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2768 - loss: 1.9752
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2765 - loss: 1.9759
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2763 - loss: 1.9764
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2761 - loss: 1.9770
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2759 - loss: 1.9776
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2757 - loss: 1.9781
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2756 - loss: 1.9785 - val_accuracy: 0.2942 - val_loss: 1.9359
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.3039
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2571 - loss: 1.9729  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2505 - loss: 2.0079
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2513 - loss: 2.0174
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2536 - loss: 2.0198
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2556 - loss: 2.0198
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2577 - loss: 2.0181
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2593 - loss: 2.0158
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2607 - loss: 2.0141
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2620 - loss: 2.0126
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2629 - loss: 2.0115
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2634 - loss: 2.0108
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2638 - loss: 2.0103
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0096
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2647 - loss: 2.0089
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2650 - loss: 2.0083
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2653 - loss: 2.0076
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2655 - loss: 2.0069
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0062
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0055
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2663 - loss: 2.0046
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0040
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0033
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2670 - loss: 2.0026
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2673 - loss: 2.0020
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0014
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0009
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0005
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2680 - loss: 2.0001
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2681 - loss: 1.9999 - val_accuracy: 0.2698 - val_loss: 1.9539

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m52s[0m 617ms/step
[1m65/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 791us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:04[0m 830ms/step
[1m 70/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 725us/step  
[1m142/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 709us/step
[1m211/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 717us/step
[1m275/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 735us/step
[1m344/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 733us/step
[1m407/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 743us/step
[1m474/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 744us/step
[1m540/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 747us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m73/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 710us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 71/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 721us/step
[1m128/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 793us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 28.75 [%]
Global F1 score (validation) = 25.7 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.08304067 0.10318741 0.08086813 ... 0.00716125 0.08374549 0.00931857]
 [0.16444223 0.20794807 0.13440998 ... 0.00236026 0.13895375 0.01977104]
 [0.1439319  0.20033264 0.12186596 ... 0.00340703 0.13680343 0.02552415]
 ...
 [0.10237186 0.13604112 0.11377811 ... 0.00651616 0.10411312 0.01200732]
 [0.15028903 0.17016205 0.1376361  ... 0.00299041 0.14636646 0.01475989]
 [0.10624821 0.13240196 0.09679376 ... 0.00551565 0.09322099 0.00922598]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 31.55 [%]
Global accuracy score (test) = 26.27 [%]
Global F1 score (train) = 28.75 [%]
Global F1 score (test) = 23.14 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.18      0.09      0.12       184
 CAMINAR CON MÓVIL O LIBRO       0.17      0.57      0.26       184
       CAMINAR USUAL SPEED       0.07      0.01      0.02       184
            CAMINAR ZIGZAG       0.07      0.04      0.05       184
          DE PIE BARRIENDO       0.18      0.44      0.25       184
   DE PIE DOBLANDO TOALLAS       0.26      0.32      0.28       184
    DE PIE MOVIENDO LIBROS       0.00      0.00      0.00       184
          DE PIE USANDO PC       0.29      0.90      0.44       184
        FASE REPOSO CON K5       0.86      0.37      0.52       184
INCREMENTAL CICLOERGOMETRO       0.97      0.16      0.27       184
           SENTADO LEYENDO       0.21      0.25      0.23       184
         SENTADO USANDO PC       0.04      0.01      0.02       184
      SENTADO VIENDO LA TV       0.44      0.36      0.40       184
   SUBIR Y BAJAR ESCALERAS       0.07      0.01      0.02       184
                    TROTAR       0.97      0.43      0.59       161

                  accuracy                           0.26      2737
                 macro avg       0.32      0.26      0.23      2737
              weighted avg       0.31      0.26      0.23      2737


Accuracy capturado en la ejecución 28: 26.27 [%]
F1-score capturado en la ejecución 28: 23.14 [%]

