2025-11-08 14:45:05.286090: 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`.
2025-11-08 14:45:05.297853: 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 00:00:1762609505.311973  922985 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762609505.316410  922985 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762609505.327149  922985 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762609505.327171  922985 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762609505.327173  922985 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762609505.327175  922985 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 14:45:05.330566: 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(
2025-11-08 14:45:08,252	INFO worker.py:1927 -- Started a local Ray instance.
2025-11-08 14:45:08,926	INFO tune.py:253 -- Initializing Ray automatically. For cluster usage or custom Ray initialization, call `ray.init(...)` before `Tuner(...)`.
2025-11-08 14:45:08,996	INFO trial.py:182 -- Creating a new dirname dir_2414b_05b6 because trial dirname 'dir_2414b' already exists.
2025-11-08 14:45:09,000	INFO trial.py:182 -- Creating a new dirname dir_2414b_149c because trial dirname 'dir_2414b' already exists.
2025-11-08 14:45:09,002	INFO trial.py:182 -- Creating a new dirname dir_2414b_0b60 because trial dirname 'dir_2414b' already exists.
2025-11-08 14:45:09,004	INFO trial.py:182 -- Creating a new dirname dir_2414b_449d because trial dirname 'dir_2414b' already exists.
2025-11-08 14:45:09,006	INFO trial.py:182 -- Creating a new dirname dir_2414b_62ef because trial dirname 'dir_2414b' already exists.
2025-11-08 14:45:09,008	INFO trial.py:182 -- Creating a new dirname dir_2414b_89c7 because trial dirname 'dir_2414b' already exists.
2025-11-08 14:45:09,011	INFO trial.py:182 -- Creating a new dirname dir_2414b_f6cd because trial dirname 'dir_2414b' already exists.
2025-11-08 14:45:09,013	INFO trial.py:182 -- Creating a new dirname dir_2414b_9688 because trial dirname 'dir_2414b' already exists.
2025-11-08 14:45:09,016	INFO trial.py:182 -- Creating a new dirname dir_2414b_476b because trial dirname 'dir_2414b' already exists.
2025-11-08 14:45:09,019	INFO trial.py:182 -- Creating a new dirname dir_2414b_a509 because trial dirname 'dir_2414b' already exists.
2025-11-08 14:45:09,022	INFO trial.py:182 -- Creating a new dirname dir_2414b_6853 because trial dirname 'dir_2414b' already exists.
2025-11-08 14:45:09,025	INFO trial.py:182 -- Creating a new dirname dir_2414b_cc57 because trial dirname 'dir_2414b' already exists.
2025-11-08 14:45:09,028	INFO trial.py:182 -- Creating a new dirname dir_2414b_6234 because trial dirname 'dir_2414b' already exists.
2025-11-08 14:45:09,032	INFO trial.py:182 -- Creating a new dirname dir_2414b_7543 because trial dirname 'dir_2414b' already exists.
2025-11-08 14:45:09,035	INFO trial.py:182 -- Creating a new dirname dir_2414b_970e because trial dirname 'dir_2414b' already exists.
2025-11-08 14:45:09,038	INFO trial.py:182 -- Creating a new dirname dir_2414b_5e73 because trial dirname 'dir_2414b' already exists.
2025-11-08 14:45:09,042	INFO trial.py:182 -- Creating a new dirname dir_2414b_3e4a because trial dirname 'dir_2414b' already exists.
2025-11-08 14:45:09,050	INFO trial.py:182 -- Creating a new dirname dir_2414b_a081 because trial dirname 'dir_2414b' already exists.
2025-11-08 14:45:09,055	INFO trial.py:182 -- Creating a new dirname dir_2414b_50cb because trial dirname 'dir_2414b' already exists.
1 GPU(s) detected and VRAM set to crossover mode..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
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_PI/case_PI_CAPTURE24_acc_superclasses_CPA_METs/CAPTURE24_hyperparameters_tuning
To visualize your results with TensorBoard, run: `tensorboard --logdir /tmp/ray/session_2025-11-08_14-45-07_535057_922985/artifacts/2025-11-08_14-45-08/CAPTURE24_hyperparameters_tuning/driver_artifacts`

Trial status: 20 PENDING
Current time: 2025-11-08 14:45:09. Total running time: 0s
Logical resource usage: 17.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status       N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs │
├─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_2414b    PENDING            2   adam            relu                                   32                 16                  5                 1          7.66658e-05         28 │
│ trial_2414b    PENDING            2   adam            relu                                   16                 64                  3                 1          1.29147e-05         16 │
│ trial_2414b    PENDING            3   rmsprop         relu                                   16                 16                  3                 0          1.74324e-05         22 │
│ trial_2414b    PENDING            3   rmsprop         relu                                   32                 32                  5                 1          6.70381e-05         15 │
│ trial_2414b    PENDING            2   rmsprop         tanh                                   32                 64                  3                 1          1.0258e-05          28 │
│ trial_2414b    PENDING            2   rmsprop         relu                                   16                 32                  5                 0          1.48377e-05         29 │
│ trial_2414b    PENDING            2   adam            tanh                                   32                 32                  3                 1          0.000126055         15 │
│ trial_2414b    PENDING            3   adam            relu                                   16                 32                  3                 0          2.34799e-05         18 │
│ trial_2414b    PENDING            2   rmsprop         tanh                                   32                 32                  5                 1          7.10308e-06         26 │
│ trial_2414b    PENDING            2   adam            tanh                                   16                 64                  3                 0          9.84048e-05         22 │
│ trial_2414b    PENDING            2   adam            relu                                   16                 32                  5                 0          8.43998e-05         27 │
│ trial_2414b    PENDING            2   rmsprop         relu                                   32                 32                  3                 0          1.54606e-05         21 │
│ trial_2414b    PENDING            3   adam            relu                                   32                 16                  3                 0          2.67621e-05         27 │
│ trial_2414b    PENDING            3   adam            relu                                   32                 64                  5                 0          5.09414e-06         25 │
│ trial_2414b    PENDING            2   adam            tanh                                   32                 32                  5                 0          2.32663e-05         22 │
│ trial_2414b    PENDING            2   rmsprop         tanh                                   16                 32                  5                 1          5.1345e-06          28 │
│ trial_2414b    PENDING            2   adam            relu                                   32                 64                  5                 1          7.77942e-05         27 │
│ trial_2414b    PENDING            3   adam            relu                                   16                 32                  3                 1          8.65481e-05         26 │
│ trial_2414b    PENDING            2   rmsprop         relu                                   32                 16                  3                 0          0.000111363         18 │
│ trial_2414b    PENDING            2   adam            relu                                   16                 16                  3                 1          7.55321e-05         16 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯

Trial trial_2414b started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_2414b 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             0.00001 │
╰──────────────────────────────────────╯
Trial trial_2414b started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_2414b config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            28 │
│ funcion_activacion              relu │
│ num_resblocks                      1 │
│ numero_filtros                    16 │
│ optimizador                     adam │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00008 │
╰──────────────────────────────────────╯
Trial trial_2414b started with configuration:
╭─────────────────────────────────────╮
│ Trial trial_2414b config            │
├─────────────────────────────────────┤
│ N_capas                           2 │
│ epochs                           22 │
│ funcion_activacion             tanh │
│ num_resblocks                     0 │
│ numero_filtros                   64 │
│ optimizador                    adam │
│ tamanho_filtro                    3 │
│ tamanho_minilote                 16 │
│ tasa_aprendizaje             0.0001 │
╰─────────────────────────────────────╯
Trial trial_2414b started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_2414b config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            18 │
│ funcion_activacion              relu │
│ num_resblocks                      0 │
│ numero_filtros                    32 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00002 │
╰──────────────────────────────────────╯
Trial trial_2414b started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_2414b config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            27 │
│ funcion_activacion              relu │
│ num_resblocks                      1 │
│ numero_filtros                    64 │
│ optimizador                     adam │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00008 │
╰──────────────────────────────────────╯
Trial trial_2414b started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_2414b config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            16 │
│ funcion_activacion              relu │
│ num_resblocks                      1 │
│ numero_filtros                    64 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00001 │
╰──────────────────────────────────────╯
Trial trial_2414b started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_2414b config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            15 │
│ funcion_activacion              relu │
│ num_resblocks                      1 │
│ numero_filtros                    32 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00007 │
╰──────────────────────────────────────╯
Trial trial_2414b started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_2414b config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            26 │
│ funcion_activacion              tanh │
│ num_resblocks                      1 │
│ numero_filtros                    32 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00001 │
╰──────────────────────────────────────╯
Trial trial_2414b started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_2414b config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            27 │
│ funcion_activacion              relu │
│ num_resblocks                      0 │
│ numero_filtros                    32 │
│ optimizador                     adam │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00008 │
╰──────────────────────────────────────╯
Trial trial_2414b started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_2414b config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            15 │
│ funcion_activacion              tanh │
│ num_resblocks                      1 │
│ numero_filtros                    32 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00013 │
╰──────────────────────────────────────╯
Trial trial_2414b started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_2414b config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            27 │
│ funcion_activacion              relu │
│ num_resblocks                      0 │
│ numero_filtros                    16 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00003 │
╰──────────────────────────────────────╯
Trial trial_2414b started with configuration:
[36m(train_cnn_ray_tune pid=924619)[0m 2025-11-08 14:45:12.195053: 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=924619)[0m 2025-11-08 14:45:12.215677: 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=924619)[0m WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
[36m(train_cnn_ray_tune pid=924619)[0m E0000 00:00:1762609512.243675  925752 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=924619)[0m E0000 00:00:1762609512.251399  925752 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=924619)[0m W0000 00:00:1762609512.271800  925752 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=924619)[0m W0000 00:00:1762609512.271836  925752 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=924619)[0m W0000 00:00:1762609512.271839  925752 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=924619)[0m W0000 00:00:1762609512.271840  925752 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=924621)[0m 2025-11-08 14:45:12.365158: 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=924621)[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=924619)[0m 2025-11-08 14:45:15.426672: 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=924619)[0m 2025-11-08 14:45:15.426730: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:167] env: CUDA_VISIBLE_DEVICES=""
[36m(train_cnn_ray_tune pid=924619)[0m 2025-11-08 14:45:15.426740: 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=924619)[0m 2025-11-08 14:45:15.426746: 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=924619)[0m 2025-11-08 14:45:15.426752: 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=924619)[0m 2025-11-08 14:45:15.426756: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:190] hostname: simur-MS-7B94
[36m(train_cnn_ray_tune pid=924619)[0m 2025-11-08 14:45:15.426969: 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=924619)[0m 2025-11-08 14:45:15.427003: 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=924619)[0m 2025-11-08 14:45:15.427008: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:291] kernel version seems to match DSO: 570.133.7
╭──────────────────────────────────────╮
│ Trial trial_2414b config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            22 │
│ funcion_activacion              tanh │
│ num_resblocks                      0 │
│ numero_filtros                    32 │
│ optimizador                     adam │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00002 │
╰──────────────────────────────────────╯
Trial trial_2414b started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_2414b config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            29 │
│ funcion_activacion              relu │
│ num_resblocks                      0 │
│ numero_filtros                    32 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00001 │
╰──────────────────────────────────────╯
Trial trial_2414b started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_2414b config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            28 │
│ funcion_activacion              tanh │
│ num_resblocks                      1 │
│ numero_filtros                    32 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00001 │
╰──────────────────────────────────────╯
Trial trial_2414b started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_2414b config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            21 │
│ funcion_activacion              relu │
│ num_resblocks                      0 │
│ numero_filtros                    32 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00002 │
╰──────────────────────────────────────╯
Trial trial_2414b started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_2414b config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            26 │
│ funcion_activacion              relu │
│ num_resblocks                      1 │
│ numero_filtros                    32 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00009 │
╰──────────────────────────────────────╯
Trial trial_2414b started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_2414b config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            22 │
│ funcion_activacion              relu │
│ num_resblocks                      0 │
│ numero_filtros                    16 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00002 │
╰──────────────────────────────────────╯
Trial trial_2414b started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_2414b config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            25 │
│ funcion_activacion              relu │
│ num_resblocks                      0 │
│ numero_filtros                    64 │
│ optimizador                     adam │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00001 │
╰──────────────────────────────────────╯
Trial trial_2414b started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_2414b config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            16 │
│ funcion_activacion              relu │
│ num_resblocks                      1 │
│ numero_filtros                    16 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00008 │
╰──────────────────────────────────────╯
Trial trial_2414b started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_2414b config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            18 │
│ funcion_activacion              relu │
│ num_resblocks                      0 │
│ numero_filtros                    16 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00011 │
╰──────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=924619)[0m Epoch 1/28
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15:16[0m 3s/step - accuracy: 0.2812 - loss: 1.9180
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.2622 - loss: 1.9123 
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.2535 - loss: 1.9024
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m  8/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.2488 - loss: 1.8928
[1m 10/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 27ms/step - accuracy: 0.2455 - loss: 1.8862
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m 13/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 27ms/step - accuracy: 0.2434 - loss: 1.8789
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m 15/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 27ms/step - accuracy: 0.2434 - loss: 1.8776
[1m 18/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 26ms/step - accuracy: 0.2433 - loss: 1.8777
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29:32[0m 3s/step - accuracy: 0.5000 - loss: 1.4280
[1m  3/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 29ms/step - accuracy: 0.3194 - loss: 1.7352
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m 20/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 27ms/step - accuracy: 0.2430 - loss: 1.8772
[1m 22/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 27ms/step - accuracy: 0.2430 - loss: 1.8757
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m  5/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 29ms/step - accuracy: 0.2692 - loss: 1.8186
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m 25/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 26ms/step - accuracy: 0.2442 - loss: 1.8700
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m  8/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 27ms/step - accuracy: 0.2411 - loss: 1.9245
[1m 10/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 26ms/step - accuracy: 0.2317 - loss: 1.9770
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 26ms/step - accuracy: 0.2453 - loss: 1.8650
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 26ms/step - accuracy: 0.2472 - loss: 1.8589
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m 13/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 25ms/step - accuracy: 0.2282 - loss: 2.0308
[1m 16/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 25ms/step - accuracy: 0.2273 - loss: 2.0588
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m 33/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 26ms/step - accuracy: 0.2496 - loss: 1.8541
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m 36/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 25ms/step - accuracy: 0.2513 - loss: 1.8509
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m 38/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 26ms/step - accuracy: 0.2525 - loss: 1.8486
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m 40/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 26ms/step - accuracy: 0.2538 - loss: 1.8461
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m 43/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 26ms/step - accuracy: 0.2556 - loss: 1.8425
[36m(train_cnn_ray_tune pid=924595)[0m Epoch 1/18[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=924611)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33:41[0m 7s/step - accuracy: 0.3125 - loss: 1.5640[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=924617)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2378 - loss: 2.0920 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2746 - loss: 1.9984[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 43ms/step - accuracy: 0.3185 - loss: 1.6711
[1m 94/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 43ms/step - accuracy: 0.3192 - loss: 1.6693[32m [repeated 171x across cluster][0m
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m 96/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 43ms/step - accuracy: 0.3205 - loss: 1.6659[32m [repeated 126x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59:36[0m 6s/step - accuracy: 0.1875 - loss: 1.7382
[1m  2/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 61ms/step - accuracy: 0.2344 - loss: 1.7248[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m139/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m13s[0m 28ms/step - accuracy: 0.2545 - loss: 2.0292[32m [repeated 146x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m156/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 22ms/step - accuracy: 0.2571 - loss: 1.9441
[1m159/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 22ms/step - accuracy: 0.2574 - loss: 1.9426[32m [repeated 219x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m169/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 28ms/step - accuracy: 0.2587 - loss: 2.0155
[1m171/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 28ms/step - accuracy: 0.2590 - loss: 2.0147
[1m173/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 28ms/step - accuracy: 0.2592 - loss: 2.0140
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m233/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m1s[0m 26ms/step - accuracy: 0.3835 - loss: 1.4992
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m1s[0m 26ms/step - accuracy: 0.3839 - loss: 1.4982
[1m237/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m1s[0m 26ms/step - accuracy: 0.3843 - loss: 1.4971
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m277/619[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2689 - loss: 1.9741 
[1m279/619[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2691 - loss: 1.9733[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m209/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 43ms/step - accuracy: 0.3740 - loss: 1.5366
[1m211/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 43ms/step - accuracy: 0.3747 - loss: 1.5348[32m [repeated 310x across cluster][0m
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 43ms/step - accuracy: 0.3754 - loss: 1.5332[32m [repeated 272x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m172/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m18s[0m 40ms/step - accuracy: 0.3401 - loss: 1.6352[32m [repeated 192x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m10s[0m 55ms/step - accuracy: 0.3195 - loss: 1.7562
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m10s[0m 55ms/step - accuracy: 0.3197 - loss: 1.7558[32m [repeated 174x across cluster][0m
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 32ms/step - accuracy: 0.3975 - loss: 1.4635 - val_accuracy: 0.5327 - val_loss: 0.9360
[36m(train_cnn_ray_tune pid=924595)[0m Epoch 2/18
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 77ms/step - accuracy: 0.5938 - loss: 1.0375
[36m(train_cnn_ray_tune pid=924617)[0m 
[1m307/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 31ms/step - accuracy: 0.4176 - loss: 1.4779
[1m309/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 31ms/step - 
[36m(train_cnn_ray_tune pid=924617)[0m accuracy: 0.4179 - loss: 1.4771
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m  2/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 60ms/step - accuracy: 0.4766 - loss: 1.7050 
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.4861 - loss: 1.1320  
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 28ms/step - accuracy: 0.4823 - loss: 1.1373
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 102ms/step - accuracy: 0.5938 - loss: 1.5113
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 41ms/step - accuracy: 0.5712 - loss: 1.4902 
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m560/619[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 23ms/step - accuracy: 0.3093 - loss: 1.7616
[1m562/619[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 23ms/step - accuracy: 0.3095 - loss: 1.7609
[1m566/619[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 23ms/step - accuracy: 0.3099 - loss: 1.7595
[36m(train_cnn_ray_tune pid=924617)[0m 
[1m 14/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.4886 - loss: 1.2512 
[1m 16/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.4907 - loss: 1.2427[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m5s[0m 27ms/step - accuracy: 0.4844 - loss: 1.2194
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m5s[0m 27ms/step - accuracy: 0.4847 - loss: 1.2191[32m [repeated 360x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m597/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 22ms/step - accuracy: 0.3129 - loss: 1.7493[32m [repeated 355x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m315/619[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m11s[0m 38ms/step - accuracy: 0.3762 - loss: 1.5537[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m331/619[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 37ms/step - accuracy: 0.3407 - loss: 1.7111
[1m333/619[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 37ms/step - accuracy: 0.3408 - loss: 1.7106[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m17s[0m 41ms/step - accuracy: 0.4846 - loss: 1.3326 - val_accuracy: 0.6682 - val_loss: 0.7141[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924631)[0m Epoch 2/27[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924617)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 100ms/step - accuracy: 0.3438 - loss: 1.5814[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924617)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.4253 - loss: 1.3581 
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m 10/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 22ms/step - accuracy: 0.4832 - loss: 1.2316
[1m 13/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 22ms/step - accuracy: 0.4838 - loss: 1.2292
[1m 15/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 22ms/step - accuracy: 0.4845 - loss: 1.2309
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 97ms/step - accuracy: 0.3750 - loss: 1.5725
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 39ms/step - accuracy: 0.3715 - loss: 1.5327
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m300/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 48ms/step - accuracy: 0.3435 - loss: 1.6956
[1m301/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 48ms/step - accuracy: 0.3436 - loss: 1.6953
[1m302/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 48ms/step - accuracy: 0.3437 - loss: 1.6950[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 68ms/step - accuracy: 0.3750 - loss: 1.5294
[1m  3/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 30ms/step - accuracy: 0.4028 - loss: 1.4998
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m112/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m9s[0m 18ms/step - accuracy: 0.4588 - loss: 1.2901
[1m115/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m9s[0m 18ms/step - accuracy: 0.4584 - loss: 1.2904[32m [repeated 401x across cluster][0m