=== EJECUCIÓN 29 ===

--- TRAIN (ejecución 29) ---

--- TEST (ejecución 29) ---
2025-11-07 14:38:10.266173: 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 14:38:10.277322: 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 00:00:1762522690.290352 3016541 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762522690.294506 3016541 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762522690.304309 3016541 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522690.304327 3016541 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522690.304328 3016541 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762522690.304329 3016541 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 14:38:10.307445: 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 00:00:1762522692.594580 3016541 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 1/25
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762522694.110276 3016674 service.cc:152] XLA service 0x769dc0016030 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762522694.110309 3016674 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 14:38:14.145913: 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 00:00:1762522694.298374 3016674 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762522695.700945 3016674 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47:39[0m 2s/step - accuracy: 0.0625 - loss: 3.0652
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0592 - loss: 3.2338  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0574 - loss: 3.2656
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0574 - loss: 3.2641
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0585 - loss: 3.2591
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0598 - loss: 3.2507
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0611 - loss: 3.2418
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0623 - loss: 3.2337
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0631 - loss: 3.2259
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.0639 - loss: 3.2186
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0647 - loss: 3.2116
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0655 - loss: 3.2049
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0661 - loss: 3.1979
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0668 - loss: 3.1911
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0675 - loss: 3.1846
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0680 - loss: 3.1788
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0687 - loss: 3.1725
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0692 - loss: 3.1668
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0698 - loss: 3.1611
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0703 - loss: 3.1555
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0708 - loss: 3.1501
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0712 - loss: 3.1452
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0716 - loss: 3.1402
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0720 - loss: 3.1350
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0723 - loss: 3.1300
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.0727 - loss: 3.1254
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0730 - loss: 3.1211
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.0732 - loss: 3.1172
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.0736 - loss: 3.1131
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step - accuracy: 0.0737 - loss: 3.1105
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 4ms/step - accuracy: 0.0738 - loss: 3.1104 - val_accuracy: 0.1526 - val_loss: 2.6645
Epoch 2/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1875 - loss: 2.6725
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1062 - loss: 2.8652  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1045 - loss: 2.8498
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1053 - loss: 2.8376
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1050 - loss: 2.8279
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1044 - loss: 2.8219
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1042 - loss: 2.8180
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1043 - loss: 2.8149
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1047 - loss: 2.8117
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1052 - loss: 2.8081
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1056 - loss: 2.8047
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1061 - loss: 2.8011
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1066 - loss: 2.7978
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1072 - loss: 2.7948
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1077 - loss: 2.7916
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1082 - loss: 2.7889
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1087 - loss: 2.7862
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1092 - loss: 2.7837
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1096 - loss: 2.7815
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1099 - loss: 2.7796
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1103 - loss: 2.7777
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1106 - loss: 2.7757
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1108 - loss: 2.7738
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1111 - loss: 2.7720
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1113 - loss: 2.7703
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1115 - loss: 2.7688
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1118 - loss: 2.7671
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1121 - loss: 2.7655
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1125 - loss: 2.7638
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1127 - loss: 2.7629 - val_accuracy: 0.1765 - val_loss: 2.5276
Epoch 3/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 20ms/step - accuracy: 0.2500 - loss: 2.7106
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1390 - loss: 2.6870  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1337 - loss: 2.6725
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1336 - loss: 2.6651
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1344 - loss: 2.6597
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1355 - loss: 2.6532
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1362 - loss: 2.6486
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1370 - loss: 2.6444
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1378 - loss: 2.6409
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1386 - loss: 2.6376
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1392 - loss: 2.6347
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1399 - loss: 2.6321
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1404 - loss: 2.6298
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1410 - loss: 2.6274
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1417 - loss: 2.6254
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1422 - loss: 2.6236
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1428 - loss: 2.6217
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1435 - loss: 2.6198
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1440 - loss: 2.6183
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1444 - loss: 2.6169
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1450 - loss: 2.6154
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1455 - loss: 2.6138
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1460 - loss: 2.6124
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1463 - loss: 2.6112
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1468 - loss: 2.6099
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1473 - loss: 2.6084
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1478 - loss: 2.6071
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1482 - loss: 2.6057
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1486 - loss: 2.6045
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1490 - loss: 2.6032
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1491 - loss: 2.6027 - val_accuracy: 0.2067 - val_loss: 2.4166
Epoch 4/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.5724
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1855 - loss: 2.5346  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1805 - loss: 2.5284
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1795 - loss: 2.5238
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1797 - loss: 2.5178
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1794 - loss: 2.5153
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1788 - loss: 2.5142
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1781 - loss: 2.5137
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1776 - loss: 2.5132
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1775 - loss: 2.5120
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1774 - loss: 2.5111
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1774 - loss: 2.5100
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1774 - loss: 2.5088
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1775 - loss: 2.5078
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1776 - loss: 2.5068
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1777 - loss: 2.5057
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1778 - loss: 2.5045
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1780 - loss: 2.5032
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1781 - loss: 2.5022
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1781 - loss: 2.5010
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1782 - loss: 2.5001
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1784 - loss: 2.4991
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1785 - loss: 2.4982
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1786 - loss: 2.4973
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1788 - loss: 2.4964
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1789 - loss: 2.4955
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1791 - loss: 2.4945
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.1793 - loss: 2.4935
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.1794 - loss: 2.4926
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.1795 - loss: 2.4918 - val_accuracy: 0.2202 - val_loss: 2.3385
Epoch 5/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.3597
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1820 - loss: 2.4387  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1864 - loss: 2.4268
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1899 - loss: 2.4225
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1920 - loss: 2.4190
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1934 - loss: 2.4163
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1940 - loss: 2.4141