Trial status: 20 RUNNING
Current time: 2025-11-08 14:45:39. 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_2414b    RUNNING            2   adam            relu                                   32                 16                  5                 1          7.66658e-05         28 │
│ trial_2414b    RUNNING            2   adam            relu                                   16                 64                  3                 1          1.29147e-05         16 │
│ trial_2414b    RUNNING            3   rmsprop         relu                                   16                 16                  3                 0          1.74324e-05         22 │
│ trial_2414b    RUNNING            3   rmsprop         relu                                   32                 32                  5                 1          6.70381e-05         15 │
│ trial_2414b    RUNNING            2   rmsprop         tanh                                   32                 64                  3                 1          1.0258e-05          28 │
│ trial_2414b    RUNNING            2   rmsprop         relu                                   16                 32                  5                 0          1.48377e-05         29 │
│ trial_2414b    RUNNING            2   adam            tanh                                   32                 32                  3                 1          0.000126055         15 │
│ trial_2414b    RUNNING            3   adam            relu                                   16                 32                  3                 0          2.34799e-05         18 │
│ trial_2414b    RUNNING            2   rmsprop         tanh                                   32                 32                  5                 1          7.10308e-06         26 │
│ trial_2414b    RUNNING            2   adam            tanh                                   16                 64                  3                 0          9.84048e-05         22 │
│ trial_2414b    RUNNING            2   adam            relu                                   16                 32                  5                 0          8.43998e-05         27 │
│ trial_2414b    RUNNING            2   rmsprop         relu                                   32                 32                  3                 0          1.54606e-05         21 │
│ trial_2414b    RUNNING            3   adam            relu                                   32                 16                  3                 0          2.67621e-05         27 │
│ trial_2414b    RUNNING            3   adam            relu                                   32                 64                  5                 0          5.09414e-06         25 │
│ trial_2414b    RUNNING            2   adam            tanh                                   32                 32                  5                 0          2.32663e-05         22 │
│ trial_2414b    RUNNING            2   rmsprop         tanh                                   16                 32                  5                 1          5.1345e-06          28 │
│ trial_2414b    RUNNING            2   adam            relu                                   32                 64                  5                 1          7.77942e-05         27 │
│ trial_2414b    RUNNING            3   adam            relu                                   16                 32                  3                 1          8.65481e-05         26 │
│ trial_2414b    RUNNING            2   rmsprop         relu                                   32                 16                  3                 0          0.000111363         18 │
│ trial_2414b    RUNNING            2   adam            relu                                   16                 16                  3                 1          7.55321e-05         16 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m470/619[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 36ms/step - accuracy: 0.4007 - loss: 1.4936[32m [repeated 249x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m 49/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 24ms/step - accuracy: 0.3992 - loss: 1.5441[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m 52/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 24ms/step - accuracy: 0.3996 - loss: 1.5438
[1m 55/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 24ms/step - accuracy: 0.3999 - loss: 1.5432[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 30ms/step - accuracy: 0.5015 - loss: 1.1406 - val_accuracy: 0.6218 - val_loss: 0.7804[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924595)[0m Epoch 3/18[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 92ms/step - accuracy: 0.3750 - loss: 1.3376[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.4601 - loss: 1.2644 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 28ms/step - accuracy: 0.4679 - loss: 1.2571
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 36ms/step - accuracy: 0.3021 - loss: 1.4880 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 37ms/step - accuracy: 0.3434 - loss: 1.4232
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m  3/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 42ms/step - accuracy: 0.5451 - loss: 0.9038  
[1m  5/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 37ms/step - accuracy: 0.5658 - loss: 0.9023
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m332/619[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m5s[0m 19ms/step - accuracy: 0.4567 - loss: 1.2852
[1m334/619[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m5s[0m 19ms/step - accuracy: 0.4567 - loss: 1.2850
[1m336/619[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m5s[0m 19ms/step - accuracy: 0.4568 - loss: 1.2848[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 122ms/step - accuracy: 0.6250 - loss: 1.1984
[1m  2/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 58ms/step - accuracy: 0.6016 - loss: 1.2526 [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 32ms/step - accuracy: 0.3748 - loss: 1.4933
[1m240/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 32ms/step - accuracy: 0.3750 - loss: 1.4931[32m [repeated 295x across cluster][0m
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m8s[0m 36ms/step - accuracy: 0.6329 - loss: 0.9098[32m [repeated 217x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m 80/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 47ms/step - accuracy: 0.4664 - loss: 1.4433[32m [repeated 111x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m 82/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 47ms/step - accuracy: 0.4663 - loss: 1.4430
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 47ms/step - accuracy: 0.4663 - loss: 1.4426[32m [repeated 175x across cluster][0m
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m10s[0m 31ms/step - accuracy: 0.4790 - loss: 1.3587 - val_accuracy: 0.5713 - val_loss: 0.9306[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=924628)[0m Epoch 3/22[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 75ms/step - accuracy: 0.5625 - loss: 1.1389[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m226/619[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 25ms/step - accuracy: 0.4450 - loss: 1.4530 
[1m227/619[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m10s[0m 26ms/step - accuracy: 0.4450 - loss: 1.4530[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m  3/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 51ms/step - accuracy: 0.4514 - loss: 1.1977  
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m4s[0m 36ms/step - accuracy: 0.6312 - loss: 0.9050
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m4s[0m 36ms/step - accuracy: 0.6313 - loss: 0.9049
[1m182/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m4s[0m 36ms/step - accuracy: 0.6313 - loss: 0.9048[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m6s[0m 47ms/step - accuracy: 0.4658 - loss: 1.4237
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m6s[0m 47ms/step - accuracy: 0.4658 - loss: 1.4236[32m [repeated 336x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m595/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 21ms/step - accuracy: 0.4646 - loss: 1.2626[32m [repeated 279x across cluster][0m
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m230/619[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m11s[0m 31ms/step - accuracy: 0.5461 - loss: 1.0798[32m [repeated 111x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m 56/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 33ms/step - accuracy: 0.4702 - loss: 1.3798
[1m 58/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 33ms/step - accuracy: 0.4709 - loss: 1.3782[32m [repeated 113x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 42ms/step - accuracy: 0.4176 - loss: 1.4491 - val_accuracy: 0.6327 - val_loss: 0.7822[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m Epoch 2/26[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 108ms/step - accuracy: 0.4375 - loss: 1.1983[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m 18/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.4639 - loss: 1.3064 
[1m 20/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.4616 - loss: 1.3129[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 60ms/step - accuracy: 0.7812 - loss: 0.7287
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.7569 - loss: 0.7323 
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m397/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 30ms/step - accuracy: 0.3990 - loss: 1.5327
[1m399/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 30ms/step - accuracy: 0.3991 - loss: 1.5327
[1m401/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 30ms/step - accuracy: 0.3991 - loss: 1.5327
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m396/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 30ms/step - accuracy: 0.5475 - loss: 1.0727
[1m398/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 30ms/step - accuracy: 0.5475 - loss: 1.0725[32m [repeated 354x across cluster][0m
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m102/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 45ms/step - accuracy: 0.6224 - loss: 0.9209[32m [repeated 293x across cluster][0m
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 37ms/step - accuracy: 0.6604 - loss: 0.8010[32m [repeated 122x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m116/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 22ms/step - accuracy: 0.5262 - loss: 1.1419
[1m120/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 22ms/step - accuracy: 0.5260 - loss: 1.1419[32m [repeated 98x across cluster][0m
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m11s[0m 35ms/step - accuracy: 0.5133 - loss: 1.2323 - val_accuracy: 0.6096 - val_loss: 0.8603[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=924628)[0m Epoch 4/22[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 94ms/step - accuracy: 0.5312 - loss: 1.0806[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m520/619[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 28ms/step - accuracy: 0.5644 - loss: 1.0755
[1m522/619[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 28ms/step - accuracy: 0.5644 - loss: 1.0753
[1m523/619[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 28ms/step - accuracy: 0.5644 - loss: 1.0753
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m 43/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.6606 - loss: 0.8013 
[1m 45/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.6606 - loss: 0.8011[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 78ms/step - accuracy: 0.4375 - loss: 1.3050
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 41ms/step - accuracy: 0.4618 - loss: 1.2857
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m 38/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 23ms/step - accuracy: 0.4458 - loss: 1.3652
[1m 40/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 23ms/step - accuracy: 0.4469 - loss: 1.3633
[1m 42/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 23ms/step - accuracy: 0.4475 - loss: 1.3622
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m347/619[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 21ms/step - accuracy: 0.5225 - loss: 1.1240
[1m350/619[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 21ms/step - accuracy: 0.5226 - loss: 1.1238[32m [repeated 387x across cluster][0m
[36m(train_cnn_ray_tune pid=924617)[0m 
[1m209/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m3s[0m 30ms/step - accuracy: 0.5805 - loss: 0.9352[32m [repeated 270x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m 44/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 50ms/step - accuracy: 0.4781 - loss: 1.3200[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m 47/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m13s[0m 51ms/step - accuracy: 0.4782 - loss: 1.3202
[1m 48/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m13s[0m 51ms/step - accuracy: 0.4782 - loss: 1.3203[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 38ms/step - accuracy: 0.4429 - loss: 1.3343 - val_accuracy: 0.5158 - val_loss: 1.0333[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m Epoch 4/27[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 73ms/step - accuracy: 0.6250 - loss: 0.9478[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m3s[0m 31ms/step - accuracy: 0.4762 - loss: 1.3754
[1m214/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m2s[0m 31ms/step - accuracy: 0.4762 - loss: 1.3753
[1m216/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m2s[0m 31ms/step - accuracy: 0.4762 - loss: 1.3751
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 27ms/step - accuracy: 0.6283 - loss: 0.9283 
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 27ms/step - accuracy: 0.6214 - loss: 0.9173[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 33ms/step - accuracy: 0.4929 - loss: 1.2671
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 33ms/step - accuracy: 0.4929 - loss: 1.2671
[1m270/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 33ms/step - accuracy: 0.4930 - loss: 1.2670
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 73ms/step - accuracy: 0.5312 - loss: 1.2241
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 26ms/step - accuracy: 0.5556 - loss: 1.1082 [32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m134/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m12s[0m 26ms/step - accuracy: 0.5983 - loss: 0.9468
[1m136/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m12s[0m 26ms/step - accuracy: 0.5982 - loss: 0.9471
[1m138/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m12s[0m 26ms/step - accuracy: 0.5981 - loss: 0.9472
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m599/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 21ms/step - accuracy: 0.5270 - loss: 1.1076
[1m601/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 21ms/step - accuracy: 0.5271 - loss: 1.1075[32m [repeated 327x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m606/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 21ms/step - accuracy: 0.5272 - loss: 1.1072[32m [repeated 207x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m112/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m14s[0m 29ms/step - accuracy: 0.4196 - loss: 1.5163[32m [repeated 97x across cluster][0m
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m 55/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 31ms/step - accuracy: 0.5663 - loss: 1.0134
[1m 57/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 30ms/step - accuracy: 0.5664 - loss: 1.0127[32m [repeated 156x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 37ms/step - accuracy: 0.4935 - loss: 1.2646 - val_accuracy: 0.5565 - val_loss: 0.8684[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m Epoch 5/28[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 70ms/step - accuracy: 0.5625 - loss: 1.1752[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.5816 - loss: 0.9737 
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.5778 - loss: 1.0268[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m6s[0m 50ms/step - accuracy: 0.4838 - loss: 1.3203
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m6s[0m 50ms/step - accuracy: 0.4838 - loss: 1.3202
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m6s[0m 50ms/step - accuracy: 0.4839 - loss: 1.3201
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m184/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m3s[0m 30ms/step - accuracy: 0.5105 - loss: 1.2069
[1m186/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m3s[0m 30ms/step - accuracy: 0.5106 - loss: 1.2067
[1m188/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m3s[0m 30ms/step - accuracy: 0.5107 - loss: 1.2066
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 65ms/step - accuracy: 0.6875 - loss: 0.9825
[1m  3/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 30ms/step - accuracy: 0.6285 - loss: 0.9965[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m 32/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 24ms/step - accuracy: 0.5495 - loss: 1.0642
[1m 35/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 23ms/step - accuracy: 0.5483 - loss: 1.0626
[1m 38/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 23ms/step - accuracy: 0.5470 - loss: 1.0611
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m102/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.6230 - loss: 0.8622
[1m104/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.6233 - loss: 0.8618[32m [repeated 372x across cluster][0m
Trial status: 20 RUNNING
Current time: 2025-11-08 14:46:09. 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_2414b    RUNNING            2   adam            relu                                   32                 16                  5                 1          7.66658e-05         28 │
│ trial_2414b    RUNNING            2   adam            relu                                   16                 64                  3                 1          1.29147e-05         16 │
│ trial_2414b    RUNNING            3   rmsprop         relu                                   16                 16                  3                 0          1.74324e-05         22 │
│ trial_2414b    RUNNING            3   rmsprop         relu                                   32                 32                  5                 1          6.70381e-05         15 │
│ trial_2414b    RUNNING            2   rmsprop         tanh                                   32                 64                  3                 1          1.0258e-05          28 │
│ trial_2414b    RUNNING            2   rmsprop         relu                                   16                 32                  5                 0          1.48377e-05         29 │
│ trial_2414b    RUNNING            2   adam            tanh                                   32                 32                  3                 1          0.000126055         15 │
│ trial_2414b    RUNNING            3   adam            relu                                   16                 32                  3                 0          2.34799e-05         18 │
│ trial_2414b    RUNNING            2   rmsprop         tanh                                   32                 32                  5                 1          7.10308e-06         26 │
│ trial_2414b    RUNNING            2   adam            tanh                                   16                 64                  3                 0          9.84048e-05         22 │
│ trial_2414b    RUNNING            2   adam            relu                                   16                 32                  5                 0          8.43998e-05         27 │
│ trial_2414b    RUNNING            2   rmsprop         relu                                   32                 32                  3                 0          1.54606e-05         21 │
│ trial_2414b    RUNNING            3   adam            relu                                   32                 16                  3                 0          2.67621e-05         27 │
│ trial_2414b    RUNNING            3   adam            relu                                   32                 64                  5                 0          5.09414e-06         25 │
│ trial_2414b    RUNNING            2   adam            tanh                                   32                 32                  5                 0          2.32663e-05         22 │
│ trial_2414b    RUNNING            2   rmsprop         tanh                                   16                 32                  5                 1          5.1345e-06          28 │
│ trial_2414b    RUNNING            2   adam            relu                                   32                 64                  5                 1          7.77942e-05         27 │
│ trial_2414b    RUNNING            3   adam            relu                                   16                 32                  3                 1          8.65481e-05         26 │
│ trial_2414b    RUNNING            2   rmsprop         relu                                   32                 16                  3                 0          0.000111363         18 │
│ trial_2414b    RUNNING            2   adam            relu                                   16                 16                  3                 1          7.55321e-05         16 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m106/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m8s[0m 44ms/step - accuracy: 0.6237 - loss: 0.8616[32m [repeated 283x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m272/619[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m10s[0m 30ms/step - accuracy: 0.4322 - loss: 1.4539[32m [repeated 116x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m133/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 22ms/step - accuracy: 0.5457 - loss: 1.0419
[1m135/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 22ms/step - accuracy: 0.5457 - loss: 1.0418[32m [repeated 122x across cluster][0m
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 30ms/step - accuracy: 0.5963 - loss: 0.9223 - val_accuracy: 0.6650 - val_loss: 0.6809[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924593)[0m Epoch 6/28[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 80ms/step - accuracy: 0.7500 - loss: 0.7128[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m155/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.5456 - loss: 1.0409 
[1m159/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.5456 - loss: 1.0406[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m285/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 50ms/step - accuracy: 0.4898 - loss: 1.3077
[1m286/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 50ms/step - accuracy: 0.4899 - loss: 1.3076
[1m287/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 50ms/step - accuracy: 0.4899 - loss: 1.3075[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 83ms/step - accuracy: 0.4375 - loss: 1.3666
[1m  2/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 52ms/step - accuracy: 0.4062 - loss: 1.3749[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m373/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 20ms/step - accuracy: 0.5513 - loss: 1.0286
[1m377/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 20ms/step - accuracy: 0.5514 - loss: 1.0285[32m [repeated 424x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 46ms/step - accuracy: 0.5469 - loss: 1.3149 
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m230/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 42ms/step - accuracy: 0.6328 - loss: 0.8521[32m [repeated 325x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m  7/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 46ms/step - accuracy: 0.5255 - loss: 1.3404[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m 41/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 33ms/step - accuracy: 0.5875 - loss: 0.9625
[1m 43/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 33ms/step - accuracy: 0.5893 - loss: 0.9609[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=924617)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m11s[0m 34ms/step - accuracy: 0.5960 - loss: 0.9066 - val_accuracy: 0.6538 - val_loss: 0.7227[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924617)[0m Epoch 6/15[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 119ms/step - accuracy: 0.5000 - loss: 1.3379[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.4815 - loss: 1.2754 
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.4808 - loss: 1.2774
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m284/619[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5486 - loss: 1.0332
[1m288/619[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5488 - loss: 1.0329
[1m291/619[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5489 - loss: 1.0327
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 65ms/step - accuracy: 0.6250 - loss: 1.2349
[1m  3/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 26ms/step - accuracy: 0.6215 - loss: 1.1757[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 26ms/step - accuracy: 0.7604 - loss: 0.7211 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.7362 - loss: 0.7401
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m 97/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 23ms/step - accuracy: 0.4983 - loss: 1.3038
[1m 99/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 23ms/step - accuracy: 0.4976 - loss: 1.3052
[1m101/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 23ms/step - accuracy: 0.4969 - loss: 1.3065
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m111/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 45ms/step - accuracy: 0.5182 - loss: 1.2423
[1m112/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 46ms/step - accuracy: 0.5182 - loss: 1.2421[32m [repeated 335x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 35ms/step - accuracy: 0.5365 - loss: 1.1114 
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m116/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 46ms/step - accuracy: 0.5184 - loss: 1.2416[32m [repeated 257x across cluster][0m
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m 11/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 42ms/step - accuracy: 0.6391 - loss: 0.8335[32m [repeated 126x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m155/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m11s[0m 25ms/step - accuracy: 0.4866 - loss: 1.3279
[1m158/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m11s[0m 25ms/step - accuracy: 0.4862 - loss: 1.3289[32m [repeated 107x across cluster][0m
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m14s[0m 46ms/step - accuracy: 0.6343 - loss: 0.8494 - val_accuracy: 0.6770 - val_loss: 0.6657[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=924592)[0m Epoch 5/15[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 70ms/step - accuracy: 0.5625 - loss: 1.1128[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m219/619[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 25ms/step - accuracy: 0.4811 - loss: 1.3450 
[1m221/619[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 25ms/step - accuracy: 0.4809 - loss: 1.3455
[1m223/619[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 25ms/step - accuracy: 0.4808 - loss: 1.3461
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 89ms/step - accuracy: 0.5000 - loss: 1.2520
[1m  2/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 54ms/step - accuracy: 0.5000 - loss: 1.2100[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m315/619[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.4963 - loss: 1.2353 
[1m317/619[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.4964 - loss: 1.2352[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m 17/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 24ms/step - accuracy: 0.5715 - loss: 0.9855
[1m 20/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 23ms/step - accuracy: 0.5715 - loss: 0.9942
[1m 23/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 22ms/step - accuracy: 0.5701 - loss: 1.0032
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m156/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.5617 - loss: 1.0001
[1m159/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.5620 - loss: 0.9994[32m [repeated 287x across cluster][0m
[36m(train_cnn_ray_tune pid=924617)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 42ms/step - accuracy: 0.6927 - loss: 0.6830 
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m166/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.5625 - loss: 0.9978[32m [repeated 240x across cluster][0m
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m 44/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 32ms/step - accuracy: 0.5497 - loss: 1.0991[32m [repeated 130x across cluster][0m
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m221/619[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m10s[0m 25ms/step - accuracy: 0.6118 - loss: 0.9245
[1m224/619[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m10s[0m 25ms/step - accuracy: 0.6118 - loss: 0.9241[32m [repeated 140x across cluster][0m
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m21s[0m 34ms/step - accuracy: 0.5705 - loss: 0.9764 - val_accuracy: 0.6478 - val_loss: 0.7228[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924630)[0m Epoch 4/22[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924617)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51:41[0m 10s/step - accuracy: 0.7188 - loss: 0.6611[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 90ms/step - accuracy: 0.5000 - loss: 1.0865
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 26ms/step - accuracy: 0.5729 - loss: 0.9420 [32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 19ms/step - accuracy: 0.5098 - loss: 0.9843 
[1m  7/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 18ms/step - accuracy: 0.5377 - loss: 0.9540[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m397/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 21ms/step - accuracy: 0.5737 - loss: 0.9697
[1m399/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 21ms/step - accuracy: 0.5738 - loss: 0.9695[32m [repeated 383x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.5608 - loss: 1.0595  
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m243/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 43ms/step - accuracy: 0.6500 - loss: 0.8132[32m [repeated 392x across cluster][0m
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m204/619[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m12s[0m 31ms/step - accuracy: 0.5595 - loss: 1.0802[32m [repeated 78x across cluster][0m
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m209/619[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m11s[0m 29ms/step - accuracy: 0.5821 - loss: 0.9029
[1m211/619[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m11s[0m 29ms/step - accuracy: 0.5822 - loss: 0.9030[32m [repeated 78x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 38ms/step - accuracy: 0.5099 - loss: 1.1643 - val_accuracy: 0.5934 - val_loss: 0.8219[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m Epoch 7/28[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 101ms/step - accuracy: 0.5938 - loss: 0.9734[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.6701 - loss: 0.8259 
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.6778 - loss: 0.8054 
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m  2/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 68ms/step - accuracy: 0.6328 - loss: 0.8829 
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m590/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 26ms/step - accuracy: 0.4704 - loss: 1.3718
[1m591/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 26ms/step - accuracy: 0.4703 - loss: 1.3718
[1m593/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 26ms/step - accuracy: 0.4703 - loss: 1.3718
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m 21/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 57ms/step - accuracy: 0.5817 - loss: 1.0664
[1m 22/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 57ms/step - accuracy: 0.5809 - loss: 1.0689
[1m 23/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 56ms/step - accuracy: 0.5802 - loss: 1.0711
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6107 - loss: 0.9989 
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.6205 - loss: 0.9778
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m308/619[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.5595 - loss: 1.0840 
[1m310/619[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.5595 - loss: 1.0840
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 69ms/step - accuracy: 0.3750 - loss: 1.3258
[1m  3/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 25ms/step - accuracy: 0.3889 - loss: 1.4024
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m616/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 34ms/step - accuracy: 0.6094 - loss: 0.9235
[1m618/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 34ms/step - accuracy: 0.6094 - loss: 0.9234[32m [repeated 413x across cluster][0m
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m5s[0m 26ms/step - accuracy: 0.5850 - loss: 1.0231[32m [repeated 297x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 49ms/step - accuracy: 0.5667 - loss: 1.1197[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 49ms/step - accuracy: 0.5662 - loss: 1.1205
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 49ms/step - accuracy: 0.5659 - loss: 1.1212[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 38ms/step - accuracy: 0.4892 - loss: 1.1896 - val_accuracy: 0.5962 - val_loss: 0.9118[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m Epoch 7/27[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=924617)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 75ms/step - accuracy: 0.5000 - loss: 0.8944[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m403/619[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 29ms/step - accuracy: 0.5909 - loss: 0.8976
[1m405/619[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 29ms/step - accuracy: 0.5910 - loss: 0.8975
[1m407/619[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 29ms/step - accuracy: 0.5911 - loss: 0.8975[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m 17/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 29ms/step - accuracy: 0.6354 - loss: 0.8728
[1m 20/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 28ms/step - accuracy: 0.6330 - loss: 0.8759
[1m 22/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 28ms/step - accuracy: 0.6316 - loss: 0.8774
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.6719 - loss: 0.7448 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.6703 - loss: 0.7370[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.4757 - loss: 1.1251 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 41ms/step - accuracy: 0.4876 - loss: 1.1425
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 93ms/step - accuracy: 0.5000 - loss: 0.8226
[1m  3/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 34ms/step - accuracy: 0.5625 - loss: 0.8655[32m [repeated 5x across cluster][0m
Trial status: 20 RUNNING
Current time: 2025-11-08 14:46:39. 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_2414b    RUNNING            2   adam            relu                                   32                 16                  5                 1          7.66658e-05         28 │
│ trial_2414b    RUNNING            2   adam            relu                                   16                 64                  3                 1          1.29147e-05         16 │
│ trial_2414b    RUNNING            3   rmsprop         relu                                   16                 16                  3                 0          1.74324e-05         22 │
│ trial_2414b    RUNNING            3   rmsprop         relu                                   32                 32                  5                 1          6.70381e-05         15 │
│ trial_2414b    RUNNING            2   rmsprop         tanh                                   32                 64                  3                 1          1.0258e-05          28 │
│ trial_2414b    RUNNING            2   rmsprop         relu                                   16                 32                  5                 0          1.48377e-05         29 │
│ trial_2414b    RUNNING            2   adam            tanh                                   32                 32                  3                 1          0.000126055         15 │
│ trial_2414b    RUNNING            3   adam            relu                                   16                 32                  3                 0          2.34799e-05         18 │
│ trial_2414b    RUNNING            2   rmsprop         tanh                                   32                 32                  5                 1          7.10308e-06         26 │
│ trial_2414b    RUNNING            2   adam            tanh                                   16                 64                  3                 0          9.84048e-05         22 │
│ trial_2414b    RUNNING            2   adam            relu                                   16                 32                  5                 0          8.43998e-05         27 │
│ trial_2414b    RUNNING            2   rmsprop         relu                                   32                 32                  3                 0          1.54606e-05         21 │
│ trial_2414b    RUNNING            3   adam            relu                                   32                 16                  3                 0          2.67621e-05         27 │
│ trial_2414b    RUNNING            3   adam            relu                                   32                 64                  5                 0          5.09414e-06         25 │
│ trial_2414b    RUNNING            2   adam            tanh                                   32                 32                  5                 0          2.32663e-05         22 │
│ trial_2414b    RUNNING            2   rmsprop         tanh                                   16                 32                  5                 1          5.1345e-06          28 │
│ trial_2414b    RUNNING            2   adam            relu                                   32                 64                  5                 1          7.77942e-05         27 │
│ trial_2414b    RUNNING            3   adam            relu                                   16                 32                  3                 1          8.65481e-05         26 │
│ trial_2414b    RUNNING            2   rmsprop         relu                                   32                 16                  3                 0          0.000111363         18 │
│ trial_2414b    RUNNING            2   adam            relu                                   16                 16                  3                 1          7.55321e-05         16 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m133/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m6s[0m 37ms/step - accuracy: 0.4887 - loss: 1.1719
[1m135/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m6s[0m 37ms/step - accuracy: 0.4888 - loss: 1.1716[32m [repeated 322x across cluster][0m
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m130/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 44ms/step - accuracy: 0.6734 - loss: 0.7674[32m [repeated 274x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m 25/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 37ms/step - accuracy: 0.5115 - loss: 1.1326[32m [repeated 119x across cluster][0m
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m 96/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m13s[0m 27ms/step - accuracy: 0.6192 - loss: 0.8754
[1m 98/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m13s[0m 27ms/step - accuracy: 0.6191 - loss: 0.8754[32m [repeated 140x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 37ms/step - accuracy: 0.5295 - loss: 1.1294 - val_accuracy: 0.5994 - val_loss: 0.8065[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m Epoch 8/28[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 119ms/step - accuracy: 0.4375 - loss: 1.1221[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m 60/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 37ms/step - accuracy: 0.6262 - loss: 0.8727
[1m 61/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 37ms/step - accuracy: 0.6263 - loss: 0.8726
[1m 62/619[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 37ms/step - accuracy: 0.6265 - loss: 0.8725
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m198/619[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.5710 - loss: 0.9717 
[1m201/619[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.5712 - loss: 0.9711[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 89ms/step - accuracy: 0.6875 - loss: 0.6521
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6934 - loss: 0.6839 [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m370/619[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 23ms/step - accuracy: 0.5794 - loss: 0.9522
[1m372/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 23ms/step - accuracy: 0.5795 - loss: 0.9521[32m [repeated 317x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m394/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 27ms/step - accuracy: 0.4636 - loss: 1.3851[32m [repeated 326x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m261/619[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m12s[0m 36ms/step - accuracy: 0.5407 - loss: 1.1382[32m [repeated 124x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m191/619[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m16s[0m 38ms/step - accuracy: 0.6237 - loss: 0.8701
[1m193/619[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m16s[0m 38ms/step - accuracy: 0.6236 - loss: 0.8701[32m [repeated 116x across cluster][0m
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m11s[0m 34ms/step - accuracy: 0.5059 - loss: 1.2332 - val_accuracy: 0.5643 - val_loss: 0.8916[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924629)[0m Epoch 9/26[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 81ms/step - accuracy: 0.5625 - loss: 0.9645[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m 41/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.6853 - loss: 0.6954 
[1m 44/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.6854 - loss: 0.6955[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m 33/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 41ms/step - accuracy: 0.5377 - loss: 1.1646
[1m 34/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 41ms/step - accuracy: 0.5383 - loss: 1.1639
[1m 35/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 42ms/step - accuracy: 0.5390 - loss: 1.1631
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:24[0m 137ms/step - accuracy: 0.6250 - loss: 0.7816
[1m  3/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 39ms/step - accuracy: 0.6181 - loss: 0.8357  [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m302/619[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m8s[0m 28ms/step - accuracy: 0.4742 - loss: 1.2594
[1m304/619[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m8s[0m 28ms/step - accuracy: 0.4742 - loss: 1.2596[32m [repeated 376x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m 50/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 42ms/step - accuracy: 0.5435 - loss: 1.1581
[1m 51/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 42ms/step - accuracy: 0.5435 - loss: 1.1582
[1m 52/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 42ms/step - accuracy: 0.5435 - loss: 1.1584
[36m(train_cnn_ray_tune pid=924617)[0m 
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m3s[0m 27ms/step - accuracy: 0.6478 - loss: 0.7967[32m [repeated 191x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 43ms/step - accuracy: 0.5436 - loss: 1.1590[32m [repeated 109x across cluster][0m
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m200/619[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m11s[0m 28ms/step - accuracy: 0.6174 - loss: 0.8526
[1m202/619[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m11s[0m 28ms/step - accuracy: 0.6174 - loss: 0.8526[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m11s[0m 35ms/step - accuracy: 0.5305 - loss: 1.1087 - val_accuracy: 0.6131 - val_loss: 0.7931[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m Epoch 9/28[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 75ms/step - accuracy: 0.4062 - loss: 1.2717[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m555/619[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 26ms/step - accuracy: 0.6300 - loss: 0.8509
[1m557/619[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 26ms/step - accuracy: 0.6300 - loss: 0.8508
[1m559/619[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 26ms/step - accuracy: 0.6301 - loss: 0.8508
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m257/619[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.5795 - loss: 1.0462 
[1m259/619[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.5795 - loss: 1.0460[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 72ms/step - accuracy: 0.4688 - loss: 0.9831
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 29ms/step - accuracy: 0.5104 - loss: 1.0438 
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 39ms/step - accuracy: 0.6627 - loss: 0.7585
[1m154/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 39ms/step - accuracy: 0.6628 - loss: 0.7584[32m [repeated 355x across cluster][0m
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m156/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m5s[0m 39ms/step - accuracy: 0.6629 - loss: 0.7582[32m [repeated 268x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m 92/619[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 24ms/step - accuracy: 0.4805 - loss: 1.3620[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m 47/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.5672 - loss: 1.0491
[1m 50/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 25ms/step - accuracy: 0.5675 - loss: 1.0491[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=924617)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m10s[0m 31ms/step - accuracy: 0.6465 - loss: 0.8013 - val_accuracy: 0.6566 - val_loss: 0.7105[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=924617)[0m Epoch 9/15[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=924617)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 76ms/step - accuracy: 0.6250 - loss: 0.9029[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m151/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 25ms/step - accuracy: 0.4819 - loss: 1.3506
[1m153/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 25ms/step - accuracy: 0.4819 - loss: 1.3503
[1m155/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m11s[0m 25ms/step - accuracy: 0.4819 - loss: 1.3499
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 37ms/step - accuracy: 0.5295 - loss: 1.1560 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 40ms/step - accuracy: 0.5202 - loss: 1.1445
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m154/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m4s[0m 27ms/step - accuracy: 0.6040 - loss: 0.9731
[1m156/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m4s[0m 27ms/step - accuracy: 0.6039 - loss: 0.9734
[1m158/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m4s[0m 27ms/step - accuracy: 0.6038 - loss: 0.9738[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924617)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 26ms/step - accuracy: 0.6341 - loss: 0.9017 
[1m  7/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 23ms/step - accuracy: 0.6457 - loss: 0.8925[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m381/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 21ms/step - accuracy: 0.6091 - loss: 0.8687
[1m384/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 21ms/step - accuracy: 0.6092 - loss: 0.8687[32m [repeated 379x across cluster][0m
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m276/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 40ms/step - accuracy: 0.6660 - loss: 0.7542[32m [repeated 357x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m 14/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 37ms/step - accuracy: 0.6014 - loss: 0.9673[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m165/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 27ms/step - accuracy: 0.6556 - loss: 0.7573
[1m167/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 27ms/step - accuracy: 0.6555 - loss: 0.7578[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 38ms/step - accuracy: 0.5407 - loss: 1.1394 - val_accuracy: 0.6310 - val_loss: 0.8433[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m Epoch 5/18[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 93ms/step - accuracy: 0.6250 - loss: 1.0666[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 96ms/step - accuracy: 0.5938 - loss: 1.1692
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 33ms/step - accuracy: 0.5642 - loss: 1.1626
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m  2/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 56ms/step - accuracy: 0.5391 - loss: 1.2077 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 57ms/step - accuracy: 0.5573 - loss: 1.1598
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m252/619[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 27ms/step - accuracy: 0.6538 - loss: 0.7701 
[1m255/619[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 27ms/step - accuracy: 0.6539 - loss: 0.7703[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m105/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m6s[0m 30ms/step - accuracy: 0.6146 - loss: 0.9819
[1m107/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m6s[0m 30ms/step - accuracy: 0.6146 - loss: 0.9819[32m [repeated 352x across cluster][0m
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m276/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 30ms/step - accuracy: 0.5761 - loss: 1.0192
[1m278/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 30ms/step - accuracy: 0.5762 - loss: 1.0190
[1m280/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 30ms/step - accuracy: 0.5763 - loss: 1.0188
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m163/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m3s[0m 24ms/step - accuracy: 0.6620 - loss: 0.7216[32m [repeated 264x across cluster][0m
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m 51/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 41ms/step - accuracy: 0.6545 - loss: 0.7987[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m100/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 35ms/step - accuracy: 0.6299 - loss: 0.8230
[1m102/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 35ms/step - accuracy: 0.6300 - loss: 0.8230[32m [repeated 100x across cluster][0m
[36m(train_cnn_ray_tune pid=924617)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m10s[0m 33ms/step - accuracy: 0.6421 - loss: 0.7972 - val_accuracy: 0.6545 - val_loss: 0.7235[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=924617)[0m Epoch 10/15[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 67ms/step - accuracy: 0.5938 - loss: 1.3465[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924617)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 80ms/step - accuracy: 0.7500 - loss: 0.5494
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 28ms/step - accuracy: 0.7413 - loss: 0.5574 [32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m141/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 34ms/step - accuracy: 0.6308 - loss: 0.8248
[1m142/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 34ms/step - accuracy: 0.6308 - loss: 0.8249
[1m144/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 34ms/step - accuracy: 0.6308 - loss: 0.8251
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m101/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.5724 - loss: 1.0838 
[1m102/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.5723 - loss: 1.0839[32m [repeated 7x across cluster][0m
Trial status: 20 RUNNING
Current time: 2025-11-08 14:47:09. 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_2414b    RUNNING            2   adam            relu                                   32                 16                  5                 1          7.66658e-05         28 │
│ trial_2414b    RUNNING            2   adam            relu                                   16                 64                  3                 1          1.29147e-05         16 │
│ trial_2414b    RUNNING            3   rmsprop         relu                                   16                 16                  3                 0          1.74324e-05         22 │
│ trial_2414b    RUNNING            3   rmsprop         relu                                   32                 32                  5                 1          6.70381e-05         15 │
│ trial_2414b    RUNNING            2   rmsprop         tanh                                   32                 64                  3                 1          1.0258e-05          28 │
│ trial_2414b    RUNNING            2   rmsprop         relu                                   16                 32                  5                 0          1.48377e-05         29 │
│ trial_2414b    RUNNING            2   adam            tanh                                   32                 32                  3                 1          0.000126055         15 │
│ trial_2414b    RUNNING            3   adam            relu                                   16                 32                  3                 0          2.34799e-05         18 │
│ trial_2414b    RUNNING            2   rmsprop         tanh                                   32                 32                  5                 1          7.10308e-06         26 │
│ trial_2414b    RUNNING            2   adam            tanh                                   16                 64                  3                 0          9.84048e-05         22 │
│ trial_2414b    RUNNING            2   adam            relu                                   16                 32                  5                 0          8.43998e-05         27 │
│ trial_2414b    RUNNING            2   rmsprop         relu                                   32                 32                  3                 0          1.54606e-05         21 │
│ trial_2414b    RUNNING            3   adam            relu                                   32                 16                  3                 0          2.67621e-05         27 │
│ trial_2414b    RUNNING            3   adam            relu                                   32                 64                  5                 0          5.09414e-06         25 │
│ trial_2414b    RUNNING            2   adam            tanh                                   32                 32                  5                 0          2.32663e-05         22 │
│ trial_2414b    RUNNING            2   rmsprop         tanh                                   16                 32                  5                 1          5.1345e-06          28 │
│ trial_2414b    RUNNING            2   adam            relu                                   32                 64                  5                 1          7.77942e-05         27 │
│ trial_2414b    RUNNING            3   adam            relu                                   16                 32                  3                 1          8.65481e-05         26 │
│ trial_2414b    RUNNING            2   rmsprop         relu                                   32                 16                  3                 0          0.000111363         18 │
│ trial_2414b    RUNNING            2   adam            relu                                   16                 16                  3                 1          7.55321e-05         16 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m136/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m8s[0m 49ms/step - accuracy: 0.5716 - loss: 1.0856
[1m138/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m8s[0m 49ms/step - accuracy: 0.5716 - loss: 1.0856[32m [repeated 290x across cluster][0m
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m5s[0m 30ms/step - accuracy: 0.6146 - loss: 0.9812
[1m123/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m5s[0m 30ms/step - accuracy: 0.6146 - loss: 0.9812
[1m125/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m5s[0m 29ms/step - accuracy: 0.6146 - loss: 0.9811
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m611/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 27ms/step - accuracy: 0.5684 - loss: 1.0509[32m [repeated 248x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m309/619[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 35ms/step - accuracy: 0.5597 - loss: 1.0583[32m [repeated 153x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m168/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 23ms/step - accuracy: 0.6413 - loss: 0.8430
[1m171/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 23ms/step - accuracy: 0.6409 - loss: 0.8433[32m [repeated 173x across cluster][0m
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 30ms/step - accuracy: 0.6630 - loss: 0.7276 - val_accuracy: 0.6664 - val_loss: 0.6564[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924595)[0m Epoch 13/18[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 86ms/step - accuracy: 0.5938 - loss: 0.9099[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 91ms/step - accuracy: 0.6250 - loss: 0.6675
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 28ms/step - accuracy: 0.6632 - loss: 0.6239 [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m161/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m5s[0m 35ms/step - accuracy: 0.6849 - loss: 0.7131
[1m162/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m5s[0m 35ms/step - accuracy: 0.6850 - loss: 0.7130
[1m164/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m5s[0m 35ms/step - accuracy: 0.6851 - loss: 0.7126
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m  3/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 34ms/step - accuracy: 0.3472 - loss: 1.4620 
[1m  5/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 33ms/step - accuracy: 0.3758 - loss: 1.4345
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m141/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 24ms/step - accuracy: 0.6459 - loss: 0.8407
[1m144/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 24ms/step - accuracy: 0.6453 - loss: 0.8410
[1m147/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 24ms/step - accuracy: 0.6447 - loss: 0.8413[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m281/619[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.6528 - loss: 0.7972 
[1m283/619[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.6528 - loss: 0.7972[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m220/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 36ms/step - accuracy: 0.5283 - loss: 1.0763
[1m222/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 36ms/step - accuracy: 0.5283 - loss: 1.0763[32m [repeated 360x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m249/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 48ms/step - accuracy: 0.5727 - loss: 1.0848[32m [repeated 333x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m 85/619[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 27ms/step - accuracy: 0.5658 - loss: 1.0737[32m [repeated 80x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m148/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m12s[0m 27ms/step - accuracy: 0.4926 - loss: 1.2828
[1m151/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m12s[0m 27ms/step - accuracy: 0.4929 - loss: 1.2825[32m [repeated 104x across cluster][0m
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m19s[0m 31ms/step - accuracy: 0.6527 - loss: 0.7863 - val_accuracy: 0.6534 - val_loss: 0.6781[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924618)[0m Epoch 7/27[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 75ms/step - accuracy: 0.5625 - loss: 0.5914[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 67ms/step - accuracy: 0.6250 - loss: 0.9681
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 26ms/step - accuracy: 0.5747 - loss: 1.0134 
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m397/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 22ms/step - accuracy: 0.6296 - loss: 0.8505
[1m399/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 22ms/step - accuracy: 0.6295 - loss: 0.8505
[1m400/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 22ms/step - accuracy: 0.6295 - loss: 0.8505
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 17ms/step - accuracy: 0.6165 - loss: 0.7723  
[36m(train_cnn_ray_tune pid=924617)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 39ms/step - accuracy: 0.6771 - loss: 0.7079 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 35ms/step - accuracy: 0.6631 - loss: 0.7359
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m140/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m13s[0m 28ms/step - accuracy: 0.5769 - loss: 1.0495
[1m142/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m13s[0m 28ms/step - accuracy: 0.5772 - loss: 1.0491
[1m144/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m13s[0m 28ms/step - accuracy: 0.5774 - loss: 1.0488
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m245/619[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 27ms/step - accuracy: 0.4945 - loss: 1.2799 
[1m248/619[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 27ms/step - accuracy: 0.4945 - loss: 1.2799[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 70ms/step - accuracy: 0.5938 - loss: 1.0106
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.5951 - loss: 1.0076 
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 240ms/step
[1m 8/43[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step   
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m12/43[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m18/43[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 9ms/step 
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m25/43[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m32/43[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m39/43[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m610/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 23ms/step - accuracy: 0.6272 - loss: 0.8530
[1m613/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 23ms/step - accuracy: 0.6272 - loss: 0.8530[32m [repeated 376x across cluster][0m
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m 64/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m6s[0m 28ms/step - accuracy: 0.5887 - loss: 0.9487[32m [repeated 317x across cluster][0m
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m 54/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 41ms/step - accuracy: 0.6997 - loss: 0.6730[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m178/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m13s[0m 30ms/step - accuracy: 0.6608 - loss: 0.7539
[1m180/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m13s[0m 30ms/step - accuracy: 0.6608 - loss: 0.7540[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m17s[0m 54ms/step - accuracy: 0.5737 - loss: 1.0825 - val_accuracy: 0.6352 - val_loss: 0.8047[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m Epoch 8/25[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 109ms/step - accuracy: 0.6250 - loss: 1.0329[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 57ms/step
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m498/619[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 30ms/step - accuracy: 0.5804 - loss: 1.0371
[1m499/619[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 30ms/step - accuracy: 0.5804 - loss: 1.0371
[1m501/619[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 30ms/step - accuracy: 0.5805 - loss: 1.0370
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m 5/89[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 13ms/step
[1m 9/89[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m14/89[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m21/89[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m24/89[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m28/89[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[1m33/89[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m36/89[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m40/89[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=924595)[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=924595)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=924595)[0m 2025-11-08 14:45:12.868628: 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=924595)[0m 2025-11-08 14:45:12.890397: 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=924602)[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=924602)[0m E0000 00:00:1762609512.830746  925885 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=924595)[0m E0000 00:00:1762609512.927576  925892 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=924595)[0m W0000 00:00:1762609512.945695  925892 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=924595)[0m 2025-11-08 14:45:12.951278: 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=924595)[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=924595)[0m 2025-11-08 14:45:16.222170: 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=924595)[0m 2025-11-08 14:45:16.222230: 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=924595)[0m 2025-11-08 14:45:16.222239: 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=924595)[0m 2025-11-08 14:45:16.222244: 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=924595)[0m 2025-11-08 14:45:16.222250: 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=924595)[0m 2025-11-08 14:45:16.222254: 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=924595)[0m 2025-11-08 14:45:16.222539: 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=924595)[0m 2025-11-08 14:45:16.222583: 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=924595)[0m 2025-11-08 14:45:16.222589: 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=924595)[0m 
[1m45/89[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 14ms/step
[1m51/89[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m57/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m61/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m64/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 13ms/step
[1m69/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 55ms/step - accuracy: 0.6111 - loss: 1.0054 
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m73/89[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 13ms/step
[1m77/89[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m81/89[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 13ms/step
[1m86/89[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 13ms/step

Trial trial_2414b finished iteration 1 at 2025-11-08 14:47:21. Total running time: 2min 12s
╭──────────────────────────────────────╮
│ Trial trial_2414b result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             129.288 │
│ time_total_s                 129.288 │
│ training_iteration                 1 │
│ val_accuracy                 0.66749 │
╰──────────────────────────────────────╯

Trial trial_2414b completed after 1 iterations at 2025-11-08 14:47:21. Total running time: 2min 12s
[36m(train_cnn_ray_tune pid=924595)[0m 
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m282/619[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.6612 - loss: 0.7604 
[1m284/619[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.6612 - loss: 0.7605[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 83ms/step - accuracy: 0.6875 - loss: 1.0226
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 26ms/step - accuracy: 0.6927 - loss: 0.9042 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m  3/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 35ms/step - accuracy: 0.6597 - loss: 0.8690  
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m153/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.6432 - loss: 0.8057
[1m156/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.6431 - loss: 0.8060[32m [repeated 337x across cluster][0m
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 40ms/step - accuracy: 0.6911 - loss: 0.6997[32m [repeated 315x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m148/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m13s[0m 28ms/step - accuracy: 0.5154 - loss: 1.1633[32m [repeated 87x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m141/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m13s[0m 28ms/step - accuracy: 0.5154 - loss: 1.1626
[1m143/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m13s[0m 28ms/step - accuracy: 0.5154 - loss: 1.1629[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m21s[0m 34ms/step - accuracy: 0.6526 - loss: 0.7983 - val_accuracy: 0.6587 - val_loss: 0.7121[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924630)[0m Epoch 7/22[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 117ms/step - accuracy: 0.6250 - loss: 0.7498[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m396/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 26ms/step - accuracy: 0.4953 - loss: 1.2794
[1m398/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 26ms/step - accuracy: 0.4953 - loss: 1.2794
[1m400/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 26ms/step - accuracy: 0.4953 - loss: 1.2794
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m128/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m4s[0m 27ms/step - accuracy: 0.6295 - loss: 0.9148
[1m130/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m4s[0m 27ms/step - accuracy: 0.6294 - loss: 0.9150
[1m132/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m4s[0m 27ms/step - accuracy: 0.6293 - loss: 0.9153
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m 33/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 28ms/step - accuracy: 0.5734 - loss: 1.0459
[1m 35/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 28ms/step - accuracy: 0.5743 - loss: 1.0438
[1m 37/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 28ms/step - accuracy: 0.5753 - loss: 1.0417
[36m(train_cnn_ray_tune pid=924617)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.6562 - loss: 0.6417 
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.6627 - loss: 0.6590[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m  3/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 47ms/step - accuracy: 0.7257 - loss: 0.7789 
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 60ms/step - accuracy: 0.7812 - loss: 0.5759
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 20ms/step - accuracy: 0.7214 - loss: 0.6962 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m303/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 40ms/step - accuracy: 0.6883 - loss: 0.7055
[1m305/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 40ms/step - accuracy: 0.6883 - loss: 0.7055[32m [repeated 309x across cluster][0m
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m307/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 40ms/step - accuracy: 0.6883 - loss: 0.7055[32m [repeated 300x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m 42/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 33ms/step - accuracy: 0.6339 - loss: 0.8351[32m [repeated 124x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m  8/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 25ms/step - accuracy: 0.4684 - loss: 1.4847
[1m 11/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 24ms/step - accuracy: 0.4634 - loss: 1.4813[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m19s[0m 31ms/step - accuracy: 0.4957 - loss: 1.2782 - val_accuracy: 0.5948 - val_loss: 0.8919[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m Epoch 8/28[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 87ms/step - accuracy: 0.5000 - loss: 1.4029[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m329/619[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6354 - loss: 0.8231
[1m333/619[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m5s[0m 21ms/step - accuracy: 0.6352 - loss: 0.8235
[1m335/619[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m5s[0m 21ms/step - accuracy: 0.6351 - loss: 0.8236[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 26ms/step - accuracy: 0.5052 - loss: 1.0038 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 27ms/step - accuracy: 0.5291 - loss: 1.0035[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 60ms/step - accuracy: 0.6250 - loss: 1.3365
[1m  4/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 22ms/step - accuracy: 0.5547 - loss: 1.3313[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m 81/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.7026 - loss: 0.7051
[1m 83/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m8s[0m 38ms/step - accuracy: 0.7024 - loss: 0.7051[32m [repeated 320x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m141/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.5434 - loss: 1.0512[32m [repeated 229x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m209/619[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 26ms/step - accuracy: 0.5048 - loss: 1.2727[32m [repeated 106x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m193/619[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m14s[0m 33ms/step - accuracy: 0.6293 - loss: 0.8378
[1m196/619[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m14s[0m 33ms/step - accuracy: 0.6294 - loss: 0.8375[32m [repeated 156x across cluster][0m
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 29ms/step - accuracy: 0.6565 - loss: 0.7562 - val_accuracy: 0.6850 - val_loss: 0.6378[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924593)[0m Epoch 15/28[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 84ms/step - accuracy: 0.6562 - loss: 0.6909[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m 41/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 33ms/step - accuracy: 0.5180 - loss: 1.1105
[1m 43/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.5190 - loss: 1.1091
[1m 45/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.5199 - loss: 1.1076
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m6s[0m 27ms/step - accuracy: 0.5522 - loss: 1.1131
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m6s[0m 27ms/step - accuracy: 0.5520 - loss: 1.1130
[1m 64/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m6s[0m 27ms/step - accuracy: 0.5518 - loss: 1.1130
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m226/619[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 25ms/step - accuracy: 0.5760 - loss: 1.0093 
[1m228/619[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 25ms/step - accuracy: 0.5761 - loss: 1.0091[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 63ms/step - accuracy: 0.5000 - loss: 1.2455
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 19ms/step - accuracy: 0.5358 - loss: 1.2061 

Trial status: 19 RUNNING | 1 TERMINATED
Current time: 2025-11-08 14:47:39. Total running time: 2min 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_2414b    RUNNING              2   adam            relu                                   32                 16                  5                 1          7.66658e-05         28                                              │
│ trial_2414b    RUNNING              2   adam            relu                                   16                 64                  3                 1          1.29147e-05         16                                              │
│ trial_2414b    RUNNING              3   rmsprop         relu                                   16                 16                  3                 0          1.74324e-05         22                                              │
│ trial_2414b    RUNNING              3   rmsprop         relu                                   32                 32                  5                 1          6.70381e-05         15                                              │
│ trial_2414b    RUNNING              2   rmsprop         tanh                                   32                 64                  3                 1          1.0258e-05          28                                              │
│ trial_2414b    RUNNING              2   rmsprop         relu                                   16                 32                  5                 0          1.48377e-05         29                                              │
│ trial_2414b    RUNNING              2   adam            tanh                                   32                 32                  3                 1          0.000126055         15                                              │
│ trial_2414b    RUNNING              3   adam            relu                                   16                 32                  3                 0          2.34799e-05         18                                              │
│ trial_2414b    RUNNING              2   rmsprop         tanh                                   32                 32                  5                 1          7.10308e-06         26                                              │
│ trial_2414b    RUNNING              2   adam            tanh                                   16                 64                  3                 0          9.84048e-05         22                                              │
│ trial_2414b    RUNNING              2   adam            relu                                   16                 32                  5                 0          8.43998e-05         27                                              │
│ trial_2414b    RUNNING              2   rmsprop         relu                                   32                 32                  3                 0          1.54606e-05         21                                              │
│ trial_2414b    RUNNING              3   adam            relu                                   32                 16                  3                 0          2.67621e-05         27                                              │
│ trial_2414b    RUNNING              3   adam            relu                                   32                 64                  5                 0          5.09414e-06         25                                              │
│ trial_2414b    RUNNING              2   adam            tanh                                   32                 32                  5                 0          2.32663e-05         22                                              │
│ trial_2414b    RUNNING              2   rmsprop         tanh                                   16                 32                  5                 1          5.1345e-06          28                                              │
│ trial_2414b    RUNNING              2   adam            relu                                   32                 64                  5                 1          7.77942e-05         27                                              │
│ trial_2414b    RUNNING              3   adam            relu                                   16                 32                  3                 1          8.65481e-05         26                                              │
│ trial_2414b    RUNNING              2   adam            relu                                   16                 16                  3                 1          7.55321e-05         16                                              │
│ trial_2414b    TERMINATED           2   rmsprop         relu                                   32                 16                  3                 0          0.000111363         18        1            129.288         0.667486 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m166/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.6470 - loss: 0.8103
[1m169/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.6469 - loss: 0.8101[32m [repeated 367x across cluster][0m
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m498/619[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 28ms/step - accuracy: 0.6011 - loss: 0.9833[32m [repeated 263x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m157/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 22ms/step - accuracy: 0.6472 - loss: 0.8111 [32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m149/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 22ms/step - accuracy: 0.6473 - loss: 0.8120
[1m154/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 22ms/step - accuracy: 0.6472 - loss: 0.8114[32m [repeated 102x across cluster][0m
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m10s[0m 31ms/step - accuracy: 0.6063 - loss: 0.9155 - val_accuracy: 0.6492 - val_loss: 0.7288[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924628)[0m Epoch 13/22[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 76ms/step - accuracy: 0.6562 - loss: 0.9109[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 78ms/step - accuracy: 0.5625 - loss: 0.9853
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.5456 - loss: 1.0343 
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 303ms/step
[1m 6/43[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step  
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m10/43[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[1m15/43[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m20/43[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[1m25/43[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m30/43[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 12ms/step
[1m35/43[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m39/43[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m589/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 27ms/step - accuracy: 0.6512 - loss: 0.7802
[1m591/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 27ms/step - accuracy: 0.6512 - loss: 0.7802
[1m593/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 27ms/step - accuracy: 0.6512 - loss: 0.7802[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 19ms/step
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 20ms/step
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 62ms/step
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m 6/89[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m11/89[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m15/89[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[1m19/89[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m24/89[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[1m29/89[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m33/89[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[1m37/89[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m40/89[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[1m44/89[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m48/89[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 13ms/step
[1m52/89[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m57/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 13ms/step
[1m61/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m65/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 13ms/step
[1m69/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m74/89[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 13ms/step
[1m79/89[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=924631)[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=924631)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=924592)[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=924592)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=924631)[0m 
[1m85/89[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 13ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 13ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 13ms/step

Trial trial_2414b finished iteration 1 at 2025-11-08 14:47:44. Total running time: 2min 35s
╭──────────────────────────────────────╮
│ Trial trial_2414b result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s              152.58 │
│ time_total_s                  152.58 │
│ training_iteration                 1 │
│ val_accuracy                 0.70119 │
╰──────────────────────────────────────╯

Trial trial_2414b completed after 1 iterations at 2025-11-08 14:47:44. Total running time: 2min 35s
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m 80/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m5s[0m 22ms/step - accuracy: 0.6815 - loss: 0.6870
[1m 83/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m5s[0m 23ms/step - accuracy: 0.6818 - loss: 0.6874[32m [repeated 382x across cluster][0m
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m5s[0m 23ms/step - accuracy: 0.6820 - loss: 0.6880[32m [repeated 297x across cluster][0m
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m 30/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 27ms/step - accuracy: 0.6199 - loss: 0.7915[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m 32/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 27ms/step - accuracy: 0.6201 - loss: 0.7942
[1m 34/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 27ms/step - accuracy: 0.6202 - loss: 0.7963[32m [repeated 31x across cluster][0m
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 43ms/step - accuracy: 0.6980 - loss: 0.6959 - val_accuracy: 0.6805 - val_loss: 0.6696[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924630)[0m Epoch 8/22[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 87ms/step - accuracy: 0.6875 - loss: 0.6596[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 356ms/step
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m 4/43[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 23ms/step  
[1m10/43[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.4948 - loss: 1.0738 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 29ms/step - accuracy: 0.5050 - loss: 1.0907
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 78ms/step - accuracy: 0.5000 - loss: 1.0318
[1m  3/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 27ms/step - accuracy: 0.4653 - loss: 1.1929[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924617)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 301ms/step
[1m 5/43[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step  
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 50ms/step
[1m 5/89[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=924592)[0m 
[1m17/89[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m20/89[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=924617)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 48ms/step
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m195/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m3s[0m 29ms/step - accuracy: 0.5729 - loss: 1.0007
[1m197/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m3s[0m 29ms/step - accuracy: 0.5729 - loss: 1.0007
[1m199/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m3s[0m 29ms/step - accuracy: 0.5729 - loss: 1.0007[32m [repeated 3x across cluster][0m

Trial trial_2414b finished iteration 1 at 2025-11-08 14:47:48. Total running time: 2min 39s
╭──────────────────────────────────────╮
│ Trial trial_2414b result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             156.622 │
│ time_total_s                 156.622 │
│ training_iteration                 1 │
│ val_accuracy                 0.68048 │
╰──────────────────────────────────────╯

Trial trial_2414b completed after 1 iterations at 2025-11-08 14:47:48. Total running time: 2min 39s

Trial trial_2414b finished iteration 1 at 2025-11-08 14:47:48. Total running time: 2min 39s
╭──────────────────────────────────────╮
│ Trial trial_2414b result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             156.701 │
│ time_total_s                 156.701 │
│ training_iteration                 1 │
│ val_accuracy                 0.66292 │
╰──────────────────────────────────────╯

Trial trial_2414b completed after 1 iterations at 2025-11-08 14:47:48. Total running time: 2min 39s
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m109/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 20ms/step - accuracy: 0.5012 - loss: 1.2765
[1m112/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 20ms/step - accuracy: 0.5013 - loss: 1.2761
[1m115/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 20ms/step - accuracy: 0.5014 - loss: 1.2757
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m105/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m4s[0m 21ms/step - accuracy: 0.6086 - loss: 0.8976
[1m108/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m4s[0m 21ms/step - accuracy: 0.6085 - loss: 0.8976[32m [repeated 295x across cluster][0m
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m192/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m2s[0m 24ms/step - accuracy: 0.5510 - loss: 1.0780[32m [repeated 170x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m159/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 28ms/step - accuracy: 0.5834 - loss: 1.0030[32m [repeated 82x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m154/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m13s[0m 28ms/step - accuracy: 0.5835 - loss: 1.0030
[1m157/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 28ms/step - accuracy: 0.5834 - loss: 1.0031[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m14s[0m 22ms/step - accuracy: 0.6386 - loss: 0.8107 - val_accuracy: 0.6657 - val_loss: 0.6752[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m Epoch 11/16[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 56ms/step - accuracy: 0.7500 - loss: 0.5785[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m 87/619[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 19ms/step - accuracy: 0.5755 - loss: 1.0042 
[1m 90/619[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 19ms/step - accuracy: 0.5760 - loss: 1.0036
[1m 92/619[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 19ms/step - accuracy: 0.5763 - loss: 1.0033
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m 25/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 17ms/step - accuracy: 0.6335 - loss: 0.7795 
[1m 29/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 16ms/step - accuracy: 0.6322 - loss: 0.7843[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 67ms/step - accuracy: 0.6562 - loss: 0.7231
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.6536 - loss: 0.6958 [32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924617)[0m 
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step[32m [repeated 23x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m172/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m8s[0m 20ms/step - accuracy: 0.5026 - loss: 1.2685
[1m175/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m8s[0m 20ms/step - accuracy: 0.5026 - loss: 1.2683
[1m178/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m8s[0m 20ms/step - accuracy: 0.5027 - loss: 1.2681[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m2s[0m 22ms/step - accuracy: 0.6734 - loss: 0.7047
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m2s[0m 22ms/step - accuracy: 0.6733 - loss: 0.7049[32m [repeated 367x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m384/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 21ms/step - accuracy: 0.5060 - loss: 1.2504[32m [repeated 231x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m165/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 28ms/step - accuracy: 0.6612 - loss: 0.8331[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m159/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 28ms/step - accuracy: 0.6616 - loss: 0.8339
[1m162/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 28ms/step - accuracy: 0.6614 - loss: 0.8335[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m19s[0m 29ms/step - accuracy: 0.5709 - loss: 0.9794 - val_accuracy: 0.6366 - val_loss: 0.7480[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m Epoch 14/28[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 81ms/step - accuracy: 0.5938 - loss: 1.0059[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 27ms/step - accuracy: 0.6476 - loss: 0.8323 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 26ms/step - accuracy: 0.6335 - loss: 0.8466
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 82ms/step - accuracy: 0.5000 - loss: 1.2868
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.5247 - loss: 1.1332 
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m397/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m3s[0m 18ms/step - accuracy: 0.6396 - loss: 0.8003
[1m401/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m3s[0m 18ms/step - accuracy: 0.6397 - loss: 0.8003
[1m405/619[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m3s[0m 18ms/step - accuracy: 0.6397 - loss: 0.8003[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m270/619[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.6557 - loss: 0.8241 
[1m273/619[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.6556 - loss: 0.8239
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m220/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m2s[0m 26ms/step - accuracy: 0.5787 - loss: 0.9640
[1m223/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m2s[0m 26ms/step - accuracy: 0.5787 - loss: 0.9640[32m [repeated 408x across cluster][0m
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m 52/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m5s[0m 21ms/step - accuracy: 0.6752 - loss: 0.7351[32m [repeated 226x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 80ms/step - accuracy: 0.4062 - loss: 1.2068
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.4271 - loss: 1.1247 
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m168/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 23ms/step - accuracy: 0.5243 - loss: 1.1446[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m162/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 23ms/step - accuracy: 0.5238 - loss: 1.1457
[1m164/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 23ms/step - accuracy: 0.5240 - loss: 1.1454[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 30ms/step - accuracy: 0.5700 - loss: 0.9766 - val_accuracy: 0.6489 - val_loss: 0.7589[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m Epoch 14/27[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 70ms/step - accuracy: 0.5625 - loss: 1.0379[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m275/619[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.6555 - loss: 0.8238
[1m277/619[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.6555 - loss: 0.8237
[1m279/619[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.6554 - loss: 0.8236
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m 23/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 13ms/step - accuracy: 0.6615 - loss: 0.7271
[1m 26/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 13ms/step - accuracy: 0.6565 - loss: 0.7381
[1m 29/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 14ms/step - accuracy: 0.6516 - loss: 0.7489
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m 57/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 16ms/step - accuracy: 0.6399 - loss: 0.7888
[1m 60/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 16ms/step - accuracy: 0.6401 - loss: 0.7897
[1m 63/619[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 16ms/step - accuracy: 0.6400 - loss: 0.7908
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m  6/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 12ms/step - accuracy: 0.6983 - loss: 0.6708 
[1m 10/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 12ms/step - accuracy: 0.6877 - loss: 0.6924[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m170/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 17ms/step - accuracy: 0.6409 - loss: 0.7935
[1m173/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 17ms/step - accuracy: 0.6410 - loss: 0.7934[32m [repeated 351x across cluster][0m
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m260/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 22ms/step - accuracy: 0.6318 - loss: 0.8831[32m [repeated 128x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 66ms/step - accuracy: 0.4375 - loss: 1.2806
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 23ms/step - accuracy: 0.4954 - loss: 1.0911 [32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m 88/619[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.5907 - loss: 0.9949[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m 22/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 27ms/step - accuracy: 0.6317 - loss: 0.8799
[1m 24/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 27ms/step - accuracy: 0.6288 - loss: 0.8892[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m19s[0m 30ms/step - accuracy: 0.5882 - loss: 0.9918 - val_accuracy: 0.6475 - val_loss: 0.7791[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m Epoch 8/18[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 70ms/step - accuracy: 0.8125 - loss: 0.4531[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m100/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.5919 - loss: 0.9892
[1m102/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.5921 - loss: 0.9883
[1m106/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.5926 - loss: 0.9865
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 296ms/step
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m 8/43[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step   
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m13/43[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m18/43[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m24/43[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step 
[1m31/43[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m36/43[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 10ms/step
[1m41/43[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 43ms/step
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m 7/89[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step 
[1m14/89[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m22/89[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m27/89[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m175/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m3s[0m 24ms/step - accuracy: 0.5690 - loss: 0.9727
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m3s[0m 24ms/step - accuracy: 0.5690 - loss: 0.9726
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m3s[0m 24ms/step - accuracy: 0.5691 - loss: 0.9725
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m33/89[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m39/89[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m46/89[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m51/89[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m57/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m63/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step
[1m69/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=924593)[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=924593)[0m   _log_deprecation_warning([32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m75/89[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 9ms/step
[1m82/89[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=924593)[0m 
[1m87/89[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 10ms/step

Trial trial_2414b finished iteration 1 at 2025-11-08 14:48:08. Total running time: 2min 59s
╭──────────────────────────────────────╮
│ Trial trial_2414b result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s              176.82 │
│ time_total_s                  176.82 │
│ training_iteration                 1 │
│ val_accuracy                 0.68785 │
╰──────────────────────────────────────╯

Trial trial_2414b completed after 1 iterations at 2025-11-08 14:48:08. Total running time: 2min 59s
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m154/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.6911 - loss: 0.7223 
[1m157/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.6911 - loss: 0.7225[32m [repeated 3x across cluster][0m

Trial status: 5 TERMINATED | 15 RUNNING
Current time: 2025-11-08 14:48:09. Total running time: 3min 0s
Logical resource usage: 15.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status         N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_2414b    RUNNING              2   adam            relu                                   16                 64                  3                 1          1.29147e-05         16                                              │
│ trial_2414b    RUNNING              3   rmsprop         relu                                   16                 16                  3                 0          1.74324e-05         22                                              │
│ trial_2414b    RUNNING              2   rmsprop         tanh                                   32                 64                  3                 1          1.0258e-05          28                                              │
│ trial_2414b    RUNNING              2   rmsprop         relu                                   16                 32                  5                 0          1.48377e-05         29                                              │
│ trial_2414b    RUNNING              3   adam            relu                                   16                 32                  3                 0          2.34799e-05         18                                              │
│ trial_2414b    RUNNING              2   rmsprop         tanh                                   32                 32                  5                 1          7.10308e-06         26                                              │
│ trial_2414b    RUNNING              2   adam            tanh                                   16                 64                  3                 0          9.84048e-05         22                                              │
│ trial_2414b    RUNNING              2   adam            relu                                   16                 32                  5                 0          8.43998e-05         27                                              │
│ trial_2414b    RUNNING              2   rmsprop         relu                                   32                 32                  3                 0          1.54606e-05         21                                              │
│ trial_2414b    RUNNING              3   adam            relu                                   32                 16                  3                 0          2.67621e-05         27                                              │
│ trial_2414b    RUNNING              3   adam            relu                                   32                 64                  5                 0          5.09414e-06         25                                              │
│ trial_2414b    RUNNING              2   adam            tanh                                   32                 32                  5                 0          2.32663e-05         22                                              │
│ trial_2414b    RUNNING              2   rmsprop         tanh                                   16                 32                  5                 1          5.1345e-06          28                                              │
│ trial_2414b    RUNNING              3   adam            relu                                   16                 32                  3                 1          8.65481e-05         26                                              │
│ trial_2414b    RUNNING              2   adam            relu                                   16                 16                  3                 1          7.55321e-05         16                                              │
│ trial_2414b    TERMINATED           2   adam            relu                                   32                 16                  5                 1          7.66658e-05         28        1            176.82          0.687851 │
│ trial_2414b    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 1          6.70381e-05         15        1            156.622         0.680478 │
│ trial_2414b    TERMINATED           2   adam            tanh                                   32                 32                  3                 1          0.000126055         15        1            156.701         0.662921 │
│ trial_2414b    TERMINATED           2   adam            relu                                   32                 64                  5                 1          7.77942e-05         27        1            152.58          0.701194 │
│ trial_2414b    TERMINATED           2   rmsprop         relu                                   32                 16                  3                 0          0.000111363         18        1            129.288         0.667486 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m489/619[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 16ms/step - accuracy: 0.6477 - loss: 0.7891
[1m493/619[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 16ms/step - accuracy: 0.6478 - loss: 0.7891[32m [repeated 353x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m498/619[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 16ms/step - accuracy: 0.6478 - loss: 0.7891
[1m501/619[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 16ms/step - accuracy: 0.6478 - loss: 0.7891
[1m505/619[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 16ms/step - accuracy: 0.6478 - loss: 0.7891
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m233/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 33ms/step - accuracy: 0.5957 - loss: 1.0155[32m [repeated 204x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 72ms/step - accuracy: 0.5625 - loss: 0.8520
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.5267 - loss: 0.9551 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m212/619[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 25ms/step - accuracy: 0.6029 - loss: 0.9515[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m 34/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 24ms/step - accuracy: 0.6669 - loss: 0.7565
[1m 37/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 24ms/step - accuracy: 0.6664 - loss: 0.7578[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m19s[0m 30ms/step - accuracy: 0.6509 - loss: 0.8071 - val_accuracy: 0.6721 - val_loss: 0.6735[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m Epoch 8/26[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 63ms/step - accuracy: 0.5000 - loss: 0.7710
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 66ms/step - accuracy: 0.5625 - loss: 1.1432
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m 99/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 24ms/step - accuracy: 0.6660 - loss: 0.7504
[1m101/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 24ms/step - accuracy: 0.6661 - loss: 0.7501
[1m103/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 24ms/step - accuracy: 0.6663 - loss: 0.7499
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m130/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m9s[0m 20ms/step - accuracy: 0.6929 - loss: 0.6942 
[1m133/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m9s[0m 20ms/step - accuracy: 0.6926 - loss: 0.6950
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m425/619[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 25ms/step - accuracy: 0.5995 - loss: 0.9568
[1m428/619[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 25ms/step - accuracy: 0.5995 - loss: 0.9568[32m [repeated 352x across cluster][0m
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m2s[0m 21ms/step - accuracy: 0.6358 - loss: 0.8623
[1m214/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m2s[0m 21ms/step - accuracy: 0.6358 - loss: 0.8623
[1m216/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m1s[0m 21ms/step - accuracy: 0.6357 - loss: 0.8624
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m286/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 23ms/step - accuracy: 0.5963 - loss: 0.9339[32m [repeated 170x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 74ms/step - accuracy: 0.5625 - loss: 0.8304
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 26ms/step - accuracy: 0.5660 - loss: 0.9305 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 19ms/step - accuracy: 0.6732 - loss: 0.8703 [32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m189/619[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 24ms/step - accuracy: 0.6683 - loss: 0.7425
[1m192/619[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 24ms/step - accuracy: 0.6683 - loss: 0.7423[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m8s[0m 24ms/step - accuracy: 0.6349 - loss: 0.8650 - val_accuracy: 0.6587 - val_loss: 0.6988[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924633)[0m Epoch 19/21[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 71ms/step - accuracy: 0.7500 - loss: 0.7845[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m297/619[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 19ms/step - accuracy: 0.6846 - loss: 0.7131
[1m300/619[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 19ms/step - accuracy: 0.6846 - loss: 0.7133
[1m303/619[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 19ms/step - accuracy: 0.6845 - loss: 0.7134
[36m(train_cnn_ray_tune pid=924632)[0m 
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m370/619[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 24ms/step - accuracy: 0.6626 - loss: 0.7440
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m150/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.6750 - loss: 0.7096 
[1m152/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.6751 - loss: 0.7098
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m 40/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.5592 - loss: 0.9640
[1m 43/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 22ms/step - accuracy: 0.5607 - loss: 0.9627[32m [repeated 299x across cluster][0m
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m480/619[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 19ms/step - accuracy: 0.6814 - loss: 0.7190[32m [repeated 216x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 74ms/step - accuracy: 0.4375 - loss: 0.9743
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 26ms/step - accuracy: 0.4965 - loss: 0.9942 [32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m 98/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 22ms/step - accuracy: 0.6485 - loss: 0.8670[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m128/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 22ms/step - accuracy: 0.6443 - loss: 0.8673
[1m131/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 22ms/step - accuracy: 0.6439 - loss: 0.8675[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 24ms/step - accuracy: 0.6127 - loss: 0.8725 - val_accuracy: 0.6619 - val_loss: 0.7105[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=924628)[0m Epoch 18/22[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 78ms/step - accuracy: 0.6875 - loss: 0.7397[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m159/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m8s[0m 18ms/step - accuracy: 0.5248 - loss: 1.1788
[1m162/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m8s[0m 18ms/step - accuracy: 0.5245 - loss: 1.1792
[1m165/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m8s[0m 18ms/step - accuracy: 0.5241 - loss: 1.1797[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 18ms/step - accuracy: 0.6165 - loss: 0.9227 
[1m  8/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.6256 - loss: 0.9084[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 277ms/step
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m 7/43[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step   
[1m14/43[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m182/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m6s[0m 14ms/step - accuracy: 0.6451 - loss: 0.7862
[1m186/619[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m6s[0m 14ms/step - accuracy: 0.6452 - loss: 0.7861[32m [repeated 373x across cluster][0m
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m19/43[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m25/43[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m422/619[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 21ms/step - accuracy: 0.6801 - loss: 0.7095[32m [repeated 185x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:33:51[0m 9s/step - accuracy: 0.6250 - loss: 0.7403
[1m  4/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 19ms/step - accuracy: 0.6393 - loss: 0.7378  [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m28/43[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 10ms/step
[1m34/43[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924618)[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=924618)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m41/43[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m150/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 23ms/step - accuracy: 0.6122 - loss: 0.9214[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m138/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 23ms/step - accuracy: 0.6121 - loss: 0.9208
[1m141/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 23ms/step - accuracy: 0.6121 - loss: 0.9210[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m14s[0m 22ms/step - accuracy: 0.5455 - loss: 1.0682 - val_accuracy: 0.6043 - val_loss: 0.8087[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m Epoch 11/22[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 75ms/step - accuracy: 0.5312 - loss: 1.1489[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 15ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 38ms/step
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m 6/89[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m12/89[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step 
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m17/89[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m21/89[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m28/89[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m33/89[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m38/89[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m43/89[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m49/89[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m55/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 10ms/step
[1m60/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m66/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 10ms/step
[1m71/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m76/89[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 10ms/step
[1m81/89[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m 95/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m4s[0m 21ms/step - accuracy: 0.6312 - loss: 0.8665
[1m 98/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m4s[0m 21ms/step - accuracy: 0.6313 - loss: 0.8662
[1m101/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m4s[0m 21ms/step - accuracy: 0.6315 - loss: 0.8659[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924618)[0m 
[1m85/89[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 11ms/step

Trial trial_2414b finished iteration 1 at 2025-11-08 14:48:27. Total running time: 3min 18s
╭──────────────────────────────────────╮
│ Trial trial_2414b result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             195.412 │
│ time_total_s                 195.412 │
│ training_iteration                 1 │
│ val_accuracy                 0.64782 │
╰──────────────────────────────────────╯

Trial trial_2414b completed after 1 iterations at 2025-11-08 14:48:27. Total running time: 3min 18s
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m123/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.5661 - loss: 1.0933
[1m125/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.5660 - loss: 1.0927
[1m127/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.5660 - loss: 1.0922
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m136/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.5659 - loss: 1.0896 
[1m139/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.5659 - loss: 1.0888[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m337/619[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 24ms/step - accuracy: 0.6135 - loss: 0.9225
[1m340/619[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 24ms/step - accuracy: 0.6135 - loss: 0.9225[32m [repeated 340x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m167/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.6142 - loss: 0.9447[32m [repeated 166x across cluster][0m
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 70ms/step - accuracy: 0.5312 - loss: 0.9405
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5645 - loss: 0.9605 [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m 44/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 19ms/step - accuracy: 0.5112 - loss: 1.1855[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m147/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m12s[0m 26ms/step - accuracy: 0.6947 - loss: 0.7258
[1m150/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m12s[0m 26ms/step - accuracy: 0.6944 - loss: 0.7258[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m8s[0m 24ms/step - accuracy: 0.6351 - loss: 0.8565 - val_accuracy: 0.6608 - val_loss: 0.6923[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924633)[0m Epoch 21/21[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 64ms/step - accuracy: 0.7188 - loss: 0.9269[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m159/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.6140 - loss: 0.9444
[1m161/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.6141 - loss: 0.9445
[1m163/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.6141 - loss: 0.9446
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6810 - loss: 0.7374 
[1m  7/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6500 - loss: 0.7724[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m557/619[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 24ms/step - accuracy: 0.6132 - loss: 0.9216
[1m560/619[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 24ms/step - accuracy: 0.6132 - loss: 0.9216[32m [repeated 335x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m 81/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m5s[0m 22ms/step - accuracy: 0.6178 - loss: 0.8755[32m [repeated 159x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 57ms/step - accuracy: 0.5938 - loss: 0.9311
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 17ms/step - accuracy: 0.5729 - loss: 0.9588 [32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m110/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 20ms/step - accuracy: 0.6157 - loss: 0.9195[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m120/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 20ms/step - accuracy: 0.6172 - loss: 0.9161
[1m123/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m9s[0m 20ms/step - accuracy: 0.6175 - loss: 0.9152 [32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m8s[0m 26ms/step - accuracy: 0.5854 - loss: 0.9287 - val_accuracy: 0.6475 - val_loss: 0.7227[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m Epoch 19/28[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 71ms/step - accuracy: 0.7188 - loss: 0.6916[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 281ms/step
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m 7/43[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step   
[1m13/43[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m18/43[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m24/43[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m29/43[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 10ms/step
[1m34/43[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m39/43[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 17ms/step
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 39ms/step
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m 7/89[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m13/89[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m20/89[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m24/89[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m29/89[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m34/89[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m40/89[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m46/89[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m51/89[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m57/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m393/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m3s[0m 15ms/step - accuracy: 0.6587 - loss: 0.7750
[1m396/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m3s[0m 15ms/step - accuracy: 0.6587 - loss: 0.7749
[1m399/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m3s[0m 15ms/step - accuracy: 0.6587 - loss: 0.7747