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1947 - loss: 2.4122
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1954 - loss: 2.4104
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1962 - loss: 2.4083
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1970 - loss: 2.4064
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1978 - loss: 2.4049
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1984 - loss: 2.4034
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1989 - loss: 2.4022
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1994 - loss: 2.4013
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.1998 - loss: 2.4005
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2002 - loss: 2.3997
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2005 - loss: 2.3991
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2007 - loss: 2.3986
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2009 - loss: 2.3980
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2010 - loss: 2.3973
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2012 - loss: 2.3968
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2013 - loss: 2.3963
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2014 - loss: 2.3958
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2015 - loss: 2.3953
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2016 - loss: 2.3948
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2017 - loss: 2.3942
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2018 - loss: 2.3936
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2019 - loss: 2.3930
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2020 - loss: 2.3925 - val_accuracy: 0.2241 - val_loss: 2.2649
Epoch 6/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3750 - loss: 2.1051
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1962 - loss: 2.3765  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1932 - loss: 2.3709
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1945 - loss: 2.3659
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1967 - loss: 2.3594
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.1989 - loss: 2.3539
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2004 - loss: 2.3505
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2017 - loss: 2.3481
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2026 - loss: 2.3464
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2030 - loss: 2.3451
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2035 - loss: 2.3439
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2040 - loss: 2.3430
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2045 - loss: 2.3420
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2050 - loss: 2.3411
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2053 - loss: 2.3401
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2055 - loss: 2.3393
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2057 - loss: 2.3385
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2059 - loss: 2.3375
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2063 - loss: 2.3366
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2066 - loss: 2.3357
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2068 - loss: 2.3349
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2071 - loss: 2.3341
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2073 - loss: 2.3334
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2076 - loss: 2.3327
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2078 - loss: 2.3320
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2081 - loss: 2.3313
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2083 - loss: 2.3307
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2085 - loss: 2.3301
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2087 - loss: 2.3295
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2089 - loss: 2.3289
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2090 - loss: 2.3287 - val_accuracy: 0.2485 - val_loss: 2.1896
Epoch 7/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.4000
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2576 - loss: 2.2891  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2456 - loss: 2.2960
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2362 - loss: 2.3009
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2304 - loss: 2.3027
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2267 - loss: 2.3031
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2247 - loss: 2.3029
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2231 - loss: 2.3025
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2224 - loss: 2.3011
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2220 - loss: 2.2994
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2216 - loss: 2.2976
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2214 - loss: 2.2957
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2214 - loss: 2.2937
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2214 - loss: 2.2919
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2214 - loss: 2.2901
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2214 - loss: 2.2887
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2213 - loss: 2.2878
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2211 - loss: 2.2871
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2210 - loss: 2.2864
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2209 - loss: 2.2856
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2209 - loss: 2.2849
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2208 - loss: 2.2843
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2206 - loss: 2.2838
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2205 - loss: 2.2833
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2204 - loss: 2.2828
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2204 - loss: 2.2823
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2204 - loss: 2.2816
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2203 - loss: 2.2810
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2203 - loss: 2.2804
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2203 - loss: 2.2798
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2203 - loss: 2.2796 - val_accuracy: 0.2292 - val_loss: 2.1587
Epoch 8/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.1125
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2147 - loss: 2.1880  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2139 - loss: 2.2001
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2154 - loss: 2.2118
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2158 - loss: 2.2179
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2158 - loss: 2.2213
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2163 - loss: 2.2224
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2171 - loss: 2.2227
[1m 305/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2181 - loss: 2.2220
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2189 - loss: 2.2212
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2198 - loss: 2.2208
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2202 - loss: 2.2209
[1m 463/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2204 - loss: 2.2213
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2206 - loss: 2.2219
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2208 - loss: 2.2225
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2209 - loss: 2.2233
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2209 - loss: 2.2240
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2210 - loss: 2.2247
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2212 - loss: 2.2250
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2214 - loss: 2.2253
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2217 - loss: 2.2254
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2220 - loss: 2.2254
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2222 - loss: 2.2253
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2225 - loss: 2.2252
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2227 - loss: 2.2251
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2229 - loss: 2.2249
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2231 - loss: 2.2248
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2233 - loss: 2.2246
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2235 - loss: 2.2245
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2236 - loss: 2.2245
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2237 - loss: 2.2244 - val_accuracy: 0.2483 - val_loss: 2.1162
Epoch 9/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.5213
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2427 - loss: 2.1520  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2418 - loss: 2.1639
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2374 - loss: 2.1786
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2341 - loss: 2.1877
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2326 - loss: 2.1926
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2314 - loss: 2.1960
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2307 - loss: 2.1983
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2303 - loss: 2.1997
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2296 - loss: 2.2006
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2290 - loss: 2.2012
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2283 - loss: 2.2020
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2275 - loss: 2.2027
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2270 - loss: 2.2029
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2265 - loss: 2.2028
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2261 - loss: 2.2029
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2259 - loss: 2.2029
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2257 - loss: 2.2029
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2255 - loss: 2.2028
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2254 - loss: 2.2027
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2253 - loss: 2.2027
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2252 - loss: 2.2025
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2252 - loss: 2.2025
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2251 - loss: 2.2023
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2251 - loss: 2.2021
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2251 - loss: 2.2019
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2252 - loss: 2.2016
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2252 - loss: 2.2013
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2253 - loss: 2.2011
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2253 - loss: 2.2008
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2253 - loss: 2.2007 - val_accuracy: 0.2538 - val_loss: 2.0959
Epoch 10/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 1.9806