Trial status: 6 TERMINATED | 14 RUNNING
Current time: 2025-11-08 14:48:39. Total running time: 3min 30s
Logical resource usage: 14.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status         N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_2414b    RUNNING              2   adam            relu                                   16                 64                  3                 1          1.29147e-05         16                                              │
│ trial_2414b    RUNNING              3   rmsprop         relu                                   16                 16                  3                 0          1.74324e-05         22                                              │
│ trial_2414b    RUNNING              2   rmsprop         tanh                                   32                 64                  3                 1          1.0258e-05          28                                              │
│ trial_2414b    RUNNING              2   rmsprop         relu                                   16                 32                  5                 0          1.48377e-05         29                                              │
│ trial_2414b    RUNNING              3   adam            relu                                   16                 32                  3                 0          2.34799e-05         18                                              │
│ trial_2414b    RUNNING              2   rmsprop         tanh                                   32                 32                  5                 1          7.10308e-06         26                                              │
│ trial_2414b    RUNNING              2   adam            tanh                                   16                 64                  3                 0          9.84048e-05         22                                              │
│ trial_2414b    RUNNING              2   rmsprop         relu                                   32                 32                  3                 0          1.54606e-05         21                                              │
│ trial_2414b    RUNNING              3   adam            relu                                   32                 16                  3                 0          2.67621e-05         27                                              │
│ trial_2414b    RUNNING              3   adam            relu                                   32                 64                  5                 0          5.09414e-06         25                                              │
│ trial_2414b    RUNNING              2   adam            tanh                                   32                 32                  5                 0          2.32663e-05         22                                              │
│ trial_2414b    RUNNING              2   rmsprop         tanh                                   16                 32                  5                 1          5.1345e-06          28                                              │
│ trial_2414b    RUNNING              3   adam            relu                                   16                 32                  3                 1          8.65481e-05         26                                              │
│ trial_2414b    RUNNING              2   adam            relu                                   16                 16                  3                 1          7.55321e-05         16                                              │
│ trial_2414b    TERMINATED           2   adam            relu                                   32                 16                  5                 1          7.66658e-05         28        1            176.82          0.687851 │
│ trial_2414b    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 1          6.70381e-05         15        1            156.622         0.680478 │
│ trial_2414b    TERMINATED           2   adam            tanh                                   32                 32                  3                 1          0.000126055         15        1            156.701         0.662921 │
│ trial_2414b    TERMINATED           2   adam            relu                                   16                 32                  5                 0          8.43998e-05         27        1            195.412         0.647823 │
│ trial_2414b    TERMINATED           2   adam            relu                                   32                 64                  5                 1          7.77942e-05         27        1            152.58          0.701194 │
│ trial_2414b    TERMINATED           2   rmsprop         relu                                   32                 16                  3                 0          0.000111363         18        1            129.288         0.667486 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m63/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 10ms/step
[1m68/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 10ms/step
[1m75/89[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m81/89[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 10ms/step
[1m88/89[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924633)[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=924633)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m408/619[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m3s[0m 15ms/step - accuracy: 0.6588 - loss: 0.7743
[1m412/619[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m3s[0m 15ms/step - accuracy: 0.6588 - loss: 0.7741
[1m415/619[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m2s[0m 15ms/step - accuracy: 0.6588 - loss: 0.7740

Trial trial_2414b finished iteration 1 at 2025-11-08 14:48:40. Total running time: 3min 31s
╭──────────────────────────────────────╮
│ Trial trial_2414b result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             207.874 │
│ time_total_s                 207.874 │
│ training_iteration                 1 │
│ val_accuracy                 0.66152 │
╰──────────────────────────────────────╯

Trial trial_2414b completed after 1 iterations at 2025-11-08 14:48:40. Total running time: 3min 31s
[36m(train_cnn_ray_tune pid=924633)[0m 
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m474/619[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 15ms/step - accuracy: 0.6592 - loss: 0.7714
[1m478/619[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 15ms/step - accuracy: 0.6592 - loss: 0.7712[32m [repeated 407x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m588/619[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 19ms/step - accuracy: 0.5242 - loss: 1.1762[32m [repeated 150x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 84ms/step - accuracy: 0.6562 - loss: 0.7486
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 34ms/step - accuracy: 0.6632 - loss: 0.7263
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m 69/619[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 20ms/step - accuracy: 0.5746 - loss: 1.0331[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m 62/619[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 25ms/step - accuracy: 0.6083 - loss: 0.9006
[1m 64/619[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 25ms/step - accuracy: 0.6084 - loss: 0.9006[32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 24ms/step - accuracy: 0.5641 - loss: 1.0303 - val_accuracy: 0.6155 - val_loss: 0.7807[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924629)[0m Epoch 22/26[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 70ms/step - accuracy: 0.5625 - loss: 0.9907[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 77ms/step - accuracy: 0.5625 - loss: 0.9598
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5697 - loss: 1.0091 
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m  5/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 14ms/step - accuracy: 0.5444 - loss: 1.0961 
[1m  9/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 15ms/step - accuracy: 0.5344 - loss: 1.1206
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m279/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 29ms/step - accuracy: 0.6186 - loss: 0.9367
[1m281/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 29ms/step - accuracy: 0.6186 - loss: 0.9367
[1m283/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 29ms/step - accuracy: 0.6186 - loss: 0.9367
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m277/619[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.6168 - loss: 0.8968
[1m280/619[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.6168 - loss: 0.8970[32m [repeated 317x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m162/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 17ms/step - accuracy: 0.5442 - loss: 1.1138[32m [repeated 120x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m 97/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 22ms/step - accuracy: 0.6788 - loss: 0.7021[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m 85/619[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 22ms/step - accuracy: 0.6804 - loss: 0.6969
[1m 88/619[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 22ms/step - accuracy: 0.6798 - loss: 0.6986[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 21ms/step - accuracy: 0.6132 - loss: 0.9071 - val_accuracy: 0.6703 - val_loss: 0.6894[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m Epoch 13/29[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 58ms/step - accuracy: 0.5000 - loss: 1.0254
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 66ms/step - accuracy: 0.7500 - loss: 0.8121
[1m  4/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 19ms/step - accuracy: 0.6393 - loss: 0.8440[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 63ms/step - accuracy: 0.5625 - loss: 0.9264
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m122/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m9s[0m 20ms/step - accuracy: 0.6318 - loss: 0.9050 
[1m125/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m9s[0m 20ms/step - accuracy: 0.6318 - loss: 0.9044
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m252/619[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m4s[0m 13ms/step - accuracy: 0.6556 - loss: 0.7367
[1m256/619[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m4s[0m 13ms/step - accuracy: 0.6556 - loss: 0.7367
[1m260/619[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m4s[0m 13ms/step - accuracy: 0.6556 - loss: 0.7367[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m511/619[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 23ms/step - accuracy: 0.6158 - loss: 0.9028
[1m514/619[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 23ms/step - accuracy: 0.6158 - loss: 0.9028[32m [repeated 371x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m517/619[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 23ms/step - accuracy: 0.6158 - loss: 0.9028[32m [repeated 172x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5755 - loss: 0.9325 [32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m116/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 20ms/step - accuracy: 0.6317 - loss: 0.9063
[1m119/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 20ms/step - accuracy: 0.6317 - loss: 0.9056[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 23ms/step - accuracy: 0.5843 - loss: 0.9234 - val_accuracy: 0.6447 - val_loss: 0.7217[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m Epoch 21/28[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 66ms/step - accuracy: 0.5625 - loss: 1.1536
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6035 - loss: 0.9387 [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 70ms/step - accuracy: 0.5938 - loss: 0.9091[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m  5/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 14ms/step - accuracy: 0.5740 - loss: 1.1159 
[1m  9/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 13ms/step - accuracy: 0.5950 - loss: 1.0615[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m538/619[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 17ms/step - accuracy: 0.5422 - loss: 1.1338
[1m541/619[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 17ms/step - accuracy: 0.5423 - loss: 1.1338
[1m544/619[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 17ms/step - accuracy: 0.5423 - loss: 1.1338
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m118/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m6s[0m 13ms/step - accuracy: 0.6476 - loss: 0.8269
[1m123/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m6s[0m 13ms/step - accuracy: 0.6481 - loss: 0.8246[32m [repeated 365x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m185/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 17ms/step - accuracy: 0.5532 - loss: 1.0560[32m [repeated 159x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m 37/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 19ms/step - accuracy: 0.6033 - loss: 0.9364[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m 22/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 20ms/step - accuracy: 0.5879 - loss: 0.9389
[1m 26/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 19ms/step - accuracy: 0.5929 - loss: 0.9393[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m16s[0m 26ms/step - accuracy: 0.6158 - loss: 0.9036 - val_accuracy: 0.6682 - val_loss: 0.7294[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924628)[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=924628)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=924621)[0m Epoch 11/18[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 52ms/step - accuracy: 0.5625 - loss: 1.3413
[1m  5/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 15ms/step - accuracy: 0.5627 - loss: 1.1925 
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 242ms/step
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m 7/43[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step   
[1m15/43[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m195/619[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m5s[0m 13ms/step - accuracy: 0.6517 - loss: 0.8041
[1m199/619[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m5s[0m 13ms/step - accuracy: 0.6519 - loss: 0.8031
[1m204/619[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m5s[0m 13ms/step - accuracy: 0.6521 - loss: 0.8019
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m21/43[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m28/43[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m35/43[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m41/43[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 60ms/step - accuracy: 0.6875 - loss: 0.7725[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 35ms/step
[1m 7/89[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step 
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m13/89[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m19/89[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m24/89[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m29/89[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m35/89[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m41/89[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m46/89[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m52/89[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m59/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m65/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 10ms/step
[1m71/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m77/89[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step 
[1m84/89[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step

Trial trial_2414b finished iteration 1 at 2025-11-08 14:48:58. Total running time: 3min 49s
╭──────────────────────────────────────╮
│ Trial trial_2414b result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             226.576 │
│ time_total_s                 226.576 │
│ training_iteration                 1 │
│ val_accuracy                 0.65098 │
╰──────────────────────────────────────╯

Trial trial_2414b completed after 1 iterations at 2025-11-08 14:48:58. Total running time: 3min 49s
[36m(train_cnn_ray_tune pid=924628)[0m 
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 17ms/step - accuracy: 0.6549 - loss: 0.7557 
[1m  8/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 17ms/step - accuracy: 0.6606 - loss: 0.7642[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m275/619[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 21ms/step - accuracy: 0.6232 - loss: 0.9094
[1m277/619[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 21ms/step - accuracy: 0.6233 - loss: 0.9093[32m [repeated 317x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m280/619[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6233 - loss: 0.9090[32m [repeated 140x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[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=924602)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m 69/619[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.6835 - loss: 0.7389[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m 77/619[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 22ms/step - accuracy: 0.6829 - loss: 0.7370
[1m 79/619[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 22ms/step - accuracy: 0.6828 - loss: 0.7365[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m14s[0m 22ms/step - accuracy: 0.6380 - loss: 0.8851 - val_accuracy: 0.6626 - val_loss: 0.7150[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=924586)[0m Epoch 13/16[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 52ms/step - accuracy: 0.8125 - loss: 0.4976
[1m  5/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 17ms/step - accuracy: 0.7719 - loss: 0.6646[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m136/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m4s[0m 28ms/step - accuracy: 0.6218 - loss: 0.9123
[1m138/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m4s[0m 28ms/step - accuracy: 0.6219 - loss: 0.9123
[1m140/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m4s[0m 28ms/step - accuracy: 0.6219 - loss: 0.9124[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 62ms/step - accuracy: 0.7500 - loss: 0.8235
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 66ms/step - accuracy: 0.6875 - loss: 0.7392
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 298ms/step
[1m 8/43[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step   
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m16/43[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m24/43[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m31/43[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 7ms/step
[1m39/43[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.6335 - loss: 0.8092 
[1m  8/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 18ms/step - accuracy: 0.6234 - loss: 0.8131[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 36ms/step
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m 8/89[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step 
[1m16/89[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m24/89[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m32/89[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m39/89[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m47/89[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m54/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 7ms/step
[1m63/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=924602)[0m 
[1m73/89[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 7ms/step
[1m83/89[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 7ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

Trial trial_2414b finished iteration 1 at 2025-11-08 14:49:05. Total running time: 3min 56s
╭──────────────────────────────────────╮
│ Trial trial_2414b result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             233.534 │
│ time_total_s                 233.534 │
│ training_iteration                 1 │
│ val_accuracy                 0.67135 │
╰──────────────────────────────────────╯

Trial trial_2414b completed after 1 iterations at 2025-11-08 14:49:05. Total running time: 3min 56s
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m517/619[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 21ms/step - accuracy: 0.6262 - loss: 0.8966
[1m520/619[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 21ms/step - accuracy: 0.6262 - loss: 0.8966[32m [repeated 313x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m327/619[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6879 - loss: 0.7123[32m [repeated 168x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m161/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 22ms/step - accuracy: 0.6854 - loss: 0.7197 [32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m  8/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 17ms/step - accuracy: 0.6304 - loss: 1.0712
[1m 12/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 16ms/step - accuracy: 0.6153 - loss: 1.0884[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 20ms/step - accuracy: 0.5654 - loss: 1.0298 - val_accuracy: 0.6254 - val_loss: 0.7674[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m Epoch 14/22[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 64ms/step - accuracy: 0.6875 - loss: 0.9309
[1m  5/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 17ms/step - accuracy: 0.6471 - loss: 1.0424[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m281/619[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 21ms/step - accuracy: 0.6877 - loss: 0.7136
[1m284/619[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 21ms/step - accuracy: 0.6877 - loss: 0.7135
[1m287/619[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 21ms/step - accuracy: 0.6877 - loss: 0.7134[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 62ms/step - accuracy: 0.5000 - loss: 0.9898[32m [repeated 5x across cluster][0m

Trial status: 9 TERMINATED | 11 RUNNING
Current time: 2025-11-08 14:49:09. Total running time: 4min 0s
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_2414b    RUNNING              2   adam            relu                                   16                 64                  3                 1          1.29147e-05         16                                              │
│ trial_2414b    RUNNING              3   rmsprop         relu                                   16                 16                  3                 0          1.74324e-05         22                                              │
│ trial_2414b    RUNNING              2   rmsprop         tanh                                   32                 64                  3                 1          1.0258e-05          28                                              │
│ trial_2414b    RUNNING              2   rmsprop         relu                                   16                 32                  5                 0          1.48377e-05         29                                              │
│ trial_2414b    RUNNING              3   adam            relu                                   16                 32                  3                 0          2.34799e-05         18                                              │
│ trial_2414b    RUNNING              2   rmsprop         tanh                                   32                 32                  5                 1          7.10308e-06         26                                              │
│ trial_2414b    RUNNING              2   adam            tanh                                   16                 64                  3                 0          9.84048e-05         22                                              │
│ trial_2414b    RUNNING              3   adam            relu                                   32                 16                  3                 0          2.67621e-05         27                                              │
│ trial_2414b    RUNNING              3   adam            relu                                   32                 64                  5                 0          5.09414e-06         25                                              │
│ trial_2414b    RUNNING              2   rmsprop         tanh                                   16                 32                  5                 1          5.1345e-06          28                                              │
│ trial_2414b    RUNNING              3   adam            relu                                   16                 32                  3                 1          8.65481e-05         26                                              │
│ trial_2414b    TERMINATED           2   adam            relu                                   32                 16                  5                 1          7.66658e-05         28        1            176.82          0.687851 │
│ trial_2414b    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 1          6.70381e-05         15        1            156.622         0.680478 │
│ trial_2414b    TERMINATED           2   adam            tanh                                   32                 32                  3                 1          0.000126055         15        1            156.701         0.662921 │
│ trial_2414b    TERMINATED           2   adam            relu                                   16                 32                  5                 0          8.43998e-05         27        1            195.412         0.647823 │
│ trial_2414b    TERMINATED           2   rmsprop         relu                                   32                 32                  3                 0          1.54606e-05         21        1            207.874         0.661517 │
│ trial_2414b    TERMINATED           2   adam            tanh                                   32                 32                  5                 0          2.32663e-05         22        1            226.576         0.650983 │
│ trial_2414b    TERMINATED           2   adam            relu                                   32                 64                  5                 1          7.77942e-05         27        1            152.58          0.701194 │
│ trial_2414b    TERMINATED           2   rmsprop         relu                                   32                 16                  3                 0          0.000111363         18        1            129.288         0.667486 │
│ trial_2414b    TERMINATED           2   adam            relu                                   16                 16                  3                 1          7.55321e-05         16        1            233.534         0.671348 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m  5/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 16ms/step - accuracy: 0.5956 - loss: 0.9159 
[1m  9/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 16ms/step - accuracy: 0.6151 - loss: 0.8862[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m580/619[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 20ms/step - accuracy: 0.6862 - loss: 0.7096
[1m583/619[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 20ms/step - accuracy: 0.6861 - loss: 0.7095[32m [repeated 310x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m586/619[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 20ms/step - accuracy: 0.6861 - loss: 0.7095[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 19ms/step - accuracy: 0.5560 - loss: 0.8509 
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m 72/619[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 19ms/step - accuracy: 0.6154 - loss: 0.8767
[1m 75/619[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 19ms/step - accuracy: 0.6160 - loss: 0.8769[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 21ms/step - accuracy: 0.6338 - loss: 0.8348 - val_accuracy: 0.6787 - val_loss: 0.6739[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m Epoch 23/27[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 58ms/step - accuracy: 0.6562 - loss: 0.7984
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 19ms/step - accuracy: 0.6549 - loss: 0.8195 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m559/619[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 20ms/step - accuracy: 0.6863 - loss: 0.7098
[1m562/619[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 20ms/step - accuracy: 0.6863 - loss: 0.7097
[1m565/619[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 20ms/step - accuracy: 0.6862 - loss: 0.7097[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 60ms/step - accuracy: 0.8750 - loss: 0.3332[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 253ms/step
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m 36/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 19ms/step - accuracy: 0.6956 - loss: 0.6758
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m 9/43[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step   
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m17/43[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m25/43[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m33/43[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 6ms/step
[1m42/43[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m 55/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 18ms/step - accuracy: 0.6909 - loss: 0.6824 
[1m 59/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 18ms/step - accuracy: 0.6909 - loss: 0.6833[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 13ms/step
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 34ms/step
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m 8/89[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step 
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m16/89[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m23/89[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m29/89[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m35/89[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m41/89[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m48/89[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m53/89[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m59/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m66/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 8ms/step
[1m74/89[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=924629)[0m 
[1m81/89[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 8ms/step
[1m87/89[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 8ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/step

Trial trial_2414b finished iteration 1 at 2025-11-08 14:49:15. Total running time: 4min 7s
[36m(train_cnn_ray_tune pid=924629)[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=924629)[0m   _log_deprecation_warning(
╭──────────────────────────────────────╮
│ Trial trial_2414b result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             244.016 │
│ time_total_s                 244.016 │
│ training_iteration                 1 │
│ val_accuracy                   0.625 │
╰──────────────────────────────────────╯

Trial trial_2414b completed after 1 iterations at 2025-11-08 14:49:15. Total running time: 4min 7s
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m141/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m8s[0m 18ms/step - accuracy: 0.6948 - loss: 0.6896
[1m144/619[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m8s[0m 18ms/step - accuracy: 0.6948 - loss: 0.6898[32m [repeated 316x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m569/619[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 14ms/step - accuracy: 0.6365 - loss: 0.8559[32m [repeated 99x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m 48/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 18ms/step - accuracy: 0.6915 - loss: 0.6802
[1m 52/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 18ms/step - accuracy: 0.6909 - loss: 0.6816[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m11s[0m 18ms/step - accuracy: 0.5882 - loss: 0.9972 - val_accuracy: 0.6275 - val_loss: 0.7547[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m Epoch 15/22[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 55ms/step - accuracy: 0.5625 - loss: 0.9024
[1m  5/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 14ms/step - accuracy: 0.5517 - loss: 1.0479 
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 66ms/step - accuracy: 0.6875 - loss: 0.8820
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 16ms/step - accuracy: 0.7174 - loss: 0.7851 
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m594/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 14ms/step - accuracy: 0.5442 - loss: 1.1192
[1m598/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 14ms/step - accuracy: 0.5442 - loss: 1.1192
[1m602/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 14ms/step - accuracy: 0.5442 - loss: 1.1191[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 59ms/step - accuracy: 0.4375 - loss: 1.4822[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 18ms/step - accuracy: 0.7246 - loss: 0.7168 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m  5/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 13ms/step - accuracy: 0.5244 - loss: 1.2019 
[1m  9/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 13ms/step - accuracy: 0.5255 - loss: 1.1724
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 17ms/step - accuracy: 0.6145 - loss: 0.8735
[1m272/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 17ms/step - accuracy: 0.6145 - loss: 0.8735[32m [repeated 326x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m200/619[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m6s[0m 15ms/step - accuracy: 0.5504 - loss: 1.0918[32m [repeated 102x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m10s[0m 17ms/step - accuracy: 0.6363 - loss: 0.8562 - val_accuracy: 0.6713 - val_loss: 0.6799[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m Epoch 16/29[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 62ms/step - accuracy: 0.6875 - loss: 0.8378
[1m  5/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 13ms/step - accuracy: 0.6438 - loss: 0.8653 
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m544/619[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 16ms/step - accuracy: 0.7380 - loss: 0.6356
[1m547/619[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 16ms/step - accuracy: 0.7380 - loss: 0.6356
[1m550/619[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 16ms/step - accuracy: 0.7380 - loss: 0.6356[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 61ms/step - accuracy: 0.6250 - loss: 0.9392
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.6268 - loss: 0.8942 
[36m(train_cnn_ray_tune pid=924630)[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=924630)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m  5/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 13ms/step - accuracy: 0.6812 - loss: 0.7332 
[1m  9/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 13ms/step - accuracy: 0.6445 - loss: 0.8173
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 299ms/step
[1m 8/43[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step   
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m16/43[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m23/43[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m30/43[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m38/43[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m  8/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 16ms/step - accuracy: 0.7102 - loss: 0.7692
[1m 12/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 16ms/step - accuracy: 0.6982 - loss: 0.7740 
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 47ms/step - accuracy: 0.6250 - loss: 0.6243[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 15ms/step - accuracy: 0.6710 - loss: 0.6798 
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 36ms/step
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m 8/89[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step 
[1m16/89[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m23/89[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m30/89[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m38/89[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m45/89[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m53/89[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m60/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m67/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 8ms/step
[1m74/89[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=924630)[0m 
[1m81/89[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 7ms/step
[1m88/89[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 7ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step

Trial trial_2414b finished iteration 1 at 2025-11-08 14:49:25. Total running time: 4min 16s
╭──────────────────────────────────────╮
│ Trial trial_2414b result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             253.532 │
│ time_total_s                 253.532 │
│ training_iteration                 1 │
│ val_accuracy                  0.6724 │
╰──────────────────────────────────────╯

Trial trial_2414b completed after 1 iterations at 2025-11-08 14:49:25. Total running time: 4min 16s
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m201/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 16ms/step - accuracy: 0.6474 - loss: 0.7930
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m1s[0m 16ms/step - accuracy: 0.6473 - loss: 0.7933[32m [repeated 250x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m227/619[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m6s[0m 16ms/step - accuracy: 0.6291 - loss: 0.8576[32m [repeated 142x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m10s[0m 16ms/step - accuracy: 0.5886 - loss: 0.9712 - val_accuracy: 0.6289 - val_loss: 0.7467[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m Epoch 16/22[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m571/619[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 17ms/step - accuracy: 0.6984 - loss: 0.6862
[1m574/619[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 17ms/step - accuracy: 0.6984 - loss: 0.6863
[1m577/619[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 17ms/step - accuracy: 0.6984 - loss: 0.6863[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 60ms/step - accuracy: 0.8125 - loss: 0.4815
[1m  5/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 15ms/step - accuracy: 0.7704 - loss: 0.5806 [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m  5/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 15ms/step - accuracy: 0.5273 - loss: 1.0083 
[1m  9/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 15ms/step - accuracy: 0.5549 - loss: 0.9767
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m  5/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 14ms/step - accuracy: 0.6902 - loss: 0.8187 
[1m 10/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 12ms/step - accuracy: 0.6560 - loss: 0.8527
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m 29/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 17ms/step - accuracy: 0.7248 - loss: 0.6057
[1m 33/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 17ms/step - accuracy: 0.7221 - loss: 0.6082 [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 58ms/step - accuracy: 0.6875 - loss: 0.9148[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m552/619[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 16ms/step - accuracy: 0.6278 - loss: 0.8586
[1m556/619[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 16ms/step - accuracy: 0.6278 - loss: 0.8586[32m [repeated 267x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m243/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 14ms/step - accuracy: 0.6096 - loss: 0.8703[32m [repeated 139x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 24ms/step - accuracy: 0.6214 - loss: 0.9078 - val_accuracy: 0.6622 - val_loss: 0.7027[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m Epoch 20/25[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m2s[0m 14ms/step - accuracy: 0.6254 - loss: 0.8429
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m2s[0m 14ms/step - accuracy: 0.6256 - loss: 0.8424
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m2s[0m 14ms/step - accuracy: 0.6257 - loss: 0.8420
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 62ms/step - accuracy: 0.4688 - loss: 1.0723
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 15ms/step - accuracy: 0.5537 - loss: 0.9131 [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6445 - loss: 0.9237 
[1m  7/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6161 - loss: 0.9472
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m300/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 15ms/step - accuracy: 0.6306 - loss: 0.8288
[1m304/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 15ms/step - accuracy: 0.6307 - loss: 0.8285
[1m307/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 15ms/step - accuracy: 0.6308 - loss: 0.8284
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m  5/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 16ms/step - accuracy: 0.6044 - loss: 0.8111 
[1m  9/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 15ms/step - accuracy: 0.6142 - loss: 0.8190
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 58ms/step - accuracy: 0.5625 - loss: 0.8962[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m292/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 20ms/step - accuracy: 0.6325 - loss: 0.8877
[1m295/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 20ms/step - accuracy: 0.6325 - loss: 0.8877[32m [repeated 274x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m158/619[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 16ms/step - accuracy: 0.6432 - loss: 0.8179[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 15ms/step - accuracy: 0.6005 - loss: 0.9443 - val_accuracy: 0.6299 - val_loss: 0.7355[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m Epoch 17/22[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m 13/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 9ms/step - accuracy: 0.6224 - loss: 0.9028
[1m 19/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 9ms/step - accuracy: 0.6181 - loss: 0.9116
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m 24/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 10ms/step - accuracy: 0.6172 - loss: 0.9130
[1m 30/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 10ms/step - accuracy: 0.6181 - loss: 0.9120
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 56ms/step - accuracy: 0.6250 - loss: 0.7606
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6302 - loss: 0.8521 [32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m587/619[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step - accuracy: 0.6327 - loss: 0.8525
[1m591/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step - accuracy: 0.6327 - loss: 0.8525
[1m595/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step - accuracy: 0.6327 - loss: 0.8525[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 306ms/step
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m 8/43[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step   
[1m15/43[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m22/43[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m30/43[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m37/43[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m  5/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 13ms/step - accuracy: 0.7758 - loss: 0.5506 
[1m  9/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 13ms/step - accuracy: 0.7469 - loss: 0.6102[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 13ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 38ms/step
[1m10/89[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step 
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m18/89[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[1m26/89[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m33/89[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 49ms/step - accuracy: 0.7500 - loss: 0.4542
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m41/89[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m49/89[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m57/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 7ms/step
[1m65/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 7ms/step

Trial status: 11 TERMINATED | 9 RUNNING
Current time: 2025-11-08 14:49:39. Total running time: 4min 30s
Logical resource usage: 9.0/20 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_2414b    RUNNING              2   adam            relu                                   16                 64                  3                 1          1.29147e-05         16                                              │
│ trial_2414b    RUNNING              3   rmsprop         relu                                   16                 16                  3                 0          1.74324e-05         22                                              │
│ trial_2414b    RUNNING              2   rmsprop         tanh                                   32                 64                  3                 1          1.0258e-05          28                                              │
│ trial_2414b    RUNNING              2   rmsprop         relu                                   16                 32                  5                 0          1.48377e-05         29                                              │
│ trial_2414b    RUNNING              3   adam            relu                                   16                 32                  3                 0          2.34799e-05         18                                              │
│ trial_2414b    RUNNING              3   adam            relu                                   32                 16                  3                 0          2.67621e-05         27                                              │
│ trial_2414b    RUNNING              3   adam            relu                                   32                 64                  5                 0          5.09414e-06         25                                              │
│ trial_2414b    RUNNING              2   rmsprop         tanh                                   16                 32                  5                 1          5.1345e-06          28                                              │
│ trial_2414b    RUNNING              3   adam            relu                                   16                 32                  3                 1          8.65481e-05         26                                              │
│ trial_2414b    TERMINATED           2   adam            relu                                   32                 16                  5                 1          7.66658e-05         28        1            176.82          0.687851 │
│ trial_2414b    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 1          6.70381e-05         15        1            156.622         0.680478 │
│ trial_2414b    TERMINATED           2   adam            tanh                                   32                 32                  3                 1          0.000126055         15        1            156.701         0.662921 │
│ trial_2414b    TERMINATED           2   rmsprop         tanh                                   32                 32                  5                 1          7.10308e-06         26        1            244.016         0.625    │
│ trial_2414b    TERMINATED           2   adam            tanh                                   16                 64                  3                 0          9.84048e-05         22        1            253.532         0.672402 │
│ trial_2414b    TERMINATED           2   adam            relu                                   16                 32                  5                 0          8.43998e-05         27        1            195.412         0.647823 │
│ trial_2414b    TERMINATED           2   rmsprop         relu                                   32                 32                  3                 0          1.54606e-05         21        1            207.874         0.661517 │
│ trial_2414b    TERMINATED           2   adam            tanh                                   32                 32                  5                 0          2.32663e-05         22        1            226.576         0.650983 │
│ trial_2414b    TERMINATED           2   adam            relu                                   32                 64                  5                 1          7.77942e-05         27        1            152.58          0.701194 │
│ trial_2414b    TERMINATED           2   rmsprop         relu                                   32                 16                  3                 0          0.000111363         18        1            129.288         0.667486 │
│ trial_2414b    TERMINATED           2   adam            relu                                   16                 16                  3                 1          7.55321e-05         16        1            233.534         0.671348 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m72/89[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 7ms/step
[1m80/89[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=924619)[0m 
[1m88/89[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 7ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 399ms/step

Trial trial_2414b finished iteration 1 at 2025-11-08 14:49:40. Total running time: 4min 31s
[36m(train_cnn_ray_tune pid=924619)[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=924619)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=924627)[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=924627)[0m   _log_deprecation_warning(
╭──────────────────────────────────────╮
│ Trial trial_2414b result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             268.245 │
│ time_total_s                 268.245 │
│ training_iteration                 1 │
│ val_accuracy                 0.65028 │
╰──────────────────────────────────────╯

Trial trial_2414b completed after 1 iterations at 2025-11-08 14:49:40. Total running time: 4min 31s
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 36ms/step
[1m 9/89[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step 

Trial trial_2414b finished iteration 1 at 2025-11-08 14:49:41. Total running time: 4min 32s
╭──────────────────────────────────────╮
│ Trial trial_2414b result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             269.448 │
│ time_total_s                 269.448 │
│ training_iteration                 1 │
│ val_accuracy                 0.67346 │
╰──────────────────────────────────────╯