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2453 - loss: 2.1189  
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2386 - loss: 2.1413
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2383 - loss: 2.1426
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2378 - loss: 2.1443
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2361 - loss: 2.1493
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2352 - loss: 2.1535
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2346 - loss: 2.1571
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2341 - loss: 2.1595
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2336 - loss: 2.1609
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2332 - loss: 2.1618
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2326 - loss: 2.1629
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2324 - loss: 2.1634
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2322 - loss: 2.1637
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2320 - loss: 2.1637
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2319 - loss: 2.1636
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2318 - loss: 2.1634
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2318 - loss: 2.1632
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2318 - loss: 2.1630
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2318 - loss: 2.1629
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2318 - loss: 2.1628
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2318 - loss: 2.1627
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2316 - loss: 2.1627
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2315 - loss: 2.1626
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2315 - loss: 2.1626
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2314 - loss: 2.1624
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2313 - loss: 2.1624
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2313 - loss: 2.1623
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2312 - loss: 2.1622
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2312 - loss: 2.1621
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2312 - loss: 2.1621 - val_accuracy: 0.2599 - val_loss: 2.0702
Epoch 11/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.1809
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2294 - loss: 2.1949  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2236 - loss: 2.1836
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2259 - loss: 2.1720
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2273 - loss: 2.1695
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2289 - loss: 2.1664
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2296 - loss: 2.1647
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2311 - loss: 2.1631
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2326 - loss: 2.1617
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2339 - loss: 2.1605
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2347 - loss: 2.1595
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2354 - loss: 2.1586
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2360 - loss: 2.1577
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2365 - loss: 2.1570
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2368 - loss: 2.1564
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2372 - loss: 2.1557
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2377 - loss: 2.1550
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2383 - loss: 2.1538
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2387 - loss: 2.1529
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2390 - loss: 2.1520
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2393 - loss: 2.1512
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2395 - loss: 2.1506
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2397 - loss: 2.1501
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2398 - loss: 2.1497
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2399 - loss: 2.1493
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2399 - loss: 2.1489
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2400 - loss: 2.1485
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2401 - loss: 2.1480
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2401 - loss: 2.1476
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2402 - loss: 2.1472
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2402 - loss: 2.1471 - val_accuracy: 0.2683 - val_loss: 2.0468
Epoch 12/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 2.0569
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2759 - loss: 2.1147  
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2654 - loss: 2.1210
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2594 - loss: 2.1258
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2560 - loss: 2.1303
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2534 - loss: 2.1331
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2516 - loss: 2.1345
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2501 - loss: 2.1356
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2491 - loss: 2.1357
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2483 - loss: 2.1353
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2478 - loss: 2.1349
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2477 - loss: 2.1343
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2476 - loss: 2.1341
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2474 - loss: 2.1337
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2473 - loss: 2.1333
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2474 - loss: 2.1326
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2475 - loss: 2.1320
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2475 - loss: 2.1316
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2476 - loss: 2.1312
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2478 - loss: 2.1307
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2479 - loss: 2.1304
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2480 - loss: 2.1301
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2482 - loss: 2.1297
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2483 - loss: 2.1293
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2484 - loss: 2.1289
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2485 - loss: 2.1284
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2487 - loss: 2.1278
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2488 - loss: 2.1273
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2489 - loss: 2.1267
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2491 - loss: 2.1261
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2491 - loss: 2.1259 - val_accuracy: 0.2751 - val_loss: 2.0214
Epoch 13/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.0128
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.3258 - loss: 1.9815  
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2998 - loss: 2.0231
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2867 - loss: 2.0500
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2813 - loss: 2.0580
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2776 - loss: 2.0630
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2751 - loss: 2.0665
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2727 - loss: 2.0705
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0734
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0760
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2691 - loss: 2.0778
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2685 - loss: 2.0788
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2678 - loss: 2.0801
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0808
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2667 - loss: 2.0816
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0822
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2656 - loss: 2.0830
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0836
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2648 - loss: 2.0844
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2645 - loss: 2.0850
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2641 - loss: 2.0856
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2637 - loss: 2.0863
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2633 - loss: 2.0869
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2630 - loss: 2.0874
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2627 - loss: 2.0878
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2624 - loss: 2.0882
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2620 - loss: 2.0886
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2617 - loss: 2.0890
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2615 - loss: 2.0893
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2612 - loss: 2.0896
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2612 - loss: 2.0897 - val_accuracy: 0.2712 - val_loss: 2.0199
Epoch 14/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.4375 - loss: 1.9706
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2642 - loss: 2.0749  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2608 - loss: 2.0627
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0656
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2557 - loss: 2.0682
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2542 - loss: 2.0724
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2533 - loss: 2.0753
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2530 - loss: 2.0768
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2528 - loss: 2.0775
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2530 - loss: 2.0779
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2534 - loss: 2.0785
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2535 - loss: 2.0790
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2538 - loss: 2.0793
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2539 - loss: 2.0796
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2540 - loss: 2.0798
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2541 - loss: 2.0798
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.0797
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2545 - loss: 2.0796
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2546 - loss: 2.0796
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2547 - loss: 2.0796
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0796
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0796
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0796
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0795
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0793
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0792
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2547 - loss: 2.0792
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2547 - loss: 2.0790
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0789