Trial trial_2414b completed after 1 iterations at 2025-11-08 14:49:41. Total running time: 4min 32s
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m508/619[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 15ms/step - accuracy: 0.6435 - loss: 0.8362
[1m512/619[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 15ms/step - accuracy: 0.6435 - loss: 0.8363[32m [repeated 272x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m462/619[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m1s[0m 12ms/step - accuracy: 0.5869 - loss: 0.9587[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m5s[0m 17ms/step - accuracy: 0.6380 - loss: 0.8157 - val_accuracy: 0.6735 - val_loss: 0.6603[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m Epoch 21/25[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m483/619[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m1s[0m 11ms/step - accuracy: 0.5464 - loss: 1.0784
[1m488/619[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m1s[0m 11ms/step - accuracy: 0.5464 - loss: 1.0784
[1m493/619[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m1s[0m 11ms/step - accuracy: 0.5465 - loss: 1.0784[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 250ms/step
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m16/43[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step   
[36m(train_cnn_ray_tune pid=924627)[0m 
[1m 9/43[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step   
[1m17/43[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m32/43[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 3ms/step[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 52ms/step - accuracy: 0.6875 - loss: 0.8669
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 30ms/step - accuracy: 0.5000 - loss: 1.3016
[1m  7/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 9ms/step - accuracy: 0.5650 - loss: 0.9820  
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m 13/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 9ms/step - accuracy: 0.5771 - loss: 0.9386
[1m 18/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 9ms/step - accuracy: 0.5861 - loss: 0.9110
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 31ms/step
[1m11/89[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step 
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m 23/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 10ms/step - accuracy: 0.5935 - loss: 0.8958
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m  5/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 13ms/step - accuracy: 0.6754 - loss: 0.8355 
[1m 10/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 13ms/step - accuracy: 0.6847 - loss: 0.7836
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m  7/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 10ms/step - accuracy: 0.6758 - loss: 0.7882 
[1m 13/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 10ms/step - accuracy: 0.6805 - loss: 0.7988

Trial trial_2414b finished iteration 1 at 2025-11-08 14:49:44. Total running time: 4min 35s
╭──────────────────────────────────────╮
│ Trial trial_2414b result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             272.734 │
│ time_total_s                 272.734 │
│ training_iteration                 1 │
│ val_accuracy                 0.65871 │
╰──────────────────────────────────────╯

Trial trial_2414b completed after 1 iterations at 2025-11-08 14:49:44. Total running time: 4min 35s
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m228/619[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m4s[0m 12ms/step - accuracy: 0.6530 - loss: 0.8180
[1m233/619[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m4s[0m 12ms/step - accuracy: 0.6527 - loss: 0.8185[32m [repeated 181x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m253/619[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m3s[0m 10ms/step - accuracy: 0.6059 - loss: 0.9056[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 15ms/step - accuracy: 0.6976 - loss: 0.6483 - val_accuracy: 0.6963 - val_loss: 0.6912[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m Epoch 15/26[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924586)[0m 
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 5ms/step[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 49ms/step - accuracy: 0.5625 - loss: 0.8768[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 54ms/step - accuracy: 0.6250 - loss: 0.7254
[1m  6/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 12ms/step - accuracy: 0.6882 - loss: 0.6286 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m546/619[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5477 - loss: 1.0885
[1m554/619[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5478 - loss: 1.0884[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m437/619[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5467 - loss: 1.0909[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m223/619[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m4s[0m 11ms/step - accuracy: 0.7024 - loss: 0.6315
[1m230/619[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m4s[0m 11ms/step - accuracy: 0.7023 - loss: 0.6319
[1m236/619[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m4s[0m 11ms/step - accuracy: 0.7022 - loss: 0.6322
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 15ms/step - accuracy: 0.6670 - loss: 0.8499 
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m  7/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 10ms/step - accuracy: 0.5228 - loss: 1.1582 
[1m 12/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 10ms/step - accuracy: 0.5326 - loss: 1.1471
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m6s[0m 10ms/step - accuracy: 0.6454 - loss: 0.8317 - val_accuracy: 0.6766 - val_loss: 0.6685
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m  7/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 8ms/step - accuracy: 0.5118 - loss: 1.0633  
[1m 13/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 9ms/step - accuracy: 0.5122 - loss: 1.0561
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m  7/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 10ms/step - accuracy: 0.4571 - loss: 1.2278 
[1m 13/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 9ms/step - accuracy: 0.5028 - loss: 1.1495 
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m453/619[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m1s[0m 11ms/step - accuracy: 0.6996 - loss: 0.6395
[1m458/619[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m1s[0m 11ms/step - accuracy: 0.6996 - loss: 0.6397[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 14ms/step - accuracy: 0.6482 - loss: 0.8443[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m5s[0m 17ms/step - accuracy: 0.6440 - loss: 0.8588 - val_accuracy: 0.6633 - val_loss: 0.6938
[36m(train_cnn_ray_tune pid=924585)[0m Epoch 19/22[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m8s[0m 13ms/step - accuracy: 0.6432 - loss: 0.8333 - val_accuracy: 0.6756 - val_loss: 0.7134
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m316/619[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.5998 - loss: 0.9544 
[1m324/619[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.5999 - loss: 0.9543
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 53ms/step - accuracy: 0.3125 - loss: 1.4606[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[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=924632)[0m   _log_deprecation_warning([32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 55ms/step - accuracy: 0.5000 - loss: 1.1469
[1m  5/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 13ms/step - accuracy: 0.5727 - loss: 0.9508 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m418/619[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m1s[0m 8ms/step - accuracy: 0.5616 - loss: 1.0561
[1m427/619[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m1s[0m 8ms/step - accuracy: 0.5616 - loss: 1.0561[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m331/619[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.5613 - loss: 1.0552[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 413ms/step
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m528/619[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5619 - loss: 1.0570
[1m534/619[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5619 - loss: 1.0570
[1m540/619[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5619 - loss: 1.0571
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m10/43[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step   
[1m20/43[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m29/43[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 6ms/step
[1m39/43[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 11ms/step - accuracy: 0.6040 - loss: 0.9148 - val_accuracy: 0.6355 - val_loss: 0.7250[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 39ms/step
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m11/89[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step 
[1m21/89[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m32/89[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step
[1m42/89[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 15ms/step - accuracy: 0.6636 - loss: 0.7933 
[1m  9/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 15ms/step - accuracy: 0.6688 - loss: 0.7919
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m52/89[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 5ms/step
[1m62/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m72/89[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 5ms/step
[1m82/89[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 5ms/step

Trial trial_2414b finished iteration 1 at 2025-11-08 14:49:56. Total running time: 4min 47s
╭──────────────────────────────────────╮
│ Trial trial_2414b result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             283.986 │
│ time_total_s                 283.986 │
│ training_iteration                 1 │
│ val_accuracy                  0.6882 │
╰──────────────────────────────────────╯

Trial trial_2414b completed after 1 iterations at 2025-11-08 14:49:56. Total running time: 4min 47s
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 5ms/step
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m  8/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 7ms/step - accuracy: 0.4295 - loss: 1.3859  
[1m 15/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 7ms/step - accuracy: 0.4288 - loss: 1.3442
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m467/619[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m1s[0m 10ms/step - accuracy: 0.6519 - loss: 0.8128
[1m473/619[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m1s[0m 10ms/step - accuracy: 0.6519 - loss: 0.8130[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 13ms/step - accuracy: 0.6465 - loss: 0.8307[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m Epoch 21/28[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924632)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m8s[0m 12ms/step - accuracy: 0.6992 - loss: 0.6433 - val_accuracy: 0.6882 - val_loss: 0.6933[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 46ms/step - accuracy: 0.3750 - loss: 1.2878[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 51ms/step - accuracy: 0.5625 - loss: 1.0800
[1m  7/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 10ms/step - accuracy: 0.6545 - loss: 0.9315 [32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m369/619[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 7ms/step - accuracy: 0.5395 - loss: 1.0955
[1m375/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 7ms/step - accuracy: 0.5398 - loss: 1.0950[32m [repeated 110x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m353/619[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 7ms/step - accuracy: 0.6483 - loss: 0.8017[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m110/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 13ms/step - accuracy: 0.6364 - loss: 0.8523
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 13ms/step - accuracy: 0.6363 - loss: 0.8524
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 13ms/step - accuracy: 0.6364 - loss: 0.8524
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m6s[0m 10ms/step - accuracy: 0.6005 - loss: 0.9496 - val_accuracy: 0.6422 - val_loss: 0.7158[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 13ms/step - accuracy: 0.6399 - loss: 0.8469
[1m240/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 13ms/step - accuracy: 0.6400 - loss: 0.8468[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m284/619[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m3s[0m 10ms/step - accuracy: 0.6484 - loss: 0.8306[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m Epoch 22/29[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m  9/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 7ms/step - accuracy: 0.6382 - loss: 0.8665  
[1m 16/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 7ms/step - accuracy: 0.6426 - loss: 0.8472
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 11ms/step - accuracy: 0.6505 - loss: 0.8156 - val_accuracy: 0.6745 - val_loss: 0.7085[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 284ms/step
[1m14/43[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step   
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m27/43[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 4ms/step
[1m40/43[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 26ms/step
[1m14/89[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step 
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 35ms/step - accuracy: 0.3750 - loss: 1.2645[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 50ms/step - accuracy: 0.5625 - loss: 0.8137
[1m  8/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 8ms/step - accuracy: 0.5957 - loss: 0.9500  
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m27/89[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step
[1m40/89[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m608/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.6458 - loss: 0.8222
[1m616/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.6458 - loss: 0.8221[32m [repeated 121x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m188/619[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m2s[0m 5ms/step - accuracy: 0.5820 - loss: 0.9879[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m53/89[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 4ms/step
[1m66/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=924611)[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=924611)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m78/89[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 4ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step

Trial trial_2414b finished iteration 1 at 2025-11-08 14:50:04. Total running time: 4min 55s
╭──────────────────────────────────────╮
│ Trial trial_2414b result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             292.219 │
│ time_total_s                 292.219 │
│ training_iteration                 1 │
│ val_accuracy                 0.66924 │
╰──────────────────────────────────────╯

Trial trial_2414b completed after 1 iterations at 2025-11-08 14:50:04. Total running time: 4min 55s
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 30ms/step - accuracy: 0.7500 - loss: 0.7366
[1m 13/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 4ms/step - accuracy: 0.5850 - loss: 0.9886  
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m4s[0m 6ms/step - accuracy: 0.5757 - loss: 1.0352 - val_accuracy: 0.6246 - val_loss: 0.7670[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m393/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m2s[0m 10ms/step - accuracy: 0.6467 - loss: 0.8268
[1m401/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m2s[0m 10ms/step - accuracy: 0.6466 - loss: 0.8266[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m417/619[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.6464 - loss: 0.8261 [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m Epoch 22/22[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m 12/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 5ms/step - accuracy: 0.6219 - loss: 0.7774  
[1m 23/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 5ms/step - accuracy: 0.6187 - loss: 0.7976[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924611)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m4s[0m 14ms/step - accuracy: 0.6415 - loss: 0.8457 - val_accuracy: 0.6692 - val_loss: 0.6872
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 30ms/step - accuracy: 0.4375 - loss: 1.1095
[1m 14/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 4ms/step - accuracy: 0.5388 - loss: 1.0901  
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 269ms/step
[1m20/43[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 3ms/step   
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 28ms/step - accuracy: 0.7500 - loss: 0.4214[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m40/43[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m109/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 4ms/step - accuracy: 0.5426 - loss: 1.0878
[1m121/619[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 4ms/step - accuracy: 0.5439 - loss: 1.0854[32m [repeated 139x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m581/619[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 5ms/step - accuracy: 0.6082 - loss: 0.8910[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/step
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 21ms/step
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m22/89[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step 
[1m44/89[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m66/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=924621)[0m 
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step

Trial trial_2414b finished iteration 1 at 2025-11-08 14:50:09. Total running time: 5min 0s
╭──────────────────────────────────────╮
│ Trial trial_2414b result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             297.985 │
│ time_total_s                 297.985 │
│ training_iteration                 1 │
│ val_accuracy                 0.67591 │
╰──────────────────────────────────────╯

Trial status: 16 TERMINATED | 4 RUNNING
Current time: 2025-11-08 14:50:09. Total running time: 5min 0s
Logical resource usage: 4.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
[36m(train_cnn_ray_tune pid=924621)[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=924621)[0m   _log_deprecation_warning(
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status         N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_2414b    RUNNING              3   rmsprop         relu                                   16                 16                  3                 0          1.74324e-05         22                                              │
│ trial_2414b    RUNNING              2   rmsprop         relu                                   16                 32                  5                 0          1.48377e-05         29                                              │
│ trial_2414b    RUNNING              3   adam            relu                                   16                 32                  3                 0          2.34799e-05         18        1            297.985         0.675913 │
│ trial_2414b    RUNNING              2   rmsprop         tanh                                   16                 32                  5                 1          5.1345e-06          28                                              │
│ trial_2414b    TERMINATED           2   adam            relu                                   32                 16                  5                 1          7.66658e-05         28        1            176.82          0.687851 │
│ trial_2414b    TERMINATED           2   adam            relu                                   16                 64                  3                 1          1.29147e-05         16        1            272.734         0.658708 │
│ trial_2414b    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 1          6.70381e-05         15        1            156.622         0.680478 │
│ trial_2414b    TERMINATED           2   rmsprop         tanh                                   32                 64                  3                 1          1.0258e-05          28        1            268.245         0.650281 │
│ trial_2414b    TERMINATED           2   adam            tanh                                   32                 32                  3                 1          0.000126055         15        1            156.701         0.662921 │
│ trial_2414b    TERMINATED           2   rmsprop         tanh                                   32                 32                  5                 1          7.10308e-06         26        1            244.016         0.625    │
│ trial_2414b    TERMINATED           2   adam            tanh                                   16                 64                  3                 0          9.84048e-05         22        1            253.532         0.672402 │
│ trial_2414b    TERMINATED           2   adam            relu                                   16                 32                  5                 0          8.43998e-05         27        1            195.412         0.647823 │
│ trial_2414b    TERMINATED           2   rmsprop         relu                                   32                 32                  3                 0          1.54606e-05         21        1            207.874         0.661517 │
│ trial_2414b    TERMINATED           3   adam            relu                                   32                 16                  3                 0          2.67621e-05         27        1            269.448         0.673455 │
│ trial_2414b    TERMINATED           3   adam            relu                                   32                 64                  5                 0          5.09414e-06         25        1            292.219         0.669242 │
│ trial_2414b    TERMINATED           2   adam            tanh                                   32                 32                  5                 0          2.32663e-05         22        1            226.576         0.650983 │
│ trial_2414b    TERMINATED           2   adam            relu                                   32                 64                  5                 1          7.77942e-05         27        1            152.58          0.701194 │
│ trial_2414b    TERMINATED           3   adam            relu                                   16                 32                  3                 1          8.65481e-05         26        1            283.986         0.688202 │
│ trial_2414b    TERMINATED           2   rmsprop         relu                                   32                 16                  3                 0          0.000111363         18        1            129.288         0.667486 │
│ trial_2414b    TERMINATED           2   adam            relu                                   16                 16                  3                 1          7.55321e-05         16        1            233.534         0.671348 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯

Trial trial_2414b completed after 1 iterations at 2025-11-08 14:50:09. Total running time: 5min 0s
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 256ms/step
[1m27/43[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step   
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 21ms/step
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m28/89[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step 

Trial trial_2414b finished iteration 1 at 2025-11-08 14:50:10. Total running time: 5min 1s
╭──────────────────────────────────────╮
│ Trial trial_2414b result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             298.463 │
│ time_total_s                 298.463 │
│ training_iteration                 1 │
│ val_accuracy                 0.64501 │
╰──────────────────────────────────────╯

Trial trial_2414b completed after 1 iterations at 2025-11-08 14:50:10. Total running time: 5min 1s
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m561/619[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 4ms/step - accuracy: 0.6484 - loss: 0.8039
[1m576/619[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 4ms/step - accuracy: 0.6485 - loss: 0.8042
[1m591/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 4ms/step - accuracy: 0.6485 - loss: 0.8045
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 5ms/step - accuracy: 0.6083 - loss: 0.8917 - val_accuracy: 0.6450 - val_loss: 0.7063[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 21ms/step - accuracy: 0.5000 - loss: 1.0571
[1m 18/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 3ms/step - accuracy: 0.6517 - loss: 0.8020  
[36m(train_cnn_ray_tune pid=924594)[0m Epoch 25/28[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m 17/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 3ms/step - accuracy: 0.6004 - loss: 0.9928  
[1m 34/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 3ms/step - accuracy: 0.5921 - loss: 1.0098[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 25ms/step - accuracy: 0.5000 - loss: 1.2298[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924585)[0m 
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m264/619[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 3ms/step - accuracy: 0.6337 - loss: 0.8158
[1m280/619[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 3ms/step - accuracy: 0.6344 - loss: 0.8146[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m248/619[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 3ms/step - accuracy: 0.6330 - loss: 0.8170[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 4ms/step - accuracy: 0.6439 - loss: 0.8041 - val_accuracy: 0.6819 - val_loss: 0.6670[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m 33/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 3ms/step - accuracy: 0.5875 - loss: 0.9964
[1m 49/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 3ms/step - accuracy: 0.5848 - loss: 1.0085
[1m 65/619[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 3ms/step - accuracy: 0.5837 - loss: 1.0140
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 25ms/step - accuracy: 0.5000 - loss: 1.0658
[1m 17/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 3ms/step - accuracy: 0.5811 - loss: 0.9895  
[36m(train_cnn_ray_tune pid=924594)[0m Epoch 27/28[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m 18/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 3ms/step - accuracy: 0.6599 - loss: 0.8231  
[1m 36/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 3ms/step - accuracy: 0.6537 - loss: 0.8376[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 22ms/step - accuracy: 0.5625 - loss: 0.9058
[1m 17/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 3ms/step - accuracy: 0.5802 - loss: 0.9791  
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 21ms/step - accuracy: 0.7500 - loss: 0.6126[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m374/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.6431 - loss: 0.8168
[1m390/619[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.6435 - loss: 0.8158[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m615/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 3ms/step - accuracy: 0.6630 - loss: 0.7879[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 4ms/step - accuracy: 0.5758 - loss: 1.0045 - val_accuracy: 0.6317 - val_loss: 0.7428[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=924594)[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=924594)[0m   _log_deprecation_warning([32m [repeated 2x across cluster][0m
2025-11-08 14:50:23,001	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_PI/case_PI_CAPTURE24_acc_superclasses_CPA_METs/CAPTURE24_hyperparameters_tuning' in 0.0059s.
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 167ms/step
[1m32/43[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step  
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 5ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 19ms/step
[1m33/89[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step 
[36m(train_cnn_ray_tune pid=924594)[0m 
[1m66/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step

Trial trial_2414b finished iteration 1 at 2025-11-08 14:50:21. Total running time: 5min 12s
╭──────────────────────────────────────╮
│ Trial trial_2414b result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             309.241 │
│ time_total_s                 309.241 │
│ training_iteration                 1 │
│ val_accuracy                 0.63167 │
╰──────────────────────────────────────╯

Trial trial_2414b completed after 1 iterations at 2025-11-08 14:50:21. Total running time: 5min 12s
[36m(train_cnn_ray_tune pid=924620)[0m Epoch 29/29[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m 18/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 3ms/step - accuracy: 0.6539 - loss: 0.7530  
[1m 35/619[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 3ms/step - accuracy: 0.6541 - loss: 0.7799[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 126ms/step
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m38/43[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step  
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m36/89[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m76/89[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step

Trial trial_2414b finished iteration 1 at 2025-11-08 14:50:22. Total running time: 5min 14s
╭──────────────────────────────────────╮
│ Trial trial_2414b result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             310.961 │
│ time_total_s                 310.961 │
│ training_iteration                 1 │
│ val_accuracy                 0.68574 │
╰──────────────────────────────────────╯

Trial trial_2414b completed after 1 iterations at 2025-11-08 14:50:22. Total running time: 5min 14s

Trial status: 20 TERMINATED
Current time: 2025-11-08 14:50:23. Total running time: 5min 14s
Logical resource usage: 1.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
I0000 00:00:1762609823.132350  922985 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_2414b    TERMINATED           2   adam            relu                                   32                 16                  5                 1          7.66658e-05         28        1            176.82          0.687851 │
│ trial_2414b    TERMINATED           2   adam            relu                                   16                 64                  3                 1          1.29147e-05         16        1            272.734         0.658708 │
│ trial_2414b    TERMINATED           3   rmsprop         relu                                   16                 16                  3                 0          1.74324e-05         22        1            298.463         0.645014 │
│ trial_2414b    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 1          6.70381e-05         15        1            156.622         0.680478 │
│ trial_2414b    TERMINATED           2   rmsprop         tanh                                   32                 64                  3                 1          1.0258e-05          28        1            268.245         0.650281 │
│ trial_2414b    TERMINATED           2   rmsprop         relu                                   16                 32                  5                 0          1.48377e-05         29        1            310.961         0.685744 │
│ trial_2414b    TERMINATED           2   adam            tanh                                   32                 32                  3                 1          0.000126055         15        1            156.701         0.662921 │
│ trial_2414b    TERMINATED           3   adam            relu                                   16                 32                  3                 0          2.34799e-05         18        1            297.985         0.675913 │
│ trial_2414b    TERMINATED           2   rmsprop         tanh                                   32                 32                  5                 1          7.10308e-06         26        1            244.016         0.625    │
│ trial_2414b    TERMINATED           2   adam            tanh                                   16                 64                  3                 0          9.84048e-05         22        1            253.532         0.672402 │
│ trial_2414b    TERMINATED           2   adam            relu                                   16                 32                  5                 0          8.43998e-05         27        1            195.412         0.647823 │
│ trial_2414b    TERMINATED           2   rmsprop         relu                                   32                 32                  3                 0          1.54606e-05         21        1            207.874         0.661517 │
│ trial_2414b    TERMINATED           3   adam            relu                                   32                 16                  3                 0          2.67621e-05         27        1            269.448         0.673455 │
│ trial_2414b    TERMINATED           3   adam            relu                                   32                 64                  5                 0          5.09414e-06         25        1            292.219         0.669242 │
│ trial_2414b    TERMINATED           2   adam            tanh                                   32                 32                  5                 0          2.32663e-05         22        1            226.576         0.650983 │
│ trial_2414b    TERMINATED           2   rmsprop         tanh                                   16                 32                  5                 1          5.1345e-06          28        1            309.241         0.631671 │
│ trial_2414b    TERMINATED           2   adam            relu                                   32                 64                  5                 1          7.77942e-05         27        1            152.58          0.701194 │
│ trial_2414b    TERMINATED           3   adam            relu                                   16                 32                  3                 1          8.65481e-05         26        1            283.986         0.688202 │
│ trial_2414b    TERMINATED           2   rmsprop         relu                                   32                 16                  3                 0          0.000111363         18        1            129.288         0.667486 │
│ trial_2414b    TERMINATED           2   adam            relu                                   16                 16                  3                 1          7.55321e-05         16        1            233.534         0.671348 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯

Mejores hiperparámetros: {'N_capas': 2, 'optimizador': 'adam', 'funcion_activacion': 'relu', 'tamanho_minilote': 32, 'numero_filtros': 64, 'tamanho_filtro': 5, 'num_resblocks': 1, 'tasa_aprendizaje': 7.779422372306605e-05, 'epochs': 27}
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762609825.691320  965923 service.cc:152] XLA service 0x7691c8029860 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762609825.691347  965923 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 14:50:25.742060: 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 00:00:1762609826.060550  965923 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762609828.479530  965923 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24:15[0m 5s/step - accuracy: 0.4062 - loss: 1.8311
[1m 25/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3758 - loss: 1.6186  
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4136 - loss: 1.5174
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4331 - loss: 1.4565
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4448 - loss: 1.4190
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4555 - loss: 1.3858
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4647 - loss: 1.3589
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4721 - loss: 1.3365
[1m236/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4791 - loss: 1.3157
[1m264/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4852 - loss: 1.2980
[1m295/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4913 - loss: 1.2805
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4939 - loss: 1.2729
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 14ms/step - accuracy: 0.4940 - loss: 1.2724 - val_accuracy: 0.6148 - val_loss: 0.8396
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.5938 - loss: 1.0957
[1m 32/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6158 - loss: 0.9687 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6156 - loss: 0.9534
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6145 - loss: 0.9474
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6129 - loss: 0.9458
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6122 - loss: 0.9457
[1m183/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6127 - loss: 0.9434
[1m214/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6136 - loss: 0.9403
[1m246/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6140 - loss: 0.9384
[1m274/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6145 - loss: 0.9367
[1m305/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6150 - loss: 0.9349
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6151 - loss: 0.9345 - val_accuracy: 0.6619 - val_loss: 0.7058
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6250 - loss: 0.8604
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6383 - loss: 0.8672 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6397 - loss: 0.8706
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6379 - loss: 0.8758
[1m123/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6378 - loss: 0.8767
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6393 - loss: 0.8728
[1m183/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6404 - loss: 0.8699
[1m209/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6413 - loss: 0.8670
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6420 - loss: 0.8638
[1m266/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6423 - loss: 0.8620
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6424 - loss: 0.8605
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6424 - loss: 0.8600 - val_accuracy: 0.6766 - val_loss: 0.6855
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.5625 - loss: 0.8059
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6400 - loss: 0.8036 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6532 - loss: 0.7873
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6573 - loss: 0.7838
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6586 - loss: 0.7839
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6593 - loss: 0.7828
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6595 - loss: 0.7825
[1m210/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6591 - loss: 0.7835
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6586 - loss: 0.7839
[1m273/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6585 - loss: 0.7843
[1m304/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6583 - loss: 0.7848
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6583 - loss: 0.7849 - val_accuracy: 0.6777 - val_loss: 0.6717
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6875 - loss: 0.7980
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6566 - loss: 0.7919 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6636 - loss: 0.7793
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6654 - loss: 0.7728
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6655 - loss: 0.7699
[1m146/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6657 - loss: 0.7673
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6662 - loss: 0.7647
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6664 - loss: 0.7627
[1m233/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6665 - loss: 0.7609
[1m265/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6665 - loss: 0.7596
[1m297/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6667 - loss: 0.7585
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6669 - loss: 0.7580 - val_accuracy: 0.6728 - val_loss: 0.6784
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6562 - loss: 0.7947
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6951 - loss: 0.7550 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6881 - loss: 0.7472
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6839 - loss: 0.7411
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6820 - loss: 0.7354
[1m142/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6819 - loss: 0.7323
[1m172/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6822 - loss: 0.7309
[1m203/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6821 - loss: 0.7306
[1m232/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6821 - loss: 0.7303
[1m262/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6822 - loss: 0.7296
[1m294/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6825 - loss: 0.7286
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6826 - loss: 0.7283 - val_accuracy: 0.6843 - val_loss: 0.6531
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6562 - loss: 0.5695
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6715 - loss: 0.7262 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6791 - loss: 0.7261
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6819 - loss: 0.7240
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6838 - loss: 0.7197
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6849 - loss: 0.7175
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6861 - loss: 0.7145
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6872 - loss: 0.7118
[1m234/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6880 - loss: 0.7095
[1m266/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6887 - loss: 0.7076
[1m295/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6892 - loss: 0.7063
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6894 - loss: 0.7059 - val_accuracy: 0.6777 - val_loss: 0.6662
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 23ms/step - accuracy: 0.7812 - loss: 0.5513
[1m 33/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7149 - loss: 0.6673 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7109 - loss: 0.6755
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7087 - loss: 0.6805
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7065 - loss: 0.6836
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7048 - loss: 0.6842
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7042 - loss: 0.6840
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7037 - loss: 0.6828
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7034 - loss: 0.6818
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7028 - loss: 0.6813
[1m297/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7025 - loss: 0.6812
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7024 - loss: 0.6811 - val_accuracy: 0.6829 - val_loss: 0.6672
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7188 - loss: 0.6432
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7506 - loss: 0.6050 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7379 - loss: 0.6302
[1m 94/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7304 - loss: 0.6412
[1m124/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7266 - loss: 0.6447
[1m156/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7237 - loss: 0.6474
[1m186/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7218 - loss: 0.6490
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7208 - loss: 0.6494
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7196 - loss: 0.6502
[1m270/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7186 - loss: 0.6507
[1m297/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7178 - loss: 0.6509
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7175 - loss: 0.6510 - val_accuracy: 0.6770 - val_loss: 0.6658
Epoch 10/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 29ms/step - accuracy: 0.8125 - loss: 0.4799
[1m 32/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7413 - loss: 0.6069 
[1m 64/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7382 - loss: 0.6125
[1m 96/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7347 - loss: 0.6202
[1m125/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7330 - loss: 0.6226
[1m156/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7311 - loss: 0.6247
[1m185/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7301 - loss: 0.6254
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7294 - loss: 0.6259
[1m243/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7288 - loss: 0.6259
[1m275/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7281 - loss: 0.6264
[1m306/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7275 - loss: 0.6276
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7274 - loss: 0.6278 - val_accuracy: 0.6777 - val_loss: 0.6694
Epoch 11/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.6250 - loss: 0.8127
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7169 - loss: 0.6496 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7234 - loss: 0.6346
[1m 92/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7256 - loss: 0.6286
[1m123/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7248 - loss: 0.6290
[1m154/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7240 - loss: 0.6294
[1m186/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7237 - loss: 0.6293
[1m217/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7233 - loss: 0.6298
[1m248/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7230 - loss: 0.6300
[1m278/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7228 - loss: 0.6301
[1m308/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7227 - loss: 0.6300
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7227 - loss: 0.6300 - val_accuracy: 0.6893 - val_loss: 0.6728

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 488ms/step2025-11-08 14:50:40.799744: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 24ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 25ms/step
Saved model to disk.
[36m(train_cnn_ray_tune pid=924620)[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=924620)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m  1/619[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 22ms/step - accuracy: 0.6250 - loss: 0.8186
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m574/619[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 3ms/step - accuracy: 0.6604 - loss: 0.7925
[1m594/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 3ms/step - accuracy: 0.6604 - loss: 0.7921[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m614/619[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 3ms/step - accuracy: 0.6604 - loss: 0.7917[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m619/619[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step - accuracy: 0.6604 - loss: 0.7916 - val_accuracy: 0.6857 - val_loss: 0.6645
[36m(train_cnn_ray_tune pid=924620)[0m 
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step[32m [repeated 2x across cluster][0m
2025-11-08 14:50:53.804251: 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`.
2025-11-08 14:50:53.815533: 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 00:00:1762609853.828562  967843 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762609853.832692  967843 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762609853.842475  967843 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762609853.842501  967843 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762609853.842503  967843 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762609853.842504  967843 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 14:50:53.845633: 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 00:00:1762609856.054388  967843 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762609858.530516  967966 service.cc:152] XLA service 0x7bd570015680 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762609858.530541  967966 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 14:50:58.579734: 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 00:00:1762609858.888305  967966 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762609861.228745  967966 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:22[0m 5s/step - accuracy: 0.3750 - loss: 1.6025
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2948 - loss: 1.8208  
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3376 - loss: 1.6966
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3645 - loss: 1.6170
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3844 - loss: 1.5632
[1m142/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4005 - loss: 1.5216
[1m173/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4154 - loss: 1.4833
[1m203/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4273 - loss: 1.4520
[1m234/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4376 - loss: 1.4244
[1m266/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4470 - loss: 1.3994
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4555 - loss: 1.3768
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4584 - loss: 1.3689
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 13ms/step - accuracy: 0.4587 - loss: 1.3683 - val_accuracy: 0.6387 - val_loss: 0.7528
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5625 - loss: 1.0185
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6289 - loss: 0.9270 
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6299 - loss: 0.9256
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6276 - loss: 0.9224
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6261 - loss: 0.9208
[1m145/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6257 - loss: 0.9206
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6255 - loss: 0.9204
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6253 - loss: 0.9207
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6251 - loss: 0.9208
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6250 - loss: 0.9206
[1m296/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6251 - loss: 0.9199
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6252 - loss: 0.9194 - val_accuracy: 0.6713 - val_loss: 0.6865
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6875 - loss: 0.7465
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6514 - loss: 0.8316 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6560 - loss: 0.8303
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6573 - loss: 0.8278
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6588 - loss: 0.8262
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6596 - loss: 0.8242
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6603 - loss: 0.8226
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6605 - loss: 0.8220
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6605 - loss: 0.8219
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6603 - loss: 0.8218
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6601 - loss: 0.8216
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6600 - loss: 0.8215 - val_accuracy: 0.6791 - val_loss: 0.6590
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6562 - loss: 0.7630
[1m 32/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6392 - loss: 0.8094 
[1m 64/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6408 - loss: 0.8107
[1m 96/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6446 - loss: 0.8156
[1m124/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6473 - loss: 0.8165
[1m157/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6497 - loss: 0.8145
[1m189/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6506 - loss: 0.8139
[1m220/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6511 - loss: 0.8134
[1m249/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6514 - loss: 0.8130
[1m279/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6519 - loss: 0.8116
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6524 - loss: 0.8101 - val_accuracy: 0.6879 - val_loss: 0.6536
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.8125 - loss: 0.5049
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6996 - loss: 0.6871 
[1m 63/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6928 - loss: 0.7080
[1m 96/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6865 - loss: 0.7238
[1m125/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6842 - loss: 0.7310
[1m155/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6838 - loss: 0.7332
[1m186/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6832 - loss: 0.7350
[1m214/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6827 - loss: 0.7365
[1m246/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6820 - loss: 0.7380
[1m277/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6817 - loss: 0.7391
[1m308/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6815 - loss: 0.7400
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6814 - loss: 0.7401 - val_accuracy: 0.6903 - val_loss: 0.6504
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.6250 - loss: 0.8828
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6883 - loss: 0.7420 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6858 - loss: 0.7423
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6842 - loss: 0.7413
[1m123/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6834 - loss: 0.7398
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6826 - loss: 0.7388
[1m182/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6822 - loss: 0.7376
[1m211/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6826 - loss: 0.7356
[1m241/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6834 - loss: 0.7335
[1m270/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6840 - loss: 0.7319
[1m303/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6847 - loss: 0.7303
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6849 - loss: 0.7300 - val_accuracy: 0.6938 - val_loss: 0.6564
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6562 - loss: 0.8785
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7080 - loss: 0.6918 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7062 - loss: 0.6929
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7033 - loss: 0.6953
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7014 - loss: 0.6962
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6996 - loss: 0.6983
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6989 - loss: 0.6975
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6984 - loss: 0.6967
[1m234/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6978 - loss: 0.6965
[1m262/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6972 - loss: 0.6963
[1m291/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6967 - loss: 0.6964
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6965 - loss: 0.6966 - val_accuracy: 0.6879 - val_loss: 0.6539
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6562 - loss: 0.7079
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7055 - loss: 0.6510 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7111 - loss: 0.6488
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7134 - loss: 0.6464
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7147 - loss: 0.6475
[1m143/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7147 - loss: 0.6501
[1m172/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7142 - loss: 0.6527
[1m201/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7137 - loss: 0.6553
[1m230/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7131 - loss: 0.6572
[1m260/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7124 - loss: 0.6588
[1m291/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7117 - loss: 0.6606
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7114 - loss: 0.6615 - val_accuracy: 0.6829 - val_loss: 0.6678
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.7812 - loss: 0.4129
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7264 - loss: 0.6377 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7156 - loss: 0.6559
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7116 - loss: 0.6620
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7114 - loss: 0.6626
[1m146/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7114 - loss: 0.6626
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7113 - loss: 0.6622
[1m204/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7105 - loss: 0.6631
[1m233/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7097 - loss: 0.6639
[1m262/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7091 - loss: 0.6648
[1m292/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7087 - loss: 0.6653
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7085 - loss: 0.6653 - val_accuracy: 0.6921 - val_loss: 0.6609
Epoch 10/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.6250 - loss: 0.5572
[1m 34/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7026 - loss: 0.6646 
[1m 64/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7072 - loss: 0.6684
[1m 96/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7086 - loss: 0.6657
[1m128/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7099 - loss: 0.6632
[1m159/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7111 - loss: 0.6606
[1m189/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7121 - loss: 0.6592
[1m219/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7136 - loss: 0.6576
[1m249/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7147 - loss: 0.6567
[1m278/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7155 - loss: 0.6561
[1m307/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7163 - loss: 0.6554
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7164 - loss: 0.6553 - val_accuracy: 0.6949 - val_loss: 0.6693

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 495ms/step2025-11-08 14:51:12.823509: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 25ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 25ms/step
Saved model to disk.

=== EJECUCIÓN 1 ===

--- TRAIN (ejecución 1) ---

--- TEST (ejecución 1) ---
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:57[0m 1s/step
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 889us/step
[1m116/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 879us/step
[1m175/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 871us/step
[1m231/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 878us/step
[1m287/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 881us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 21ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 21ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m57/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 902us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 69.28 [%]
Global F1 score (validation) = 69.09 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[6.6019201e-01 2.7950832e-01 4.4215336e-02 1.6084410e-02]
 [4.7610727e-01 4.6326187e-01 3.6497962e-02 2.4132963e-02]
 [2.9252532e-01 3.2775152e-01 8.5203476e-02 2.9451963e-01]
 ...
 [2.6674289e-04 7.9188459e-05 1.3932671e-03 9.9826092e-01]
 [1.8410992e-03 6.5850449e-04 1.0489778e-02 9.8701060e-01]
 [3.3711758e-03 2.9871818e-03 9.7905308e-01 1.4588459e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 75.24 [%]
Global accuracy score (test) = 72.05 [%]
Global F1 score (train) = 74.98 [%]
Global F1 score (test) = 72.5 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.51      0.67      0.58       350
MODERATE-INTENSITY       0.50      0.37      0.43       350
         SEDENTARY       0.98      0.99      0.98       350
VIGOROUS-INTENSITY       0.95      0.87      0.91       299

          accuracy                           0.72      1349
         macro avg       0.73      0.73      0.72      1349
      weighted avg       0.73      0.72      0.72      1349


Accuracy capturado en la ejecución 1: 72.05 [%]
F1-score capturado en la ejecución 1: 72.5 [%]

=== EJECUCIÓN 2 ===

--- TRAIN (ejecución 2) ---

--- TEST (ejecución 2) ---
2025-11-08 14:51:23.823777: 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`.
2025-11-08 14:51:23.835055: 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 00:00:1762609883.848405  969763 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762609883.852552  969763 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762609883.862514  969763 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762609883.862530  969763 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762609883.862532  969763 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762609883.862533  969763 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 14:51:23.865664: 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 00:00:1762609886.057014  969763 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762609888.541538  969892 service.cc:152] XLA service 0x7d8cc0016ae0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762609888.541583  969892 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 14:51:28.595463: 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 00:00:1762609888.917023  969892 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762609891.293397  969892 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:44[0m 5s/step - accuracy: 0.3438 - loss: 1.6463
[1m 23/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 1.8104  
[1m 53/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3404 - loss: 1.7187
[1m 83/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3693 - loss: 1.6595
[1m110/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3872 - loss: 1.6180
[1m138/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4017 - loss: 1.5831
[1m167/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4145 - loss: 1.5502
[1m199/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4267 - loss: 1.5179
[1m229/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4369 - loss: 1.4910
[1m254/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4444 - loss: 1.4706
[1m284/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4527 - loss: 1.4477
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4592 - loss: 1.4298
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 14ms/step - accuracy: 0.4595 - loss: 1.4292 - val_accuracy: 0.6303 - val_loss: 0.8220
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6875 - loss: 0.7748
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6119 - loss: 0.9917 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6067 - loss: 0.9941
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6053 - loss: 0.9945
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6061 - loss: 0.9935
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6078 - loss: 0.9894
[1m173/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6091 - loss: 0.9863
[1m201/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6106 - loss: 0.9824
[1m234/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6118 - loss: 0.9787
[1m263/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6124 - loss: 0.9763
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6127 - loss: 0.9742
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6129 - loss: 0.9730 - val_accuracy: 0.6517 - val_loss: 0.7173
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.6875 - loss: 0.8472
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6540 - loss: 0.8478 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6418 - loss: 0.8654
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6393 - loss: 0.8685
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6391 - loss: 0.8720
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6394 - loss: 0.8724
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6393 - loss: 0.8732
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6391 - loss: 0.8739
[1m237/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6389 - loss: 0.8742
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6391 - loss: 0.8735
[1m297/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6391 - loss: 0.8729
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6392 - loss: 0.8727 - val_accuracy: 0.6756 - val_loss: 0.6793
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.6875 - loss: 0.7762
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6738 - loss: 0.7590 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6723 - loss: 0.7706
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6720 - loss: 0.7783
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6709 - loss: 0.7830
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6701 - loss: 0.7861
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6695 - loss: 0.7891
[1m210/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6689 - loss: 0.7917
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6684 - loss: 0.7937
[1m266/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6681 - loss: 0.7948
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6677 - loss: 0.7961
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6675 - loss: 0.7966 - val_accuracy: 0.6882 - val_loss: 0.6451
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7188 - loss: 0.5390
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6810 - loss: 0.7165 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6813 - loss: 0.7319
[1m 94/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6803 - loss: 0.7446
[1m125/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6796 - loss: 0.7493
[1m157/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6786 - loss: 0.7533
[1m186/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6781 - loss: 0.7556
[1m218/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6775 - loss: 0.7572
[1m245/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6768 - loss: 0.7586
[1m274/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6758 - loss: 0.7602
[1m305/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6748 - loss: 0.7618
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6746 - loss: 0.7621 - val_accuracy: 0.6791 - val_loss: 0.6533
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7188 - loss: 0.6104
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7017 - loss: 0.7307 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6912 - loss: 0.7397
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6862 - loss: 0.7406
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6856 - loss: 0.7389
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6859 - loss: 0.7372
[1m185/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6857 - loss: 0.7365
[1m216/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6850 - loss: 0.7366
[1m248/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6844 - loss: 0.7368
[1m277/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6836 - loss: 0.7373
[1m307/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6829 - loss: 0.7380
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6828 - loss: 0.7381 - val_accuracy: 0.6903 - val_loss: 0.6331
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7188 - loss: 0.6823
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6918 - loss: 0.6955 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6938 - loss: 0.6956
[1m 92/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6945 - loss: 0.7029
[1m123/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6930 - loss: 0.7089
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6911 - loss: 0.7127
[1m184/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6894 - loss: 0.7163
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6888 - loss: 0.7182
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6885 - loss: 0.7185
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6882 - loss: 0.7188
[1m299/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6878 - loss: 0.7194
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6877 - loss: 0.7197 - val_accuracy: 0.6889 - val_loss: 0.6339
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.7188 - loss: 0.6759
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7091 - loss: 0.6798 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6949 - loss: 0.7016
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6914 - loss: 0.7038
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6911 - loss: 0.7026
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6912 - loss: 0.7022
[1m175/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6913 - loss: 0.7022
[1m204/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6916 - loss: 0.7016
[1m232/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6919 - loss: 0.7009
[1m261/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6920 - loss: 0.7006
[1m292/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6920 - loss: 0.7005
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6920 - loss: 0.7005 - val_accuracy: 0.6896 - val_loss: 0.6296
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.7188 - loss: 0.6211
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6814 - loss: 0.7237 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6811 - loss: 0.7210
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6836 - loss: 0.7136
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6855 - loss: 0.7093
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6869 - loss: 0.7070
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6873 - loss: 0.7049
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6875 - loss: 0.7032
[1m236/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6881 - loss: 0.7014
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6888 - loss: 0.6995
[1m296/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6895 - loss: 0.6977
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6899 - loss: 0.6969 - val_accuracy: 0.6998 - val_loss: 0.6349
Epoch 10/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 23ms/step - accuracy: 0.7500 - loss: 0.5462
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7057 - loss: 0.6558 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6993 - loss: 0.6710
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6966 - loss: 0.6751
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6959 - loss: 0.6771
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6956 - loss: 0.6775
[1m183/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6962 - loss: 0.6763
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6970 - loss: 0.6749
[1m244/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6976 - loss: 0.6735
[1m275/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6982 - loss: 0.6723
[1m306/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6988 - loss: 0.6715
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6989 - loss: 0.6714 - val_accuracy: 0.6773 - val_loss: 0.6546
Epoch 11/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5938 - loss: 0.7012
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7020 - loss: 0.6493 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7069 - loss: 0.6486
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7078 - loss: 0.6504
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7080 - loss: 0.6512
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7075 - loss: 0.6529
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7070 - loss: 0.6545
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7070 - loss: 0.6548
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7074 - loss: 0.6545
[1m266/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7078 - loss: 0.6540
[1m296/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7082 - loss: 0.6536
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7084 - loss: 0.6534 - val_accuracy: 0.7012 - val_loss: 0.6313
Epoch 12/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6875 - loss: 0.6808
[1m 32/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7326 - loss: 0.6247 
[1m 64/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7307 - loss: 0.6243
[1m 95/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7301 - loss: 0.6223
[1m128/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7293 - loss: 0.6232
[1m159/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7280 - loss: 0.6257
[1m189/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7268 - loss: 0.6278
[1m220/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7261 - loss: 0.6294
[1m251/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7259 - loss: 0.6305
[1m282/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7258 - loss: 0.6311
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7256 - loss: 0.6315 - val_accuracy: 0.7029 - val_loss: 0.6389
Epoch 13/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7188 - loss: 0.5280
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7362 - loss: 0.5918 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7334 - loss: 0.6055
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7289 - loss: 0.6151
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7275 - loss: 0.6191
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7276 - loss: 0.6203
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7275 - loss: 0.6214
[1m210/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7276 - loss: 0.6224
[1m234/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7275 - loss: 0.6227
[1m264/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7274 - loss: 0.6228
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7275 - loss: 0.6226
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7275 - loss: 0.6226 - val_accuracy: 0.7124 - val_loss: 0.6205
Epoch 14/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7188 - loss: 0.7202
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7520 - loss: 0.5810 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7485 - loss: 0.5974
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7435 - loss: 0.6050
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7420 - loss: 0.6073
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7413 - loss: 0.6077
[1m183/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7406 - loss: 0.6086
[1m215/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7399 - loss: 0.6090
[1m246/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7393 - loss: 0.6093
[1m273/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7389 - loss: 0.6092
[1m303/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7386 - loss: 0.6089
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7385 - loss: 0.6089 - val_accuracy: 0.6970 - val_loss: 0.6383
Epoch 15/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6875 - loss: 0.7238
[1m 25/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7310 - loss: 0.6066 
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7446 - loss: 0.5760
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7471 - loss: 0.5745
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7494 - loss: 0.5717
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7495 - loss: 0.5724
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7488 - loss: 0.5749
[1m203/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7485 - loss: 0.5763
[1m231/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7482 - loss: 0.5776
[1m263/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7479 - loss: 0.5789
[1m290/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7475 - loss: 0.5801
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7473 - loss: 0.5808 - val_accuracy: 0.7068 - val_loss: 0.6407
Epoch 16/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7812 - loss: 0.4795
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7733 - loss: 0.4917 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7682 - loss: 0.5215
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7659 - loss: 0.5320
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7629 - loss: 0.5398
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7614 - loss: 0.5453
[1m184/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7601 - loss: 0.5489
[1m218/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7591 - loss: 0.5514
[1m248/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7585 - loss: 0.5531
[1m276/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7580 - loss: 0.5543
[1m305/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7573 - loss: 0.5556
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7572 - loss: 0.5558 - val_accuracy: 0.6956 - val_loss: 0.6723
Epoch 17/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6875 - loss: 0.6073
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7330 - loss: 0.5786 
[1m 63/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7457 - loss: 0.5657
[1m 96/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7503 - loss: 0.5669
[1m126/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7524 - loss: 0.5674
[1m158/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7540 - loss: 0.5669
[1m186/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7548 - loss: 0.5671
[1m216/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7550 - loss: 0.5676
[1m246/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7549 - loss: 0.5682
[1m276/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7547 - loss: 0.5690
[1m305/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7545 - loss: 0.5694
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7544 - loss: 0.5695 - val_accuracy: 0.6984 - val_loss: 0.6543
Epoch 18/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.8125 - loss: 0.6555
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7823 - loss: 0.5366 
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7779 - loss: 0.5329
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7762 - loss: 0.5357
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7739 - loss: 0.5396
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7713 - loss: 0.5436
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7694 - loss: 0.5467
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7681 - loss: 0.5488
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7674 - loss: 0.5501
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7669 - loss: 0.5512
[1m296/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7666 - loss: 0.5521
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7663 - loss: 0.5524 - val_accuracy: 0.7114 - val_loss: 0.6646

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 484ms/step2025-11-08 14:51:48.539633: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 24ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 24ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:39[0m 1s/step
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 883us/step
[1m112/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 908us/step
[1m171/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 889us/step
[1m227/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 892us/step
[1m286/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 888us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 21ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 22ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m57/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 905us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 69.49 [%]
Global F1 score (validation) = 70.46 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[3.2357728e-01 5.8840537e-01 2.4691500e-02 6.3325867e-02]
 [6.6515261e-01 2.8629798e-01 3.3354707e-02 1.5194699e-02]
 [6.4896405e-01 3.0535841e-01 3.0440766e-02 1.5236736e-02]
 ...
 [5.0660834e-04 2.3772438e-04 4.1418318e-03 9.9511385e-01]
 [7.1413297e-04 2.4259456e-04 2.0013691e-03 9.9704188e-01]
 [4.7731497e-03 3.5469546e-03 8.5061836e-01 1.4106148e-01]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 75.01 [%]
Global accuracy score (test) = 73.61 [%]
Global F1 score (train) = 75.33 [%]
Global F1 score (test) = 74.57 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.57      0.59      0.58       350
MODERATE-INTENSITY       0.53      0.56      0.54       350
         SEDENTARY       0.98      0.97      0.97       350
VIGOROUS-INTENSITY       0.94      0.85      0.89       299

          accuracy                           0.74      1349
         macro avg       0.75      0.74      0.75      1349
      weighted avg       0.75      0.74      0.74      1349


Accuracy capturado en la ejecución 2: 73.61 [%]
F1-score capturado en la ejecución 2: 74.57 [%]

=== EJECUCIÓN 3 ===

--- TRAIN (ejecución 3) ---

--- TEST (ejecución 3) ---
2025-11-08 14:51:59.389645: 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`.
2025-11-08 14:51:59.401519: 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 00:00:1762609919.415415  972461 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762609919.419788  972461 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762609919.430174  972461 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762609919.430190  972461 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762609919.430192  972461 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762609919.430193  972461 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 14:51:59.433405: 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 00:00:1762609921.653419  972461 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762609924.106382  972592 service.cc:152] XLA service 0x7af5d0012ff0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762609924.106432  972592 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 14:52:04.162104: 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 00:00:1762609924.510536  972592 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762609926.846086  972592 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:29[0m 5s/step - accuracy: 0.2812 - loss: 2.0482
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2593 - loss: 1.9910  
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3018 - loss: 1.8581
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3335 - loss: 1.7646
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3555 - loss: 1.7003
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3731 - loss: 1.6480
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3879 - loss: 1.6038
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4009 - loss: 1.5655
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4127 - loss: 1.5309
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4225 - loss: 1.5023
[1m295/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4308 - loss: 1.4779
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4348 - loss: 1.4659
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 14ms/step - accuracy: 0.4351 - loss: 1.4651 - val_accuracy: 0.6520 - val_loss: 0.7573
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7500 - loss: 0.5980
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6335 - loss: 0.8743 
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6220 - loss: 0.9037
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6159 - loss: 0.9226
[1m110/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6126 - loss: 0.9338
[1m142/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6113 - loss: 0.9390
[1m173/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6111 - loss: 0.9406
[1m204/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6112 - loss: 0.9415
[1m234/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6114 - loss: 0.9418
[1m266/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6116 - loss: 0.9414
[1m295/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6117 - loss: 0.9409
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6118 - loss: 0.9405 - val_accuracy: 0.6826 - val_loss: 0.6809
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.6250 - loss: 0.7856
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6538 - loss: 0.8227 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6503 - loss: 0.8360
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6479 - loss: 0.8423
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6469 - loss: 0.8415
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6461 - loss: 0.8409
[1m184/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6448 - loss: 0.8431
[1m216/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6435 - loss: 0.8452
[1m243/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6428 - loss: 0.8464
[1m273/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6422 - loss: 0.8474
[1m301/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6417 - loss: 0.8480
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6416 - loss: 0.8483 - val_accuracy: 0.6777 - val_loss: 0.6757
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6250 - loss: 0.8458
[1m 32/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6196 - loss: 0.9148 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6350 - loss: 0.8758
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6444 - loss: 0.8513
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6492 - loss: 0.8371
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6514 - loss: 0.8306
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6528 - loss: 0.8274
[1m210/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6531 - loss: 0.8263
[1m240/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6529 - loss: 0.8253
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6527 - loss: 0.8245
[1m301/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6526 - loss: 0.8238
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6526 - loss: 0.8236 - val_accuracy: 0.6801 - val_loss: 0.6589
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5938 - loss: 1.0689
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6708 - loss: 0.8127 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6704 - loss: 0.7902
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6663 - loss: 0.7873
[1m116/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6638 - loss: 0.7881
[1m143/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6629 - loss: 0.7872
[1m173/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6615 - loss: 0.7868
[1m203/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6607 - loss: 0.7866
[1m234/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6602 - loss: 0.7860
[1m258/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6599 - loss: 0.7854
[1m287/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6595 - loss: 0.7849
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6593 - loss: 0.7846 - val_accuracy: 0.6871 - val_loss: 0.6554
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6562 - loss: 0.7265
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6921 - loss: 0.7039 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6919 - loss: 0.7111
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6915 - loss: 0.7137
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6892 - loss: 0.7187
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6876 - loss: 0.7201
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6860 - loss: 0.7219
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6843 - loss: 0.7246
[1m237/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6829 - loss: 0.7272
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6818 - loss: 0.7295
[1m297/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6811 - loss: 0.7309
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6809 - loss: 0.7314 - val_accuracy: 0.6900 - val_loss: 0.6497
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7188 - loss: 0.4565
[1m 25/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6743 - loss: 0.7148 
[1m 52/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6700 - loss: 0.7377
[1m 83/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6674 - loss: 0.7461
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6685 - loss: 0.7466
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6701 - loss: 0.7442
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6721 - loss: 0.7412
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6733 - loss: 0.7402
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6745 - loss: 0.7388
[1m265/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6756 - loss: 0.7371
[1m295/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6766 - loss: 0.7356
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6770 - loss: 0.7351 - val_accuracy: 0.6931 - val_loss: 0.6515
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.5938 - loss: 0.6696
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7105 - loss: 0.6570 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7080 - loss: 0.6670
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7049 - loss: 0.6742
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7013 - loss: 0.6788
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6997 - loss: 0.6812
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6987 - loss: 0.6837
[1m209/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6981 - loss: 0.6857
[1m240/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6977 - loss: 0.6865
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6973 - loss: 0.6876
[1m300/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6972 - loss: 0.6881
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6972 - loss: 0.6883 - val_accuracy: 0.6942 - val_loss: 0.6505
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6250 - loss: 0.7789
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6682 - loss: 0.7134 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6782 - loss: 0.6927
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6841 - loss: 0.6850
[1m116/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6877 - loss: 0.6825
[1m145/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6920 - loss: 0.6798
[1m175/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6949 - loss: 0.6789
[1m200/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6966 - loss: 0.6785
[1m229/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6980 - loss: 0.6781
[1m256/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6990 - loss: 0.6782
[1m286/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6996 - loss: 0.6786
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6998 - loss: 0.6790 - val_accuracy: 0.6833 - val_loss: 0.6663
Epoch 10/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6875 - loss: 0.5607
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7055 - loss: 0.6427 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7113 - loss: 0.6438
[1m 92/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7110 - loss: 0.6469
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7117 - loss: 0.6465
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7098 - loss: 0.6496
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7083 - loss: 0.6518
[1m209/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7076 - loss: 0.6529
[1m241/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7071 - loss: 0.6538
[1m273/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7068 - loss: 0.6544
[1m304/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7064 - loss: 0.6553
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7063 - loss: 0.6555 - val_accuracy: 0.7012 - val_loss: 0.6551
Epoch 11/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.8125 - loss: 0.3313
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7393 - loss: 0.5967 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7377 - loss: 0.5957
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7335 - loss: 0.6008
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7312 - loss: 0.6031
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7285 - loss: 0.6067
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7264 - loss: 0.6098
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7245 - loss: 0.6131
[1m233/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7232 - loss: 0.6157
[1m263/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7218 - loss: 0.6187
[1m294/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7209 - loss: 0.6212
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7205 - loss: 0.6223 - val_accuracy: 0.6998 - val_loss: 0.6601

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 492ms/step2025-11-08 14:52:19.230882: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 24ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 25ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:54[0m 1s/step
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 835us/step
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 832us/step
[1m182/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 834us/step
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 852us/step
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 850us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 21ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 21ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m62/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 841us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 69.84 [%]
Global F1 score (validation) = 70.88 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[5.86401582e-01 3.75309438e-01 2.72966679e-02 1.09923715e-02]
 [5.64194739e-01 4.00569350e-01 2.16100197e-02 1.36258062e-02]
 [3.78693581e-01 5.92143834e-01 2.02379078e-02 8.92462116e-03]
 ...
 [1.64322718e-03 1.24096090e-03 6.41303509e-03 9.90702748e-01]
 [3.36990634e-04 1.74032379e-04 2.51918170e-03 9.96969819e-01]
 [4.04118514e-03 4.24088771e-03 9.65396047e-01 2.63219457e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 77.39 [%]
Global accuracy score (test) = 74.72 [%]
Global F1 score (train) = 77.69 [%]
Global F1 score (test) = 75.57 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.59      0.59      0.59       350
MODERATE-INTENSITY       0.55      0.61      0.58       350
         SEDENTARY       0.98      0.99      0.98       350
VIGOROUS-INTENSITY       0.94      0.81      0.87       299

          accuracy                           0.75      1349
         macro avg       0.77      0.75      0.76      1349
      weighted avg       0.76      0.75      0.75      1349


Accuracy capturado en la ejecución 3: 74.72 [%]
F1-score capturado en la ejecución 3: 75.57 [%]

=== EJECUCIÓN 4 ===

--- TRAIN (ejecución 4) ---

--- TEST (ejecución 4) ---
2025-11-08 14:52:30.179009: 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`.
2025-11-08 14:52:30.190198: 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 00:00:1762609950.203336  974501 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762609950.207282  974501 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762609950.217262  974501 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762609950.217278  974501 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762609950.217280  974501 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762609950.217281  974501 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 14:52:30.220251: 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 00:00:1762609952.401262  974501 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762609954.861370  974611 service.cc:152] XLA service 0x73174c004130 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762609954.861406  974611 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 14:52:34.912253: 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 00:00:1762609955.221825  974611 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762609957.544994  974611 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:14[0m 5s/step - accuracy: 0.1250 - loss: 2.1379
[1m 24/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3048 - loss: 1.7621  
[1m 53/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3626 - loss: 1.6281
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3963 - loss: 1.5503
[1m116/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4209 - loss: 1.4930
[1m146/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4384 - loss: 1.4501
[1m172/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4505 - loss: 1.4195
[1m201/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4618 - loss: 1.3908
[1m233/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4719 - loss: 1.3646
[1m263/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4800 - loss: 1.3433
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4870 - loss: 1.3248
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4906 - loss: 1.3149
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 13ms/step - accuracy: 0.4908 - loss: 1.3144 - val_accuracy: 0.6478 - val_loss: 0.7654
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6562 - loss: 0.8142
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5913 - loss: 0.9710 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6042 - loss: 0.9605
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6084 - loss: 0.9528
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6113 - loss: 0.9467
[1m154/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6134 - loss: 0.9415
[1m185/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6151 - loss: 0.9382
[1m216/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6165 - loss: 0.9357
[1m247/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6175 - loss: 0.9337
[1m280/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6184 - loss: 0.9316
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6193 - loss: 0.9291
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6193 - loss: 0.9290 - val_accuracy: 0.6534 - val_loss: 0.7077
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.6875 - loss: 0.8314
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6295 - loss: 0.8539 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6406 - loss: 0.8491
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6426 - loss: 0.8487
[1m123/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6430 - loss: 0.8478
[1m154/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6434 - loss: 0.8459
[1m184/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6437 - loss: 0.8455
[1m210/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6441 - loss: 0.8450
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6445 - loss: 0.8445
[1m272/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6449 - loss: 0.8438
[1m299/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6451 - loss: 0.8431
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6452 - loss: 0.8428 - val_accuracy: 0.6735 - val_loss: 0.6897
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.4688 - loss: 0.9355
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6312 - loss: 0.8328 
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6462 - loss: 0.8046
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6497 - loss: 0.7954
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6515 - loss: 0.7925
[1m145/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6526 - loss: 0.7910
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6533 - loss: 0.7894
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6540 - loss: 0.7880
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6546 - loss: 0.7867
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6551 - loss: 0.7858
[1m301/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6556 - loss: 0.7851
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6557 - loss: 0.7848 - val_accuracy: 0.6900 - val_loss: 0.6665
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6562 - loss: 0.8335
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6761 - loss: 0.7399 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6748 - loss: 0.7441
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6729 - loss: 0.7531
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6705 - loss: 0.7584
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6699 - loss: 0.7586
[1m175/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6699 - loss: 0.7572
[1m204/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6702 - loss: 0.7559
[1m232/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6704 - loss: 0.7553
[1m263/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6706 - loss: 0.7548
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6706 - loss: 0.7547
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6706 - loss: 0.7545 - val_accuracy: 0.6706 - val_loss: 0.6719
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6562 - loss: 1.0307
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6964 - loss: 0.7309 
[1m 54/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6868 - loss: 0.7350
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6813 - loss: 0.7426
[1m111/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6799 - loss: 0.7460
[1m140/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6789 - loss: 0.7475
[1m170/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6785 - loss: 0.7479
[1m200/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6783 - loss: 0.7471
[1m230/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6780 - loss: 0.7465
[1m261/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6776 - loss: 0.7463
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6777 - loss: 0.7454
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6777 - loss: 0.7448 - val_accuracy: 0.6752 - val_loss: 0.6774
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7188 - loss: 0.8769
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7126 - loss: 0.6806 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7036 - loss: 0.6873
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6976 - loss: 0.6911
[1m112/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6951 - loss: 0.6929
[1m143/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6931 - loss: 0.6945
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6917 - loss: 0.6966
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6907 - loss: 0.6983
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6899 - loss: 0.6994
[1m264/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6892 - loss: 0.7002
[1m296/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6886 - loss: 0.7009
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6883 - loss: 0.7013 - val_accuracy: 0.6808 - val_loss: 0.6702
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.8438 - loss: 0.4310
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7513 - loss: 0.6180 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7323 - loss: 0.6436
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7222 - loss: 0.6545
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7165 - loss: 0.6613
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7121 - loss: 0.6666
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7087 - loss: 0.6702
[1m209/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7063 - loss: 0.6728
[1m239/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7047 - loss: 0.6747
[1m270/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7033 - loss: 0.6763
[1m299/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7023 - loss: 0.6775
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7019 - loss: 0.6780 - val_accuracy: 0.6879 - val_loss: 0.6625
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 23ms/step - accuracy: 0.6562 - loss: 0.8589
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6971 - loss: 0.7131 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6932 - loss: 0.7058
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6912 - loss: 0.7024
[1m123/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6918 - loss: 0.6982
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6927 - loss: 0.6943
[1m183/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6934 - loss: 0.6915
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6937 - loss: 0.6891
[1m243/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6938 - loss: 0.6871
[1m275/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6941 - loss: 0.6855
[1m300/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6941 - loss: 0.6851
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6941 - loss: 0.6850 - val_accuracy: 0.6864 - val_loss: 0.6646
Epoch 10/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6875 - loss: 0.6286
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6775 - loss: 0.6849 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6823 - loss: 0.6740
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6867 - loss: 0.6709
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6905 - loss: 0.6671
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6944 - loss: 0.6636
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6974 - loss: 0.6609
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6989 - loss: 0.6602
[1m236/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7002 - loss: 0.6592
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7014 - loss: 0.6582
[1m299/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7023 - loss: 0.6574
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7026 - loss: 0.6572 - val_accuracy: 0.6914 - val_loss: 0.6616
Epoch 11/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.8125 - loss: 0.5901
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7307 - loss: 0.6245 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7247 - loss: 0.6282
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7207 - loss: 0.6335
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7191 - loss: 0.6361
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7178 - loss: 0.6383
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7176 - loss: 0.6382
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7176 - loss: 0.6377
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7178 - loss: 0.6371
[1m264/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7179 - loss: 0.6366
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7182 - loss: 0.6360
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7184 - loss: 0.6358 - val_accuracy: 0.6924 - val_loss: 0.6542
Epoch 12/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6562 - loss: 0.7430
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7106 - loss: 0.7019 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7205 - loss: 0.6695
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7236 - loss: 0.6584
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7248 - loss: 0.6515
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7248 - loss: 0.6483
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7249 - loss: 0.6452
[1m211/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7252 - loss: 0.6417
[1m243/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7251 - loss: 0.6396
[1m272/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7251 - loss: 0.6378
[1m300/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7252 - loss: 0.6363
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7252 - loss: 0.6357 - val_accuracy: 0.6963 - val_loss: 0.6718
Epoch 13/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6562 - loss: 0.7738
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7199 - loss: 0.6335 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7250 - loss: 0.6364
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7250 - loss: 0.6393
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7272 - loss: 0.6367
[1m154/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7291 - loss: 0.6337
[1m183/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7299 - loss: 0.6319
[1m214/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7304 - loss: 0.6301
[1m244/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7309 - loss: 0.6285
[1m272/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7313 - loss: 0.6270
[1m301/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7315 - loss: 0.6258
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7316 - loss: 0.6254 - val_accuracy: 0.6864 - val_loss: 0.6777
Epoch 14/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7812 - loss: 0.6151
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7635 - loss: 0.5479 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7516 - loss: 0.5702
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7491 - loss: 0.5766
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7479 - loss: 0.5803
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7465 - loss: 0.5833
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7454 - loss: 0.5852
[1m211/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7447 - loss: 0.5869
[1m241/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7444 - loss: 0.5877
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7443 - loss: 0.5880
[1m302/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7441 - loss: 0.5886
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7440 - loss: 0.5888 - val_accuracy: 0.6942 - val_loss: 0.6801
Epoch 15/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6875 - loss: 0.5807
[1m 32/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7579 - loss: 0.5523 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7588 - loss: 0.5639
[1m 92/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7566 - loss: 0.5734
[1m123/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7542 - loss: 0.5794
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7532 - loss: 0.5817
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7526 - loss: 0.5825
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7522 - loss: 0.5827
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7519 - loss: 0.5828
[1m263/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7514 - loss: 0.5831
[1m295/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7509 - loss: 0.5834
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7508 - loss: 0.5834 - val_accuracy: 0.6914 - val_loss: 0.6987
Epoch 16/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7812 - loss: 0.7613
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7574 - loss: 0.6144 
[1m 53/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7567 - loss: 0.5943
[1m 82/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7563 - loss: 0.5868
[1m113/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7562 - loss: 0.5837
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7562 - loss: 0.5815
[1m172/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7566 - loss: 0.5797
[1m201/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7571 - loss: 0.5781
[1m230/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7575 - loss: 0.5767
[1m261/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7580 - loss: 0.5758
[1m289/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7584 - loss: 0.5752
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7586 - loss: 0.5748 - val_accuracy: 0.6935 - val_loss: 0.6903