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2548 - loss: 2.0788
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2548 - loss: 2.0788 - val_accuracy: 0.2686 - val_loss: 2.0011
Epoch 15/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0529
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0418  
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2616 - loss: 2.0478
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2578 - loss: 2.0502
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2569 - loss: 2.0509
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0513
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2569 - loss: 2.0516
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0517
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2567 - loss: 2.0518
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2564 - loss: 2.0518
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2561 - loss: 2.0522
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2558 - loss: 2.0526
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2555 - loss: 2.0530
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2552 - loss: 2.0537
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2549 - loss: 2.0544
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2546 - loss: 2.0552
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2543 - loss: 2.0560
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2541 - loss: 2.0567
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2540 - loss: 2.0573
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2539 - loss: 2.0578
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2538 - loss: 2.0582
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2538 - loss: 2.0587
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2537 - loss: 2.0591
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2536 - loss: 2.0595
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2535 - loss: 2.0599
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2534 - loss: 2.0603
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2533 - loss: 2.0607
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2532 - loss: 2.0609
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2532 - loss: 2.0611
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2533 - loss: 2.0612
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2533 - loss: 2.0613 - val_accuracy: 0.2738 - val_loss: 2.0001
Epoch 16/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.1721
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2297 - loss: 2.1714  
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2412 - loss: 2.1344
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2464 - loss: 2.1184
[1m 168/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2484 - loss: 2.1112
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2502 - loss: 2.1057
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2520 - loss: 2.1008
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2533 - loss: 2.0968
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2544 - loss: 2.0935
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2552 - loss: 2.0910
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2559 - loss: 2.0891
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2565 - loss: 2.0873
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2570 - loss: 2.0858
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2574 - loss: 2.0842
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2578 - loss: 2.0829
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2582 - loss: 2.0817
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2587 - loss: 2.0804
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2591 - loss: 2.0791
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2596 - loss: 2.0777
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2599 - loss: 2.0765
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2601 - loss: 2.0756
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2604 - loss: 2.0745
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2606 - loss: 2.0736
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2609 - loss: 2.0727
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0718
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2611 - loss: 2.0712
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2612 - loss: 2.0706
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2613 - loss: 2.0700
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2614 - loss: 2.0694
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2615 - loss: 2.0688
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2615 - loss: 2.0688 - val_accuracy: 0.2673 - val_loss: 1.9886
Epoch 17/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0244
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2467 - loss: 2.1285  
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2493 - loss: 2.1018
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2480 - loss: 2.0924
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2471 - loss: 2.0850
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2466 - loss: 2.0802
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2465 - loss: 2.0775
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2471 - loss: 2.0750
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2477 - loss: 2.0731
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2483 - loss: 2.0713
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2488 - loss: 2.0700
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2493 - loss: 2.0694
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2499 - loss: 2.0686
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2506 - loss: 2.0680
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2513 - loss: 2.0671
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2520 - loss: 2.0664
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2527 - loss: 2.0656
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2534 - loss: 2.0647
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2539 - loss: 2.0640
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2545 - loss: 2.0634
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2549 - loss: 2.0629
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2553 - loss: 2.0624
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2557 - loss: 2.0619
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2560 - loss: 2.0614
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2563 - loss: 2.0610
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2566 - loss: 2.0606
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2568 - loss: 2.0602
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2571 - loss: 2.0597
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2573 - loss: 2.0592
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2575 - loss: 2.0588
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2575 - loss: 2.0587 - val_accuracy: 0.2690 - val_loss: 1.9811
Epoch 18/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.2913
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2471 - loss: 2.0655  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2543 - loss: 2.0556
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2603 - loss: 2.0467
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2612 - loss: 2.0441
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2617 - loss: 2.0416
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2631 - loss: 2.0390
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2641 - loss: 2.0370
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2651 - loss: 2.0353
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0342
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0332
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0324
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2671 - loss: 2.0317
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0312
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0311
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0312
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0313
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0312
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2673 - loss: 2.0311
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0311
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2673 - loss: 2.0309
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2673 - loss: 2.0307
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2673 - loss: 2.0305
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2674 - loss: 2.0303
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2675 - loss: 2.0301
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0299
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0297
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0296
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2677 - loss: 2.0295
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2677 - loss: 2.0294 - val_accuracy: 0.2731 - val_loss: 1.9895
Epoch 19/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.2500 - loss: 2.3616
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0353  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2719 - loss: 2.0279
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0277
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0290
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2688 - loss: 2.0281
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2684 - loss: 2.0269
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2685 - loss: 2.0255
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0245
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2690 - loss: 2.0234
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2694 - loss: 2.0230
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2698 - loss: 2.0225
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0222
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2701 - loss: 2.0219
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0217
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0215
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0214
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0213
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0213
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0212
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0211
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0209
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2700 - loss: 2.0207
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2701 - loss: 2.0205
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2701 - loss: 2.0203
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0202
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2702 - loss: 2.0202
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0202
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0202