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 493ms/step2025-11-08 14:52:53.398958: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 24ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 24ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7:04[0m 1s/step
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 919us/step
[1m113/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 900us/step
[1m173/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 879us/step
[1m231/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 876us/step
[1m288/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 878us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 20ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 21ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 21ms/step
[1m55/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 930us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 70.61 [%]
Global F1 score (validation) = 71.24 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[2.2490987e-01 7.4643791e-01 4.3625934e-03 2.4289630e-02]
 [5.8761096e-01 3.7833813e-01 2.2297788e-02 1.1753194e-02]
 [5.8486867e-01 3.4190714e-01 2.0190056e-02 5.3034090e-02]
 ...
 [1.0083041e-03 1.6437962e-03 4.4967677e-03 9.9285126e-01]
 [1.5093794e-04 3.0669596e-04 5.0768780e-04 9.9903470e-01]
 [7.8802211e-03 8.4199579e-03 8.5304129e-01 1.3065848e-01]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 74.41 [%]
Global accuracy score (test) = 73.24 [%]
Global F1 score (train) = 74.53 [%]
Global F1 score (test) = 73.99 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.55      0.62      0.58       350
MODERATE-INTENSITY       0.53      0.50      0.51       350
         SEDENTARY       0.98      0.99      0.98       350
VIGOROUS-INTENSITY       0.93      0.84      0.88       299

          accuracy                           0.73      1349
         macro avg       0.75      0.74      0.74      1349
      weighted avg       0.74      0.73      0.73      1349


Accuracy capturado en la ejecución 4: 73.24 [%]
F1-score capturado en la ejecución 4: 73.99 [%]

=== EJECUCIÓN 5 ===

--- TRAIN (ejecución 5) ---

--- TEST (ejecución 5) ---
2025-11-08 14:53:04.351873: 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`.
2025-11-08 14:53:04.363052: 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 00:00:1762609984.376097  976993 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762609984.380231  976993 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762609984.390318  976993 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762609984.390335  976993 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762609984.390336  976993 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762609984.390337  976993 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 14:53:04.393424: 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 00:00:1762609986.580047  976993 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762609989.010540  977125 service.cc:152] XLA service 0x7b69a8016830 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762609989.010564  977125 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 14:53:09.061011: 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 00:00:1762609989.383007  977125 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762609991.750613  977125 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:23[0m 5s/step - accuracy: 0.1250 - loss: 2.2296
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2823 - loss: 1.8213  
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3363 - loss: 1.6825
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3687 - loss: 1.6037
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3938 - loss: 1.5425
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4096 - loss: 1.5030
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4240 - loss: 1.4677
[1m210/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4370 - loss: 1.4360
[1m239/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4466 - loss: 1.4123
[1m272/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4560 - loss: 1.3879
[1m301/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4634 - loss: 1.3687
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4655 - loss: 1.3630
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 13ms/step - accuracy: 0.4657 - loss: 1.3624 - val_accuracy: 0.6587 - val_loss: 0.7468
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7188 - loss: 0.8117
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6171 - loss: 0.9694 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6157 - loss: 0.9668
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6125 - loss: 0.9648
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6119 - loss: 0.9596
[1m146/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6122 - loss: 0.9541
[1m175/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6124 - loss: 0.9500
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6131 - loss: 0.9455
[1m234/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6138 - loss: 0.9416
[1m264/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6143 - loss: 0.9383
[1m294/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6147 - loss: 0.9357
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6149 - loss: 0.9345 - val_accuracy: 0.6763 - val_loss: 0.6685
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5625 - loss: 1.0183
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6202 - loss: 0.8485 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6202 - loss: 0.8578
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6222 - loss: 0.8559
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6247 - loss: 0.8527
[1m145/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6268 - loss: 0.8511
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6289 - loss: 0.8490
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6308 - loss: 0.8468
[1m237/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6327 - loss: 0.8452
[1m264/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6339 - loss: 0.8441
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6351 - loss: 0.8430
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6357 - loss: 0.8422 - val_accuracy: 0.6850 - val_loss: 0.6422
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5625 - loss: 0.7701
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6616 - loss: 0.7865 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6591 - loss: 0.7965
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6582 - loss: 0.7973
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6578 - loss: 0.7977
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6575 - loss: 0.7973
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6575 - loss: 0.7962
[1m209/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6580 - loss: 0.7953
[1m236/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6586 - loss: 0.7943
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6591 - loss: 0.7931
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6596 - loss: 0.7920
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6598 - loss: 0.7914 - val_accuracy: 0.6847 - val_loss: 0.6485
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.6875 - loss: 0.9610
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6842 - loss: 0.7441 
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6824 - loss: 0.7369
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6801 - loss: 0.7400
[1m113/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6780 - loss: 0.7433
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6773 - loss: 0.7445
[1m172/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6772 - loss: 0.7450
[1m199/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6767 - loss: 0.7458
[1m227/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6764 - loss: 0.7463
[1m256/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6763 - loss: 0.7471
[1m286/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6761 - loss: 0.7479
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6760 - loss: 0.7483 - val_accuracy: 0.6847 - val_loss: 0.6453
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7500 - loss: 0.6047
[1m 25/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6891 - loss: 0.7179 
[1m 54/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6908 - loss: 0.7069
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6873 - loss: 0.7133
[1m113/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6854 - loss: 0.7183
[1m142/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6848 - loss: 0.7189
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6846 - loss: 0.7181
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6846 - loss: 0.7171
[1m233/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6846 - loss: 0.7163
[1m266/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6843 - loss: 0.7158
[1m296/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6840 - loss: 0.7159
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6839 - loss: 0.7160 - val_accuracy: 0.6822 - val_loss: 0.6442
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.7188 - loss: 0.8839
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7106 - loss: 0.7332 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7128 - loss: 0.7090
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7105 - loss: 0.7005
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7083 - loss: 0.6984
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7064 - loss: 0.6995
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7048 - loss: 0.7003
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7038 - loss: 0.7000
[1m244/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7029 - loss: 0.7000
[1m274/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7025 - loss: 0.6994
[1m305/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7022 - loss: 0.6986
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7021 - loss: 0.6985 - val_accuracy: 0.6875 - val_loss: 0.6408
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6250 - loss: 0.5945
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6809 - loss: 0.6809 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6814 - loss: 0.6933
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6826 - loss: 0.6929
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6840 - loss: 0.6905
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6858 - loss: 0.6878
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6871 - loss: 0.6856
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6881 - loss: 0.6841
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6890 - loss: 0.6833
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6897 - loss: 0.6825
[1m297/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6903 - loss: 0.6816
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6907 - loss: 0.6812 - val_accuracy: 0.6942 - val_loss: 0.6524
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7500 - loss: 0.5572
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7145 - loss: 0.6365 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7138 - loss: 0.6516
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7127 - loss: 0.6564
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7132 - loss: 0.6573
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7125 - loss: 0.6595
[1m186/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7117 - loss: 0.6615
[1m216/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7111 - loss: 0.6627
[1m247/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7107 - loss: 0.6634
[1m275/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7106 - loss: 0.6635
[1m307/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7104 - loss: 0.6637
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7104 - loss: 0.6637 - val_accuracy: 0.6843 - val_loss: 0.6590
Epoch 10/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.5938 - loss: 0.7663
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7008 - loss: 0.6853 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7065 - loss: 0.6754
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7084 - loss: 0.6682
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7094 - loss: 0.6642
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7104 - loss: 0.6622
[1m175/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7105 - loss: 0.6609
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7108 - loss: 0.6589
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7111 - loss: 0.6569
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7113 - loss: 0.6560
[1m297/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7114 - loss: 0.6556
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7114 - loss: 0.6555 - val_accuracy: 0.6886 - val_loss: 0.6685
Epoch 11/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6250 - loss: 0.7661
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7268 - loss: 0.5874 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7226 - loss: 0.5943
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7195 - loss: 0.6027
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7185 - loss: 0.6087
[1m143/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7190 - loss: 0.6122
[1m173/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7195 - loss: 0.6145
[1m200/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7196 - loss: 0.6165
[1m228/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7195 - loss: 0.6183
[1m259/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7193 - loss: 0.6202
[1m288/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7194 - loss: 0.6212
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7193 - loss: 0.6219 - val_accuracy: 0.6970 - val_loss: 0.6600
Epoch 12/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7812 - loss: 0.6324
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7498 - loss: 0.6019 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7424 - loss: 0.6033
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7411 - loss: 0.6035
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7395 - loss: 0.6060
[1m146/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7380 - loss: 0.6084
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7370 - loss: 0.6092
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7366 - loss: 0.6095
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7361 - loss: 0.6098
[1m266/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7356 - loss: 0.6105
[1m296/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7349 - loss: 0.6112
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7346 - loss: 0.6116 - val_accuracy: 0.6917 - val_loss: 0.6689

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 505ms/step2025-11-08 14:53:24.900886: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 25ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 25ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:48[0m 1s/step
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 950us/step
[1m112/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 914us/step
[1m172/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 888us/step
[1m228/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 891us/step
[1m287/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 883us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 23ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 23ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m53/89[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 968us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 70.01 [%]
Global F1 score (validation) = 71.16 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[6.4304388e-01 3.2925266e-01 1.9732248e-02 7.9712905e-03]
 [6.8506062e-01 2.8251350e-01 2.4174193e-02 8.2517173e-03]
 [5.0693381e-01 4.6723449e-01 1.4437164e-02 1.1394531e-02]
 ...
 [2.7025424e-04 4.3936619e-05 1.1409085e-03 9.9854487e-01]
 [5.0826874e-03 2.6718390e-03 6.1249011e-03 9.8612064e-01]
 [1.1766773e-02 1.0123578e-02 9.6397167e-01 1.4137907e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 77.28 [%]
Global accuracy score (test) = 71.98 [%]
Global F1 score (train) = 77.72 [%]
Global F1 score (test) = 73.28 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.53      0.63      0.58       350
MODERATE-INTENSITY       0.51      0.51      0.51       350
         SEDENTARY       0.98      0.95      0.96       350
VIGOROUS-INTENSITY       0.97      0.80      0.88       299

          accuracy                           0.72      1349
         macro avg       0.75      0.72      0.73      1349
      weighted avg       0.74      0.72      0.73      1349


Accuracy capturado en la ejecución 5: 71.98 [%]
F1-score capturado en la ejecución 5: 73.28 [%]

=== EJECUCIÓN 6 ===

--- TRAIN (ejecución 6) ---

--- TEST (ejecución 6) ---
2025-11-08 14:53:35.828444: 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`.
2025-11-08 14:53:35.839670: 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 00:00:1762610015.852741  979133 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762610015.856894  979133 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762610015.866910  979133 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610015.866929  979133 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610015.866930  979133 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610015.866931  979133 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 14:53:35.870058: 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 00:00:1762610018.065389  979133 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762610020.583169  979249 service.cc:152] XLA service 0x7e94e8008f10 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762610020.583200  979249 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 14:53:40.634503: 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 00:00:1762610020.957036  979249 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762610023.307217  979249 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:41[0m 5s/step - accuracy: 0.2812 - loss: 2.0726
[1m 25/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 1.7637  
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3389 - loss: 1.6556
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3655 - loss: 1.5810
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3847 - loss: 1.5270
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3995 - loss: 1.4870
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4135 - loss: 1.4488
[1m204/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4258 - loss: 1.4163
[1m236/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4369 - loss: 1.3871
[1m262/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4450 - loss: 1.3660
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4537 - loss: 1.3435
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4579 - loss: 1.3324
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 14ms/step - accuracy: 0.4582 - loss: 1.3317 - val_accuracy: 0.6376 - val_loss: 0.7268
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.5312 - loss: 1.0120
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6067 - loss: 0.9258 
[1m 54/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6137 - loss: 0.9137
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6150 - loss: 0.9132
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6159 - loss: 0.9128
[1m145/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6169 - loss: 0.9115
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6172 - loss: 0.9108
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6178 - loss: 0.9086
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6189 - loss: 0.9058
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6197 - loss: 0.9034
[1m301/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6204 - loss: 0.9012
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6205 - loss: 0.9005 - val_accuracy: 0.6903 - val_loss: 0.6413
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.4375 - loss: 1.2701
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6185 - loss: 0.8968 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6246 - loss: 0.8836
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6292 - loss: 0.8714
[1m116/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6311 - loss: 0.8639
[1m142/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6325 - loss: 0.8574
[1m170/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6335 - loss: 0.8525
[1m199/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6345 - loss: 0.8492
[1m230/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6357 - loss: 0.8466
[1m260/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6367 - loss: 0.8447
[1m290/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6378 - loss: 0.8429
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6386 - loss: 0.8417 - val_accuracy: 0.6868 - val_loss: 0.6428
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.4062 - loss: 1.5649
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6025 - loss: 0.8982 
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6284 - loss: 0.8409
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6356 - loss: 0.8290
[1m113/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6404 - loss: 0.8212
[1m142/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6432 - loss: 0.8172
[1m173/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6455 - loss: 0.8123
[1m204/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6472 - loss: 0.8093
[1m232/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6482 - loss: 0.8083
[1m261/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6493 - loss: 0.8067
[1m292/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6502 - loss: 0.8050
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6507 - loss: 0.8039 - val_accuracy: 0.6938 - val_loss: 0.6327
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6875 - loss: 0.8590
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6835 - loss: 0.7511 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6886 - loss: 0.7413
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6875 - loss: 0.7391
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6862 - loss: 0.7391
[1m145/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6850 - loss: 0.7393
[1m175/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6831 - loss: 0.7407
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6815 - loss: 0.7419
[1m232/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6806 - loss: 0.7428
[1m262/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6798 - loss: 0.7435
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6792 - loss: 0.7439
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6789 - loss: 0.7443 - val_accuracy: 0.6889 - val_loss: 0.6360
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.5312 - loss: 1.0145
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6446 - loss: 0.8093 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6438 - loss: 0.7975
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6480 - loss: 0.7872
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6508 - loss: 0.7808
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6537 - loss: 0.7753
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6560 - loss: 0.7707
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6582 - loss: 0.7659
[1m237/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6601 - loss: 0.7616
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6619 - loss: 0.7572
[1m294/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6633 - loss: 0.7539
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6641 - loss: 0.7520 - val_accuracy: 0.7005 - val_loss: 0.6289
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6250 - loss: 0.8763
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6770 - loss: 0.7398 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6850 - loss: 0.7169
[1m 92/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6874 - loss: 0.7103
[1m124/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6897 - loss: 0.7061
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6911 - loss: 0.7029
[1m185/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6916 - loss: 0.7016
[1m218/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6916 - loss: 0.7006
[1m249/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6916 - loss: 0.6996
[1m279/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6915 - loss: 0.6993
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6913 - loss: 0.6992 - val_accuracy: 0.7008 - val_loss: 0.6305
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6562 - loss: 0.7152
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6971 - loss: 0.6786 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6920 - loss: 0.6833
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6921 - loss: 0.6871
[1m116/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6931 - loss: 0.6877
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6943 - loss: 0.6875
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6947 - loss: 0.6880
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6950 - loss: 0.6879
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6952 - loss: 0.6881
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6955 - loss: 0.6878
[1m297/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6957 - loss: 0.6874
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6958 - loss: 0.6873 - val_accuracy: 0.7058 - val_loss: 0.6317
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7500 - loss: 0.6206
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6862 - loss: 0.7118 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6855 - loss: 0.7010
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6871 - loss: 0.6932
[1m116/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6891 - loss: 0.6886
[1m145/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6902 - loss: 0.6854
[1m173/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6912 - loss: 0.6829
[1m204/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6925 - loss: 0.6804
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6933 - loss: 0.6795
[1m262/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6939 - loss: 0.6787
[1m290/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6942 - loss: 0.6780
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6944 - loss: 0.6775 - val_accuracy: 0.7075 - val_loss: 0.6332
Epoch 10/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6562 - loss: 0.6575
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6962 - loss: 0.6841 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6991 - loss: 0.6934
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7004 - loss: 0.6892
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7013 - loss: 0.6849
[1m145/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7021 - loss: 0.6817
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7028 - loss: 0.6775
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7037 - loss: 0.6736
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7046 - loss: 0.6701
[1m263/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7051 - loss: 0.6681
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7057 - loss: 0.6657
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7061 - loss: 0.6643 - val_accuracy: 0.7051 - val_loss: 0.6300
Epoch 11/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.6875 - loss: 0.5204
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7337 - loss: 0.5865 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7296 - loss: 0.6066
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7288 - loss: 0.6150
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7284 - loss: 0.6186
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7280 - loss: 0.6204
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7280 - loss: 0.6216
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7280 - loss: 0.6229
[1m233/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7280 - loss: 0.6236
[1m260/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7278 - loss: 0.6241
[1m289/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7274 - loss: 0.6247
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7272 - loss: 0.6251 - val_accuracy: 0.7173 - val_loss: 0.6314

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 494ms/step2025-11-08 14:53:55.691416: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 24ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 24ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:46[0m 1s/step
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 932us/step
[1m107/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 952us/step
[1m165/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 921us/step
[1m223/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 908us/step
[1m276/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 917us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 21ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 22ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m54/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 949us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 68.71 [%]
Global F1 score (validation) = 68.58 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[2.8493896e-01 6.4104217e-01 5.3194533e-03 6.8699412e-02]
 [4.0744767e-01 5.2093416e-01 1.5065638e-02 5.6552462e-02]
 [6.9444406e-01 2.5687245e-01 2.8880499e-02 1.9802975e-02]
 ...
 [3.7225863e-04 5.1691080e-04 4.7728834e-03 9.9433798e-01]
 [1.9449618e-04 3.4132702e-04 1.0453331e-02 9.8901087e-01]
 [7.2791381e-03 5.7640383e-03 9.6970111e-01 1.7255701e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 75.67 [%]
Global accuracy score (test) = 72.2 [%]
Global F1 score (train) = 75.35 [%]
Global F1 score (test) = 72.55 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.52      0.71      0.60       350
MODERATE-INTENSITY       0.52      0.37      0.44       350
         SEDENTARY       0.98      0.99      0.98       350
VIGOROUS-INTENSITY       0.95      0.83      0.88       299

          accuracy                           0.72      1349
         macro avg       0.74      0.73      0.73      1349
      weighted avg       0.73      0.72      0.72      1349


Accuracy capturado en la ejecución 6: 72.2 [%]
F1-score capturado en la ejecución 6: 72.55 [%]

=== EJECUCIÓN 7 ===

--- TRAIN (ejecución 7) ---

--- TEST (ejecución 7) ---
2025-11-08 14:54:06.655592: 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`.
2025-11-08 14:54:06.666911: 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 00:00:1762610046.680159  981168 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762610046.684277  981168 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762610046.694001  981168 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610046.694016  981168 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610046.694018  981168 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610046.694019  981168 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 14:54:06.697140: 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 00:00:1762610048.910937  981168 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762610051.367890  981271 service.cc:152] XLA service 0x7aa6dc017340 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762610051.367937  981271 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 14:54:11.423072: 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 00:00:1762610051.731652  981271 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762610054.069750  981271 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:16[0m 5s/step - accuracy: 0.2188 - loss: 2.1766
[1m 23/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3100 - loss: 1.8250  
[1m 53/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3614 - loss: 1.6904
[1m 82/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3918 - loss: 1.6100
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4139 - loss: 1.5470
[1m143/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4290 - loss: 1.5023
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4417 - loss: 1.4638
[1m203/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4517 - loss: 1.4332
[1m234/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4609 - loss: 1.4048
[1m260/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4679 - loss: 1.3833
[1m289/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4747 - loss: 1.3619
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4793 - loss: 1.3479
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 14ms/step - accuracy: 0.4795 - loss: 1.3473 - val_accuracy: 0.6591 - val_loss: 0.7062
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.6562 - loss: 0.7896
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6401 - loss: 0.8716 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6335 - loss: 0.8874
[1m 92/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6285 - loss: 0.8970
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6260 - loss: 0.9039
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6234 - loss: 0.9092
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6218 - loss: 0.9122
[1m210/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6211 - loss: 0.9129
[1m239/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6208 - loss: 0.9128
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6206 - loss: 0.9121
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6207 - loss: 0.9107
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6209 - loss: 0.9100 - val_accuracy: 0.6745 - val_loss: 0.6593
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.8438 - loss: 0.5475
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6707 - loss: 0.8033 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6617 - loss: 0.8113
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6571 - loss: 0.8159
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6559 - loss: 0.8179
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6546 - loss: 0.8213
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6533 - loss: 0.8243
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6522 - loss: 0.8261
[1m234/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6516 - loss: 0.8267
[1m262/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6511 - loss: 0.8271
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6504 - loss: 0.8277
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6500 - loss: 0.8280 - val_accuracy: 0.6766 - val_loss: 0.6471
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6875 - loss: 0.6704
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6514 - loss: 0.7802 
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6538 - loss: 0.7869
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6512 - loss: 0.7918
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6481 - loss: 0.7984
[1m142/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6468 - loss: 0.8018
[1m173/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6458 - loss: 0.8039
[1m202/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6453 - loss: 0.8042
[1m231/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6453 - loss: 0.8038
[1m261/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6455 - loss: 0.8030
[1m291/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6460 - loss: 0.8018
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6464 - loss: 0.8009 - val_accuracy: 0.6854 - val_loss: 0.6426
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6250 - loss: 0.8267
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6588 - loss: 0.7539 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6670 - loss: 0.7488
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6662 - loss: 0.7496
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6645 - loss: 0.7510
[1m145/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6636 - loss: 0.7525
[1m175/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6636 - loss: 0.7531
[1m203/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6638 - loss: 0.7537
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6644 - loss: 0.7543
[1m265/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6647 - loss: 0.7548
[1m296/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6649 - loss: 0.7552
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6650 - loss: 0.7553 - val_accuracy: 0.6812 - val_loss: 0.6474
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.8438 - loss: 0.4223
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6873 - loss: 0.6957 
[1m 53/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6732 - loss: 0.7160
[1m 82/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6692 - loss: 0.7263
[1m112/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6678 - loss: 0.7321
[1m142/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6680 - loss: 0.7340
[1m166/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6680 - loss: 0.7347
[1m192/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6685 - loss: 0.7346
[1m218/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6687 - loss: 0.7346
[1m247/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6688 - loss: 0.7348
[1m276/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6689 - loss: 0.7355
[1m306/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6692 - loss: 0.7357
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6692 - loss: 0.7357 - val_accuracy: 0.6882 - val_loss: 0.6393
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6250 - loss: 1.0487
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6605 - loss: 0.7570 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6737 - loss: 0.7386
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6803 - loss: 0.7272
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6820 - loss: 0.7229
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6818 - loss: 0.7222
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6821 - loss: 0.7220
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6823 - loss: 0.7214
[1m237/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6825 - loss: 0.7203
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6827 - loss: 0.7194
[1m299/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6829 - loss: 0.7188
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6829 - loss: 0.7185 - val_accuracy: 0.6864 - val_loss: 0.6351
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6875 - loss: 0.6299
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6821 - loss: 0.6981 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6903 - loss: 0.6923
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6959 - loss: 0.6871
[1m123/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6972 - loss: 0.6855
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6966 - loss: 0.6871
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6959 - loss: 0.6887
[1m209/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6950 - loss: 0.6906
[1m240/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6941 - loss: 0.6928
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6936 - loss: 0.6939
[1m301/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6935 - loss: 0.6943
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6935 - loss: 0.6943 - val_accuracy: 0.6836 - val_loss: 0.6508
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 23ms/step - accuracy: 0.6875 - loss: 0.7195
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7000 - loss: 0.7082 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7008 - loss: 0.6991
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7005 - loss: 0.6942
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6996 - loss: 0.6934
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6994 - loss: 0.6920
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6993 - loss: 0.6911
[1m209/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6996 - loss: 0.6902
[1m241/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7000 - loss: 0.6892
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7002 - loss: 0.6880
[1m299/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7006 - loss: 0.6865
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7008 - loss: 0.6860 - val_accuracy: 0.6938 - val_loss: 0.6362
Epoch 10/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6562 - loss: 0.4413
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7232 - loss: 0.5797 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7154 - loss: 0.6133
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7145 - loss: 0.6236
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7121 - loss: 0.6315
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7100 - loss: 0.6362
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7089 - loss: 0.6401
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7084 - loss: 0.6429
[1m237/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7080 - loss: 0.6450
[1m264/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7078 - loss: 0.6464
[1m295/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7075 - loss: 0.6479
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7073 - loss: 0.6487 - val_accuracy: 0.6900 - val_loss: 0.6470
Epoch 11/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.6875 - loss: 0.8025
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7154 - loss: 0.6550 
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7126 - loss: 0.6451
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7106 - loss: 0.6405
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7101 - loss: 0.6407
[1m143/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7108 - loss: 0.6408
[1m173/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7111 - loss: 0.6417
[1m202/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7114 - loss: 0.6426
[1m231/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7119 - loss: 0.6426
[1m260/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7125 - loss: 0.6420
[1m291/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7131 - loss: 0.6415
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7134 - loss: 0.6414 - val_accuracy: 0.6896 - val_loss: 0.6585
Epoch 12/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.7188 - loss: 0.5481
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7394 - loss: 0.5733 
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7397 - loss: 0.5844
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7346 - loss: 0.5972
[1m112/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7312 - loss: 0.6045
[1m142/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7287 - loss: 0.6088
[1m170/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7266 - loss: 0.6126
[1m202/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7250 - loss: 0.6159
[1m231/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7243 - loss: 0.6178
[1m263/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7237 - loss: 0.6194
[1m292/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7234 - loss: 0.6203
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7232 - loss: 0.6208 - val_accuracy: 0.6938 - val_loss: 0.6562

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 504ms/step2025-11-08 14:54:27.288697: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 24ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 25ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:46[0m 1s/step
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 935us/step
[1m113/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 902us/step
[1m168/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 909us/step
[1m227/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 895us/step
[1m280/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 906us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 20ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 21ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 19ms/step
[1m55/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 938us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 71.88 [%]
Global F1 score (validation) = 72.78 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[5.71416140e-01 4.04891968e-01 1.26743130e-02 1.10176215e-02]
 [5.11496007e-01 4.61741090e-01 1.25590386e-02 1.42039144e-02]
 [4.79853451e-01 4.08038855e-01 1.96623933e-02 9.24452767e-02]
 ...
 [3.38530634e-04 4.85825643e-04 2.16433685e-03 9.97011185e-01]
 [6.15314420e-05 4.31532026e-05 4.89647617e-04 9.99405742e-01]
 [5.78290643e-03 6.37781387e-03 9.44403231e-01 4.34360765e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 74.64 [%]
Global accuracy score (test) = 72.72 [%]
Global F1 score (train) = 75.0 [%]
Global F1 score (test) = 73.63 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.55      0.47      0.51       350
MODERATE-INTENSITY       0.51      0.64      0.57       350
         SEDENTARY       0.98      0.99      0.98       350
VIGOROUS-INTENSITY       0.96      0.83      0.89       299

          accuracy                           0.73      1349
         macro avg       0.75      0.73      0.74      1349
      weighted avg       0.74      0.73      0.73      1349


Accuracy capturado en la ejecución 7: 72.72 [%]
F1-score capturado en la ejecución 7: 73.63 [%]

=== EJECUCIÓN 8 ===

--- TRAIN (ejecución 8) ---

--- TEST (ejecución 8) ---
2025-11-08 14:54:38.330813: 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`.
2025-11-08 14:54:38.342116: 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 00:00:1762610078.355469  983306 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762610078.359622  983306 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762610078.369717  983306 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610078.369737  983306 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610078.369739  983306 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610078.369740  983306 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 14:54:38.373098: 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 00:00:1762610080.589860  983306 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762610083.003379  983417 service.cc:152] XLA service 0x766814026400 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762610083.003432  983417 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 14:54:43.063071: 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 00:00:1762610083.371185  983417 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762610085.696196  983417 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:06[0m 4s/step - accuracy: 0.2188 - loss: 1.9316
[1m 24/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3184 - loss: 1.7116  
[1m 54/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3657 - loss: 1.5976
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3950 - loss: 1.5287
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4170 - loss: 1.4755
[1m146/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4328 - loss: 1.4363
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4473 - loss: 1.4001
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4589 - loss: 1.3708
[1m240/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4691 - loss: 1.3444
[1m270/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4773 - loss: 1.3228
[1m300/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4846 - loss: 1.3042
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4868 - loss: 1.2984
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 13ms/step - accuracy: 0.4870 - loss: 1.2978 - val_accuracy: 0.6752 - val_loss: 0.7045
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.4062 - loss: 1.2818
[1m 24/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6216 - loss: 0.9454 
[1m 53/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6238 - loss: 0.9366
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6206 - loss: 0.9401
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6195 - loss: 0.9402
[1m143/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6179 - loss: 0.9409
[1m175/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6165 - loss: 0.9414
[1m201/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6159 - loss: 0.9409
[1m233/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6152 - loss: 0.9400
[1m263/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6146 - loss: 0.9391
[1m292/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6145 - loss: 0.9376
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6147 - loss: 0.9364 - val_accuracy: 0.6703 - val_loss: 0.6641
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7188 - loss: 0.7680
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6402 - loss: 0.8932 
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6377 - loss: 0.8830
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6364 - loss: 0.8732
[1m113/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6335 - loss: 0.8703
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6327 - loss: 0.8677
[1m175/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6330 - loss: 0.8649
[1m204/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6337 - loss: 0.8620
[1m233/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6343 - loss: 0.8598
[1m263/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6350 - loss: 0.8580
[1m292/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6356 - loss: 0.8565
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6360 - loss: 0.8554 - val_accuracy: 0.6752 - val_loss: 0.6544
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5625 - loss: 0.9592
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6263 - loss: 0.8333 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6372 - loss: 0.8303
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6417 - loss: 0.8288
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6445 - loss: 0.8239
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6455 - loss: 0.8224
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6465 - loss: 0.8202
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6478 - loss: 0.8174
[1m237/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6485 - loss: 0.8159
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6492 - loss: 0.8142
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6497 - loss: 0.8129
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6500 - loss: 0.8123 - val_accuracy: 0.6766 - val_loss: 0.6488
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.5938 - loss: 1.0287
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6570 - loss: 0.8264 
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6565 - loss: 0.8181
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6538 - loss: 0.8156
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6531 - loss: 0.8112
[1m146/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6531 - loss: 0.8059
[1m173/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6538 - loss: 0.8022
[1m203/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6548 - loss: 0.7982
[1m232/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6559 - loss: 0.7943
[1m263/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6572 - loss: 0.7909
[1m292/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6583 - loss: 0.7878
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6590 - loss: 0.7859 - val_accuracy: 0.6854 - val_loss: 0.6423
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6562 - loss: 0.7353
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7004 - loss: 0.7013 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6984 - loss: 0.7087
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6917 - loss: 0.7170
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6885 - loss: 0.7224
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6854 - loss: 0.7273
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6838 - loss: 0.7304
[1m202/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6826 - loss: 0.7327
[1m229/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6817 - loss: 0.7341
[1m260/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6813 - loss: 0.7346
[1m287/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6810 - loss: 0.7351
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6806 - loss: 0.7356 - val_accuracy: 0.6780 - val_loss: 0.6418
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5000 - loss: 0.9914
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6701 - loss: 0.8090 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6753 - loss: 0.7725
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6779 - loss: 0.7527
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6806 - loss: 0.7407
[1m143/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6826 - loss: 0.7342
[1m175/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6842 - loss: 0.7294
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6851 - loss: 0.7260
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6852 - loss: 0.7245
[1m264/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6854 - loss: 0.7232
[1m294/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6857 - loss: 0.7217
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6857 - loss: 0.7210 - val_accuracy: 0.6875 - val_loss: 0.6461
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6250 - loss: 0.6398
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7105 - loss: 0.6695 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7138 - loss: 0.6759
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7126 - loss: 0.6811
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7111 - loss: 0.6831
[1m154/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7095 - loss: 0.6846
[1m185/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7084 - loss: 0.6854
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7077 - loss: 0.6853
[1m243/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7067 - loss: 0.6854
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7058 - loss: 0.6859
[1m301/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7051 - loss: 0.6865
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7048 - loss: 0.6867 - val_accuracy: 0.6822 - val_loss: 0.6524
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7500 - loss: 0.5568
[1m 25/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7354 - loss: 0.6184 
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7158 - loss: 0.6433
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7121 - loss: 0.6490
[1m111/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7107 - loss: 0.6519
[1m141/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7098 - loss: 0.6543
[1m169/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7092 - loss: 0.6567
[1m198/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7089 - loss: 0.6588
[1m226/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7085 - loss: 0.6607
[1m251/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7082 - loss: 0.6619
[1m281/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7079 - loss: 0.6627
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7077 - loss: 0.6633 - val_accuracy: 0.6886 - val_loss: 0.6508
Epoch 10/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.7188 - loss: 0.5158
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6964 - loss: 0.6702 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6993 - loss: 0.6639
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6990 - loss: 0.6651
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6992 - loss: 0.6647
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7003 - loss: 0.6632
[1m184/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7016 - loss: 0.6609
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7027 - loss: 0.6586
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7036 - loss: 0.6578
[1m274/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7045 - loss: 0.6575
[1m303/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7053 - loss: 0.6573
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7055 - loss: 0.6572 - val_accuracy: 0.6935 - val_loss: 0.6554
Epoch 11/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6250 - loss: 0.7512
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6989 - loss: 0.6822 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7047 - loss: 0.6706
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7096 - loss: 0.6601
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7126 - loss: 0.6538
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7148 - loss: 0.6512
[1m183/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7162 - loss: 0.6496
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7168 - loss: 0.6482
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7175 - loss: 0.6465
[1m273/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7181 - loss: 0.6453
[1m303/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7185 - loss: 0.6449
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7186 - loss: 0.6449 - val_accuracy: 0.6861 - val_loss: 0.6645