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2703 - loss: 2.0202 - val_accuracy: 0.2812 - val_loss: 1.9648
Epoch 20/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.9574
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2796 - loss: 2.0308  
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2798 - loss: 2.0251
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2794 - loss: 2.0236
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2774 - loss: 2.0253
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2752 - loss: 2.0254
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0238
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2722 - loss: 2.0220
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2716 - loss: 2.0212
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2713 - loss: 2.0204
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0189
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0176
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0168
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0158
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0149
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0140
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0131
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0124
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0118
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0112
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0107
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0103
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0101
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2708 - loss: 2.0099
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0097
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2709 - loss: 2.0095
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0094
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2710 - loss: 2.0092
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0091
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0090
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2711 - loss: 2.0090 - val_accuracy: 0.2864 - val_loss: 1.9629
Epoch 21/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.1250 - loss: 1.9441
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2615 - loss: 1.9929  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2598 - loss: 2.0251
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2610 - loss: 2.0280
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2629 - loss: 2.0252
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2639 - loss: 2.0222
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2648 - loss: 2.0204
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2652 - loss: 2.0186
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2657 - loss: 2.0172
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2659 - loss: 2.0155
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2661 - loss: 2.0136
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2662 - loss: 2.0122
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2665 - loss: 2.0110
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2668 - loss: 2.0100
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2672 - loss: 2.0090
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2676 - loss: 2.0082
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2679 - loss: 2.0075
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2682 - loss: 2.0071
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2685 - loss: 2.0065
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2687 - loss: 2.0061
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2689 - loss: 2.0055
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2691 - loss: 2.0051
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2693 - loss: 2.0046
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2696 - loss: 2.0041
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2697 - loss: 2.0037
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2699 - loss: 2.0033
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2701 - loss: 2.0028
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0024
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2705 - loss: 2.0020
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2706 - loss: 2.0016
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2707 - loss: 2.0014 - val_accuracy: 0.2945 - val_loss: 1.9654
Epoch 22/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 2.3494
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2791 - loss: 2.0320  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2750 - loss: 2.0189
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2742 - loss: 2.0189
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2747 - loss: 2.0146
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2749 - loss: 2.0123
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2742 - loss: 2.0120
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2732 - loss: 2.0133
[1m 307/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2723 - loss: 2.0143
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2715 - loss: 2.0146
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2711 - loss: 2.0146
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2707 - loss: 2.0144
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0139
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0133
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0126
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2703 - loss: 2.0118
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0111
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0105
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0100
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2704 - loss: 2.0097
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2705 - loss: 2.0092
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2705 - loss: 2.0088
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2705 - loss: 2.0084
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2705 - loss: 2.0081
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2705 - loss: 2.0080
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2705 - loss: 2.0078
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2705 - loss: 2.0077
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2705 - loss: 2.0074
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2705 - loss: 2.0072
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2705 - loss: 2.0070
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2706 - loss: 2.0067 - val_accuracy: 0.2690 - val_loss: 1.9598
Epoch 23/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.8892
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2572 - loss: 2.0252  
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2638 - loss: 2.0145
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2684 - loss: 2.0091
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2718 - loss: 2.0015
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2744 - loss: 1.9967
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2769 - loss: 1.9916
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2787 - loss: 1.9879
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2794 - loss: 1.9864
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2799 - loss: 1.9859
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2801 - loss: 1.9859
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2802 - loss: 1.9858
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2800 - loss: 1.9856
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2799 - loss: 1.9849
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2798 - loss: 1.9846
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2797 - loss: 1.9844
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9842
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9842
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9841
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9839
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9836
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2797 - loss: 1.9834
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2797 - loss: 1.9833
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2797 - loss: 1.9830
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2796 - loss: 1.9829
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2795 - loss: 1.9828
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2794 - loss: 1.9827
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2793 - loss: 1.9828
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2792 - loss: 1.9828
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2791 - loss: 1.9828 - val_accuracy: 0.2842 - val_loss: 1.9410
Epoch 24/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.3125 - loss: 2.5231
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2934 - loss: 2.0158  
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2895 - loss: 1.9850
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2854 - loss: 1.9830
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2843 - loss: 1.9818
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2838 - loss: 1.9815
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2842 - loss: 1.9808
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2846 - loss: 1.9808
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2847 - loss: 1.9811
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2844 - loss: 1.9818
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2842 - loss: 1.9824
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2841 - loss: 1.9823
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2842 - loss: 1.9821
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2843 - loss: 1.9817
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2843 - loss: 1.9812
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2843 - loss: 1.9807
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2843 - loss: 1.9802
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2843 - loss: 1.9799
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2843 - loss: 1.9797
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2842 - loss: 1.9796
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2842 - loss: 1.9795
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2841 - loss: 1.9797
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2840 - loss: 1.9797
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2840 - loss: 1.9798
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2839 - loss: 1.9798
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2838 - loss: 1.9798
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2838 - loss: 1.9798
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2838 - loss: 1.9797
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2837 - loss: 1.9796
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2837 - loss: 1.9796 - val_accuracy: 0.2812 - val_loss: 1.9654
Epoch 25/25

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.0076
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2841 - loss: 1.9580  
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2891 - loss: 1.9454
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2917 - loss: 1.9419
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2924 - loss: 1.9422
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2921 - loss: 1.9410
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2913 - loss: 1.9417
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2903 - loss: 1.9430
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 1ms/step - accuracy: 0.2900 - loss: 1.9437
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2895 - loss: 1.9448
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2889 - loss: 1.9460
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2885 - loss: 1.9471
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2883 - loss: 1.9478
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2878 - loss: 1.9488
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2874 - loss: 1.9498
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2870 - loss: 1.9507
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2866 - loss: 1.9520
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2862 - loss: 1.9533
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2859 - loss: 1.9544
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2855 - loss: 1.9554
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2852 - loss: 1.9561
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2849 - loss: 1.9568
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2846 - loss: 1.9575
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2845 - loss: 1.9581
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2843 - loss: 1.9588
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step - accuracy: 0.2841 - loss: 1.9593
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2839 - loss: 1.9598
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.2838 - loss: 1.9602
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.2837 - loss: 1.9605
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step - accuracy: 0.2836 - loss: 1.9607 - val_accuracy: 0.2786 - val_loss: 1.9473

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 655ms/step
[1m63/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 815us/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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:18[0m 855ms/step
[1m 60/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 855us/step  
[1m127/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 799us/step
[1m192/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 790us/step
[1m265/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 762us/step
[1m338/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 745us/step
[1m412/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 733us/step
[1m484/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 728us/step
[1m551/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 733us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m66/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 774us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 59/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 872us/step
[1m125/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 813us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 26.98 [%]
Global F1 score (validation) = 23.44 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.11325783 0.12596434 0.10711747 ... 0.00788581 0.09479005 0.00818091]
 [0.2160933  0.18339242 0.16544574 ... 0.00183189 0.17144808 0.01668846]
 [0.15007672 0.1988065  0.18746766 ... 0.00201978 0.16561903 0.02507237]
 ...
 [0.18705997 0.18476401 0.20063199 ... 0.00203387 0.15580893 0.0258641 ]
 [0.18813099 0.20686896 0.1412766  ... 0.00338272 0.16849239 0.02256452]
 [0.13588482 0.18448013 0.13227949 ... 0.00394722 0.13043578 0.01403417]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 29.32 [%]
Global accuracy score (test) = 23.68 [%]
Global F1 score (train) = 25.92 [%]
Global F1 score (test) = 20.53 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.28      0.09      0.13       184
 CAMINAR CON MÓVIL O LIBRO       0.17      0.67      0.27       184
       CAMINAR USUAL SPEED       0.17      0.05      0.08       184
            CAMINAR ZIGZAG       0.00      0.00      0.00       184
          DE PIE BARRIENDO       0.19      0.41      0.26       184
   DE PIE DOBLANDO TOALLAS       0.20      0.44      0.27       184
    DE PIE MOVIENDO LIBROS       0.01      0.02      0.01       184
          DE PIE USANDO PC       0.30      0.15      0.20       184
        FASE REPOSO CON K5       0.43      0.75      0.55       184
INCREMENTAL CICLOERGOMETRO       0.00      0.00      0.00       184
           SENTADO LEYENDO       0.18      0.14      0.16       184
         SENTADO USANDO PC       0.17      0.03      0.05       184
      SENTADO VIENDO LA TV       0.31      0.25      0.28       184
   SUBIR Y BAJAR ESCALERAS       0.47      0.11      0.18       184
                    TROTAR       0.95      0.47      0.63       161

                  accuracy                           0.24      2737
                 macro avg       0.26      0.24      0.21      2737
              weighted avg       0.25      0.24      0.20      2737


Accuracy capturado en la ejecución 29: 23.68 [%]
F1-score capturado en la ejecución 29: 20.53 [%]

=== 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)
(18676, 3, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7:50[0m 808ms/step
[1m 63/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 821us/step  
[1m133/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 766us/step
[1m202/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 755us/step
[1m272/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 746us/step
[1m345/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 734us/step
[1m416/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 730us/step
[1m488/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 725us/step
[1m554/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 730us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m66/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 775us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 58/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 881us/step
[1m131/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 774us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 27.86 [%]
Global F1 score (validation) = 24.62 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.141724   0.17022282 0.17773321 ... 0.00375945 0.1551664  0.01925883]
 [0.16661562 0.18218005 0.19206339 ... 0.00134763 0.16340716 0.01990896]
 [0.17253874 0.16681921 0.18770865 ... 0.00201841 0.16475023 0.02237361]
 ...
 [0.18741877 0.16715439 0.19022405 ... 0.00075356 0.14949134 0.02804295]
 [0.16828229 0.15538181 0.17197427 ... 0.00466922 0.14776883 0.01527159]
 [0.13010156 0.15811725 0.14501216 ... 0.00422911 0.11763735 0.01034538]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 31.4 [%]
Global accuracy score (test) = 27.84 [%]
Global F1 score (train) = 28.78 [%]
Global F1 score (test) = 25.78 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.09      0.03      0.04       184
 CAMINAR CON MÓVIL O LIBRO       0.19      0.55      0.28       184
       CAMINAR USUAL SPEED       0.19      0.13      0.15       184
            CAMINAR ZIGZAG       0.10      0.11      0.11       184
          DE PIE BARRIENDO       0.17      0.14      0.15       184
   DE PIE DOBLANDO TOALLAS       0.23      0.38      0.29       184
    DE PIE MOVIENDO LIBROS       0.37      0.21      0.26       184
          DE PIE USANDO PC       0.29      0.72      0.42       184
        FASE REPOSO CON K5       0.77      0.62      0.69       184
INCREMENTAL CICLOERGOMETRO       0.45      0.23      0.31       184
           SENTADO LEYENDO       0.27      0.18      0.22       184
         SENTADO USANDO PC       0.05      0.01      0.01       184
      SENTADO VIENDO LA TV       0.33      0.51      0.40       184
   SUBIR Y BAJAR ESCALERAS       0.18      0.07      0.10       184
                    TROTAR       0.96      0.29      0.45       161

                  accuracy                           0.28      2737
                 macro avg       0.31      0.28      0.26      2737
              weighted avg       0.30      0.28      0.26      2737


Accuracy capturado en la ejecución 30: 27.84 [%]
F1-score capturado en la ejecución 30: 25.78 [%]

=== RESUMEN FINAL ===
Accuracies: [24.77, 24.19, 25.61, 26.6, 24.92, 23.86, 25.94, 23.64, 24.66, 25.21, 27.99, 26.49, 24.7, 25.76, 24.33, 24.22, 23.27, 26.05, 27.99, 28.02, 26.82, 22.54, 22.32, 26.6, 25.06, 27.11, 26.01, 26.27, 23.68, 27.84]
F1-scores: [21.71, 22.56, 20.99, 23.63, 23.11, 20.91, 23.73, 21.15, 22.04, 22.08, 25.55, 25.14, 21.09, 21.66, 21.62, 21.67, 20.67, 24.21, 25.53, 25.06, 23.37, 19.86, 20.33, 23.02, 21.61, 25.58, 23.1, 23.14, 20.53, 25.78]
Accuracy mean: 25.4157 | std: 1.5674
F1 mean: 22.6810 | std: 1.7383

Resultados guardados en /mnt/nvme1n2/git/uniovi-simur-wearablepermed-data/output/Paper_results/cases_dataset_C/case_C_CAPTURE24_acc_17_classes/metrics_test.npz