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 489ms/step2025-11-08 14:54:58.137347: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 24ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 25ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:46[0m 1s/step
[1m 54/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 947us/step
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 884us/step
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 863us/step
[1m233/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 868us/step
[1m294/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 858us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 21ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 22ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m55/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 932us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 69.52 [%]
Global F1 score (validation) = 69.65 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[0.64201355 0.31989974 0.02610518 0.01198157]
 [0.09176207 0.37607202 0.00483479 0.5273311 ]
 [0.64739877 0.30411416 0.03469368 0.01379339]
 ...
 [0.00146651 0.00240462 0.00382025 0.9923086 ]
 [0.00118729 0.00099533 0.00481803 0.99299943]
 [0.00375916 0.00205027 0.9780629  0.01612764]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 74.21 [%]
Global accuracy score (test) = 72.94 [%]
Global F1 score (train) = 74.51 [%]
Global F1 score (test) = 73.55 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.53      0.69      0.60       350
MODERATE-INTENSITY       0.53      0.43      0.47       350
         SEDENTARY       0.98      0.99      0.99       350
VIGOROUS-INTENSITY       0.95      0.83      0.88       299

          accuracy                           0.73      1349
         macro avg       0.75      0.73      0.74      1349
      weighted avg       0.74      0.73      0.73      1349


Accuracy capturado en la ejecución 8: 72.94 [%]
F1-score capturado en la ejecución 8: 73.55 [%]

=== EJECUCIÓN 9 ===

--- TRAIN (ejecución 9) ---

--- TEST (ejecución 9) ---
2025-11-08 14:55:09.158051: 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`.
2025-11-08 14:55:09.169417: 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 00:00:1762610109.182736  985331 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762610109.186826  985331 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762610109.196505  985331 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610109.196523  985331 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610109.196525  985331 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610109.196526  985331 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 14:55:09.199624: 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 00:00:1762610111.406910  985331 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762610113.868709  985463 service.cc:152] XLA service 0x777110007100 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762610113.868737  985463 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 14:55:13.925744: 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 00:00:1762610114.236026  985463 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762610116.608467  985463 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:37[0m 5s/step - accuracy: 0.3438 - loss: 1.6370
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3138 - loss: 1.7437  
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3517 - loss: 1.6647
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3811 - loss: 1.5882
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4004 - loss: 1.5386
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4153 - loss: 1.4995
[1m175/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4287 - loss: 1.4627
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4401 - loss: 1.4309
[1m237/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4498 - loss: 1.4039
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4585 - loss: 1.3798
[1m296/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4655 - loss: 1.3601
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4687 - loss: 1.3509
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 13ms/step - accuracy: 0.4690 - loss: 1.3503 - val_accuracy: 0.6366 - val_loss: 0.7829
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6875 - loss: 1.0683
[1m 32/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6486 - loss: 0.9082 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6377 - loss: 0.9074
[1m 94/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6338 - loss: 0.9056
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6318 - loss: 0.9063
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6305 - loss: 0.9050
[1m182/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6291 - loss: 0.9053
[1m214/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6283 - loss: 0.9046
[1m245/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6278 - loss: 0.9034
[1m278/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6274 - loss: 0.9021
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6271 - loss: 0.9013
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6271 - loss: 0.9013 - val_accuracy: 0.6692 - val_loss: 0.6937
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6562 - loss: 0.9791
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6377 - loss: 0.8967 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6414 - loss: 0.8756
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6412 - loss: 0.8647
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6404 - loss: 0.8608
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6403 - loss: 0.8593
[1m182/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6402 - loss: 0.8576
[1m211/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6399 - loss: 0.8561
[1m240/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6397 - loss: 0.8546
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6398 - loss: 0.8528
[1m302/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6401 - loss: 0.8506
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6402 - loss: 0.8500 - val_accuracy: 0.6756 - val_loss: 0.6748
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5000 - loss: 0.9733
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6481 - loss: 0.8124 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6530 - loss: 0.8074
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6516 - loss: 0.8069
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6517 - loss: 0.8036
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6521 - loss: 0.8011
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6530 - loss: 0.7984
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6534 - loss: 0.7972
[1m240/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6536 - loss: 0.7960
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6537 - loss: 0.7952
[1m300/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6541 - loss: 0.7942
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6543 - loss: 0.7938 - val_accuracy: 0.6840 - val_loss: 0.6566
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5000 - loss: 0.9433
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6728 - loss: 0.7605 
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6809 - loss: 0.7349
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6824 - loss: 0.7284
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6812 - loss: 0.7300
[1m142/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6792 - loss: 0.7330
[1m172/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6773 - loss: 0.7359
[1m201/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6760 - loss: 0.7387
[1m229/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6753 - loss: 0.7400
[1m261/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6747 - loss: 0.7410
[1m292/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6743 - loss: 0.7418
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6741 - loss: 0.7424 - val_accuracy: 0.6836 - val_loss: 0.6592
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6250 - loss: 0.7019
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6758 - loss: 0.6939 
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6833 - loss: 0.7016
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6855 - loss: 0.7037
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6847 - loss: 0.7068
[1m141/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6843 - loss: 0.7085
[1m165/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6841 - loss: 0.7098
[1m194/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6836 - loss: 0.7118
[1m224/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6831 - loss: 0.7140
[1m254/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6828 - loss: 0.7163
[1m286/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6823 - loss: 0.7184
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6818 - loss: 0.7198 - val_accuracy: 0.6942 - val_loss: 0.6379
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5312 - loss: 0.7886
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7157 - loss: 0.6758 
[1m 63/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7064 - loss: 0.6950
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7016 - loss: 0.7044
[1m125/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6987 - loss: 0.7074
[1m155/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6968 - loss: 0.7083
[1m185/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6955 - loss: 0.7085
[1m216/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6945 - loss: 0.7085
[1m248/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6934 - loss: 0.7085
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6927 - loss: 0.7086
[1m304/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6920 - loss: 0.7087
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6918 - loss: 0.7088 - val_accuracy: 0.6861 - val_loss: 0.6469
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.7188 - loss: 0.4819
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6955 - loss: 0.6929 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6973 - loss: 0.6914
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6949 - loss: 0.6979
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6939 - loss: 0.6994
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6934 - loss: 0.6991
[1m183/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6930 - loss: 0.6982
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6926 - loss: 0.6978
[1m246/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6927 - loss: 0.6970
[1m275/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6929 - loss: 0.6964
[1m305/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6933 - loss: 0.6956
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6934 - loss: 0.6954 - val_accuracy: 0.6945 - val_loss: 0.6444
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5938 - loss: 0.9847
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6934 - loss: 0.7000 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7018 - loss: 0.6792
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7036 - loss: 0.6708
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7043 - loss: 0.6659
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7048 - loss: 0.6630
[1m182/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7048 - loss: 0.6614
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7048 - loss: 0.6612
[1m243/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7049 - loss: 0.6613
[1m274/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7047 - loss: 0.6620
[1m300/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7045 - loss: 0.6625
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7044 - loss: 0.6627 - val_accuracy: 0.6896 - val_loss: 0.6495
Epoch 10/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.6562 - loss: 0.7046
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6956 - loss: 0.7160 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7004 - loss: 0.7015
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7011 - loss: 0.6960
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7038 - loss: 0.6895
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7061 - loss: 0.6847
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7077 - loss: 0.6806
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7089 - loss: 0.6771
[1m236/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7096 - loss: 0.6745
[1m265/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7103 - loss: 0.6721
[1m294/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7109 - loss: 0.6701
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7112 - loss: 0.6691 - val_accuracy: 0.6970 - val_loss: 0.6308
Epoch 11/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.8750 - loss: 0.4102
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7755 - loss: 0.5679 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7592 - loss: 0.5811
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7498 - loss: 0.5953
[1m123/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7432 - loss: 0.6023
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7387 - loss: 0.6069
[1m184/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7355 - loss: 0.6110
[1m214/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7332 - loss: 0.6142
[1m247/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7313 - loss: 0.6174
[1m275/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7300 - loss: 0.6197
[1m305/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7288 - loss: 0.6215
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7286 - loss: 0.6218 - val_accuracy: 0.6970 - val_loss: 0.6551
Epoch 12/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7812 - loss: 0.5728
[1m 32/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7145 - loss: 0.6129 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7266 - loss: 0.6027
[1m 94/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7301 - loss: 0.6048
[1m124/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7307 - loss: 0.6091
[1m154/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7310 - loss: 0.6118
[1m185/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7314 - loss: 0.6128
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7319 - loss: 0.6134
[1m243/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7322 - loss: 0.6140
[1m275/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7327 - loss: 0.6141
[1m306/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7329 - loss: 0.6142
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7329 - loss: 0.6142 - val_accuracy: 0.6928 - val_loss: 0.6537
Epoch 13/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7500 - loss: 0.6579
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7423 - loss: 0.6457 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7388 - loss: 0.6315
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7380 - loss: 0.6232
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7408 - loss: 0.6155
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7424 - loss: 0.6105
[1m182/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7427 - loss: 0.6086
[1m215/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7426 - loss: 0.6077
[1m244/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7425 - loss: 0.6066
[1m277/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7423 - loss: 0.6056
[1m308/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7420 - loss: 0.6051
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7420 - loss: 0.6050 - val_accuracy: 0.7008 - val_loss: 0.6419
Epoch 14/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7188 - loss: 0.6947
[1m 32/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7255 - loss: 0.5939 
[1m 63/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7337 - loss: 0.5936
[1m 92/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7354 - loss: 0.5948
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7359 - loss: 0.5957
[1m155/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7367 - loss: 0.5962
[1m185/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7380 - loss: 0.5958
[1m218/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7388 - loss: 0.5957
[1m248/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7392 - loss: 0.5958
[1m277/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7399 - loss: 0.5955
[1m306/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7404 - loss: 0.5950
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7404 - loss: 0.5950 - val_accuracy: 0.6938 - val_loss: 0.6589
Epoch 15/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7500 - loss: 0.4494
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7659 - loss: 0.5173 
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7611 - loss: 0.5417
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7595 - loss: 0.5531
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7595 - loss: 0.5567
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7593 - loss: 0.5586
[1m173/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7590 - loss: 0.5597
[1m204/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7586 - loss: 0.5606
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7583 - loss: 0.5613
[1m265/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7580 - loss: 0.5622
[1m296/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7579 - loss: 0.5626
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7579 - loss: 0.5628 - val_accuracy: 0.7001 - val_loss: 0.6586

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 520ms/step2025-11-08 14:55:31.740809: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 25ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 25ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:43[0m 1s/step
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 910us/step
[1m112/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 902us/step
[1m172/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 878us/step
[1m230/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 875us/step
[1m290/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 868us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 22ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 22ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m58/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 892us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 69.07 [%]
Global F1 score (validation) = 69.84 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[2.9139811e-01 5.4054099e-01 8.1341770e-03 1.5992668e-01]
 [6.4857358e-01 3.2411331e-01 1.5772529e-02 1.1540537e-02]
 [6.4034528e-01 3.3391497e-01 1.4786871e-02 1.0952791e-02]
 ...
 [1.1010016e-03 8.6528173e-04 2.7598115e-03 9.9527383e-01]
 [1.8193292e-03 5.1925395e-04 7.1117887e-03 9.9054974e-01]
 [3.8061060e-03 7.0172474e-03 9.6079975e-01 2.8376861e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 74.49 [%]
Global accuracy score (test) = 72.42 [%]
Global F1 score (train) = 74.85 [%]
Global F1 score (test) = 73.4 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.54      0.57      0.55       350
MODERATE-INTENSITY       0.52      0.56      0.54       350
         SEDENTARY       0.98      0.99      0.98       350
VIGOROUS-INTENSITY       0.94      0.79      0.86       299

          accuracy                           0.72      1349
         macro avg       0.75      0.73      0.73      1349
      weighted avg       0.74      0.72      0.73      1349


Accuracy capturado en la ejecución 9: 72.42 [%]
F1-score capturado en la ejecución 9: 73.4 [%]

=== EJECUCIÓN 10 ===

--- TRAIN (ejecución 10) ---

--- TEST (ejecución 10) ---
2025-11-08 14:55:42.751185: 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`.
2025-11-08 14:55:42.762551: 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 00:00:1762610142.775770  987757 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762610142.779886  987757 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762610142.790091  987757 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610142.790109  987757 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610142.790111  987757 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610142.790112  987757 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 14:55:42.793451: 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 00:00:1762610144.997137  987757 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762610147.476728  987855 service.cc:152] XLA service 0x71af0c015970 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762610147.476754  987855 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 14:55:47.527041: 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 00:00:1762610147.850336  987855 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762610150.188729  987855 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:30[0m 5s/step - accuracy: 0.2188 - loss: 1.9655
[1m 22/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2919 - loss: 1.7771  
[1m 53/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3571 - loss: 1.6480
[1m 81/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3887 - loss: 1.5763
[1m113/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4106 - loss: 1.5211
[1m141/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4250 - loss: 1.4832
[1m170/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4366 - loss: 1.4517
[1m200/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4465 - loss: 1.4236
[1m230/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4548 - loss: 1.3992
[1m259/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4618 - loss: 1.3787
[1m289/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4681 - loss: 1.3602
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4721 - loss: 1.3485
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 13ms/step - accuracy: 0.4723 - loss: 1.3480 - val_accuracy: 0.6552 - val_loss: 0.7601
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6250 - loss: 0.8901
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5925 - loss: 1.0088 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5970 - loss: 1.0015
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5972 - loss: 0.9928
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5982 - loss: 0.9847
[1m145/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5981 - loss: 0.9800
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5973 - loss: 0.9777
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5968 - loss: 0.9756
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5968 - loss: 0.9732
[1m261/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5972 - loss: 0.9708
[1m291/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.5976 - loss: 0.9681
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.5979 - loss: 0.9663 - val_accuracy: 0.6703 - val_loss: 0.6573
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7188 - loss: 0.7505
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5797 - loss: 0.9344 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5929 - loss: 0.9276
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6029 - loss: 0.9168
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6082 - loss: 0.9087
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6123 - loss: 0.9003
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6150 - loss: 0.8946
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6171 - loss: 0.8898
[1m244/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6186 - loss: 0.8871
[1m277/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6201 - loss: 0.8842
[1m306/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6213 - loss: 0.8819
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6215 - loss: 0.8816 - val_accuracy: 0.6735 - val_loss: 0.6480
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7500 - loss: 0.7122
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6811 - loss: 0.7706 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6691 - loss: 0.7851
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6620 - loss: 0.8002
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6582 - loss: 0.8051
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6558 - loss: 0.8075
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6541 - loss: 0.8091
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6525 - loss: 0.8112
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6514 - loss: 0.8123
[1m273/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6504 - loss: 0.8132
[1m302/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6498 - loss: 0.8137
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6497 - loss: 0.8137 - val_accuracy: 0.6854 - val_loss: 0.6261
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.6875 - loss: 0.7943
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6662 - loss: 0.8009 
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6624 - loss: 0.8020
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6579 - loss: 0.8025
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6543 - loss: 0.8057
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6528 - loss: 0.8054
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6518 - loss: 0.8047
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6514 - loss: 0.8033
[1m236/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6515 - loss: 0.8014
[1m266/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6515 - loss: 0.7999
[1m294/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6518 - loss: 0.7981
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6519 - loss: 0.7971 - val_accuracy: 0.6959 - val_loss: 0.6223
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7812 - loss: 0.6503
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6764 - loss: 0.7310 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6700 - loss: 0.7387
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6700 - loss: 0.7363
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6689 - loss: 0.7385
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6673 - loss: 0.7420
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6667 - loss: 0.7433
[1m200/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6666 - loss: 0.7435
[1m229/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6671 - loss: 0.7436
[1m259/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6675 - loss: 0.7441
[1m288/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6680 - loss: 0.7446
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6682 - loss: 0.7451 - val_accuracy: 0.6882 - val_loss: 0.6282
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.5625 - loss: 1.1227
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6430 - loss: 0.8407 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6617 - loss: 0.8014
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6689 - loss: 0.7844
[1m123/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6724 - loss: 0.7740
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6737 - loss: 0.7685
[1m183/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6751 - loss: 0.7630
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6758 - loss: 0.7588
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6764 - loss: 0.7554
[1m272/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6769 - loss: 0.7525
[1m303/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6773 - loss: 0.7498
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6774 - loss: 0.7493 - val_accuracy: 0.6882 - val_loss: 0.6199
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.9375 - loss: 0.4657
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7481 - loss: 0.6337 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7194 - loss: 0.6618
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7096 - loss: 0.6740
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7021 - loss: 0.6823
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6981 - loss: 0.6870
[1m184/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6958 - loss: 0.6887
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6944 - loss: 0.6900
[1m244/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6933 - loss: 0.6907
[1m273/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6924 - loss: 0.6918
[1m306/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6918 - loss: 0.6923
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6917 - loss: 0.6924 - val_accuracy: 0.6791 - val_loss: 0.6351
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7188 - loss: 0.4840
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6916 - loss: 0.6456 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6885 - loss: 0.6621
[1m 96/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6889 - loss: 0.6659
[1m128/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6886 - loss: 0.6692
[1m159/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6885 - loss: 0.6714
[1m192/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6887 - loss: 0.6727
[1m224/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6888 - loss: 0.6739
[1m252/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6889 - loss: 0.6748
[1m283/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6891 - loss: 0.6755
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6892 - loss: 0.6761 - val_accuracy: 0.7075 - val_loss: 0.6296
Epoch 10/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7812 - loss: 0.6058
[1m 33/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7356 - loss: 0.6502 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7209 - loss: 0.6646
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7146 - loss: 0.6684
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7112 - loss: 0.6699
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7090 - loss: 0.6706
[1m183/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7074 - loss: 0.6708
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7062 - loss: 0.6709
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7054 - loss: 0.6705
[1m274/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7049 - loss: 0.6700
[1m306/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7044 - loss: 0.6695
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7044 - loss: 0.6695 - val_accuracy: 0.7037 - val_loss: 0.6267
Epoch 11/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7500 - loss: 0.4762
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7226 - loss: 0.6330 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7176 - loss: 0.6383
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7162 - loss: 0.6404
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7158 - loss: 0.6423
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7146 - loss: 0.6459
[1m182/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7142 - loss: 0.6473
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7142 - loss: 0.6480
[1m244/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7140 - loss: 0.6485
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7139 - loss: 0.6485
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7137 - loss: 0.6484
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7137 - loss: 0.6483 - val_accuracy: 0.7068 - val_loss: 0.6323
Epoch 12/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7812 - loss: 0.3844
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7178 - loss: 0.6097 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7183 - loss: 0.6260
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7190 - loss: 0.6255
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7191 - loss: 0.6239
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7189 - loss: 0.6223
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7192 - loss: 0.6207
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7194 - loss: 0.6197
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7193 - loss: 0.6200
[1m274/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7194 - loss: 0.6201
[1m305/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7195 - loss: 0.6203
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7195 - loss: 0.6204 - val_accuracy: 0.6991 - val_loss: 0.6486

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 482ms/step2025-11-08 14:56:03.062144: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 24ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 25ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:38[0m 1s/step
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 912us/step
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 870us/step
[1m175/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 870us/step
[1m239/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 847us/step
[1m294/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 859us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 21ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 22ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m57/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 900us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 70.12 [%]
Global F1 score (validation) = 70.97 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[8.0491459e-01 1.6690382e-01 6.0167974e-03 2.2164872e-02]
 [5.7871884e-01 3.9110166e-01 1.7953442e-02 1.2226068e-02]
 [5.0058943e-01 4.6264499e-01 1.6877493e-02 1.9888064e-02]
 ...
 [1.0693794e-03 6.4564106e-04 3.8067801e-03 9.9447823e-01]
 [1.2581263e-03 1.0427365e-03 6.0373684e-03 9.9166167e-01]
 [7.6901722e-03 9.4965696e-03 9.4291759e-01 3.9895713e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 76.57 [%]
Global accuracy score (test) = 72.2 [%]
Global F1 score (train) = 76.93 [%]
Global F1 score (test) = 73.22 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.52      0.59      0.55       350
MODERATE-INTENSITY       0.52      0.51      0.52       350
         SEDENTARY       0.98      0.99      0.98       350
VIGOROUS-INTENSITY       0.95      0.81      0.88       299

          accuracy                           0.72      1349
         macro avg       0.74      0.73      0.73      1349
      weighted avg       0.74      0.72      0.73      1349


Accuracy capturado en la ejecución 10: 72.2 [%]
F1-score capturado en la ejecución 10: 73.22 [%]

=== EJECUCIÓN 11 ===

--- TRAIN (ejecución 11) ---

--- TEST (ejecución 11) ---
2025-11-08 14:56:14.250554: 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`.
2025-11-08 14:56:14.261578: 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 00:00:1762610174.275005  989874 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762610174.279210  989874 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762610174.289491  989874 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610174.289508  989874 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610174.289509  989874 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610174.289510  989874 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 14:56:14.292459: 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 00:00:1762610176.514303  989874 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762610179.005852  989981 service.cc:152] XLA service 0x7de91c014d90 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762610179.005878  989981 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 14:56:19.057833: 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 00:00:1762610179.380535  989981 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762610181.737368  989981 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:39[0m 5s/step - accuracy: 0.3438 - loss: 1.6270
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3946 - loss: 1.5557  
[1m 53/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4229 - loss: 1.4901
[1m 83/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4383 - loss: 1.4455
[1m113/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4515 - loss: 1.4072
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4635 - loss: 1.3752
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4739 - loss: 1.3477
[1m201/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4812 - loss: 1.3268
[1m231/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4884 - loss: 1.3059
[1m262/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4947 - loss: 1.2871
[1m288/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4993 - loss: 1.2732
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.5028 - loss: 1.2624
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 13ms/step - accuracy: 0.5030 - loss: 1.2620 - val_accuracy: 0.6408 - val_loss: 0.8029
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.6875 - loss: 0.8356
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6257 - loss: 0.8921 
[1m 53/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6242 - loss: 0.9046
[1m 83/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6231 - loss: 0.9120
[1m113/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6236 - loss: 0.9117
[1m143/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6234 - loss: 0.9115
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6224 - loss: 0.9130
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6219 - loss: 0.9125
[1m232/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6214 - loss: 0.9119
[1m260/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6210 - loss: 0.9110
[1m289/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6209 - loss: 0.9098
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6208 - loss: 0.9089 - val_accuracy: 0.6692 - val_loss: 0.6899
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6875 - loss: 0.7482
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6012 - loss: 0.9098 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6085 - loss: 0.8970
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6144 - loss: 0.8851
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6195 - loss: 0.8764
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6227 - loss: 0.8710
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6252 - loss: 0.8660
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6272 - loss: 0.8620
[1m236/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6287 - loss: 0.8588
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6300 - loss: 0.8559
[1m297/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6311 - loss: 0.8529
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6316 - loss: 0.8516 - val_accuracy: 0.6777 - val_loss: 0.6775
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7500 - loss: 0.6541
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6542 - loss: 0.8328 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6472 - loss: 0.8274
[1m 92/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6466 - loss: 0.8211
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6470 - loss: 0.8165
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6475 - loss: 0.8131
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6482 - loss: 0.8105
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6489 - loss: 0.8081
[1m236/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6498 - loss: 0.8057
[1m266/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6510 - loss: 0.8030
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6518 - loss: 0.8012
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6523 - loss: 0.8004 - val_accuracy: 0.6896 - val_loss: 0.6624
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 23ms/step - accuracy: 0.7812 - loss: 0.6722
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6877 - loss: 0.7929 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6674 - loss: 0.8093
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6644 - loss: 0.8018
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6644 - loss: 0.7955
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6640 - loss: 0.7904
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6638 - loss: 0.7862
[1m210/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6636 - loss: 0.7828
[1m240/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6636 - loss: 0.7802
[1m270/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6640 - loss: 0.7780
[1m300/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6647 - loss: 0.7759
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6648 - loss: 0.7753 - val_accuracy: 0.6889 - val_loss: 0.6701
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6875 - loss: 0.7417
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6797 - loss: 0.7630 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6753 - loss: 0.7571
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6748 - loss: 0.7521
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6747 - loss: 0.7477
[1m146/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6743 - loss: 0.7456
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6742 - loss: 0.7442
[1m204/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6751 - loss: 0.7415
[1m234/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6762 - loss: 0.7391
[1m264/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6770 - loss: 0.7378
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6776 - loss: 0.7365
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6778 - loss: 0.7357 - val_accuracy: 0.6850 - val_loss: 0.6595
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.6875 - loss: 0.5252
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7040 - loss: 0.6743 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6949 - loss: 0.6960
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6896 - loss: 0.7060
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6877 - loss: 0.7104
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6861 - loss: 0.7143
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6851 - loss: 0.7156
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6848 - loss: 0.7154
[1m233/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6844 - loss: 0.7150
[1m266/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6842 - loss: 0.7139
[1m297/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6845 - loss: 0.7122
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6847 - loss: 0.7115 - val_accuracy: 0.6917 - val_loss: 0.6575
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6250 - loss: 0.6396
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6844 - loss: 0.6486 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6881 - loss: 0.6666
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6901 - loss: 0.6738
[1m111/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6901 - loss: 0.6781
[1m143/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6901 - loss: 0.6819
[1m172/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6908 - loss: 0.6830
[1m200/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6916 - loss: 0.6836
[1m231/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6922 - loss: 0.6844
[1m260/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6924 - loss: 0.6853
[1m288/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6927 - loss: 0.6857
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6929 - loss: 0.6858 - val_accuracy: 0.6826 - val_loss: 0.6702
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.8438 - loss: 0.6272
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7373 - loss: 0.6423 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7258 - loss: 0.6555
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7190 - loss: 0.6631
[1m123/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7150 - loss: 0.6657
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7125 - loss: 0.6662
[1m184/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7113 - loss: 0.6658
[1m214/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7105 - loss: 0.6652
[1m245/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7098 - loss: 0.6649
[1m275/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7094 - loss: 0.6644
[1m308/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7092 - loss: 0.6641
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7092 - loss: 0.6641 - val_accuracy: 0.6928 - val_loss: 0.6645
Epoch 10/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7188 - loss: 0.7048
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7229 - loss: 0.6274 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7160 - loss: 0.6408
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7163 - loss: 0.6434
[1m116/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7169 - loss: 0.6459
[1m146/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7179 - loss: 0.6462
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7179 - loss: 0.6459
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7178 - loss: 0.6459
[1m241/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7177 - loss: 0.6462
[1m270/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7175 - loss: 0.6464
[1m302/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7175 - loss: 0.6462
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7175 - loss: 0.6462 - val_accuracy: 0.6935 - val_loss: 0.6672
Epoch 11/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6875 - loss: 0.7937
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7087 - loss: 0.6567 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7077 - loss: 0.6565
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7060 - loss: 0.6571
[1m125/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7067 - loss: 0.6551
[1m155/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7080 - loss: 0.6528
[1m185/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7094 - loss: 0.6508
[1m215/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7105 - loss: 0.6496
[1m244/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7112 - loss: 0.6488
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7117 - loss: 0.6481
[1m303/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7122 - loss: 0.6471
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7123 - loss: 0.6469 - val_accuracy: 0.6854 - val_loss: 0.6711
Epoch 12/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.7812 - loss: 0.4750
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7537 - loss: 0.5896 
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7424 - loss: 0.5918
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7350 - loss: 0.5983
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7303 - loss: 0.6029
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7272 - loss: 0.6059
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7257 - loss: 0.6077
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7243 - loss: 0.6091
[1m233/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7236 - loss: 0.6103
[1m264/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7229 - loss: 0.6115
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7225 - loss: 0.6120
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7222 - loss: 0.6123 - val_accuracy: 0.6917 - val_loss: 0.6771

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 493ms/step2025-11-08 14:56:34.687563: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 24ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 24ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:56[0m 1s/step
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 916us/step
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 883us/step
[1m173/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 879us/step
[1m226/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 897us/step
[1m283/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 893us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 22ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 22ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m58/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 888us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 71.07 [%]
Global F1 score (validation) = 71.86 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[5.32878101e-01 4.32189673e-01 1.87683888e-02 1.61638707e-02]
 [3.67098391e-01 5.72738528e-01 1.00962445e-02 5.00668399e-02]
 [5.88114500e-01 3.56764227e-01 3.94810997e-02 1.56402010e-02]
 ...
 [1.94697132e-04 1.33863417e-04 1.05326425e-03 9.98618245e-01]
 [9.66767489e-04 5.36418112e-04 8.43109377e-03 9.90065753e-01]
 [1.75100798e-03 2.33841222e-03 9.78562415e-01 1.73481945e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 74.66 [%]
Global accuracy score (test) = 72.2 [%]
Global F1 score (train) = 75.0 [%]
Global F1 score (test) = 73.19 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.53      0.58      0.55       350
MODERATE-INTENSITY       0.50      0.49      0.49       350
         SEDENTARY       0.98      0.99      0.99       350
VIGOROUS-INTENSITY       0.95      0.85      0.90       299

          accuracy                           0.72      1349
         macro avg       0.74      0.73      0.73      1349
      weighted avg       0.73      0.72      0.73      1349


Accuracy capturado en la ejecución 11: 72.2 [%]
F1-score capturado en la ejecución 11: 73.19 [%]

=== EJECUCIÓN 12 ===

--- TRAIN (ejecución 12) ---

--- TEST (ejecución 12) ---
2025-11-08 14:56:45.562614: 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`.
2025-11-08 14:56:45.574024: 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 00:00:1762610205.587199  991991 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762610205.591311  991991 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762610205.601048  991991 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610205.601066  991991 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610205.601067  991991 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610205.601069  991991 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 14:56:45.604173: 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 00:00:1762610207.807156  991991 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762610210.272152  992124 service.cc:152] XLA service 0x7e2eb8027a20 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762610210.272212  992124 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 14:56:50.330950: 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 00:00:1762610210.638164  992124 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762610213.006215  992124 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:30[0m 5s/step - accuracy: 0.1562 - loss: 1.7641
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 1.7019  
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3455 - loss: 1.6334
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3743 - loss: 1.5757
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3954 - loss: 1.5309
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4105 - loss: 1.4974
[1m172/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4215 - loss: 1.4717
[1m202/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4330 - loss: 1.4447
[1m231/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4430 - loss: 1.4210
[1m262/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4523 - loss: 1.3980
[1m289/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4595 - loss: 1.3802
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4645 - loss: 1.3675
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 14ms/step - accuracy: 0.4647 - loss: 1.3669 - val_accuracy: 0.6261 - val_loss: 0.8139
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6250 - loss: 1.0315
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6103 - loss: 1.0093 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6096 - loss: 1.0007
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6070 - loss: 0.9969
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6053 - loss: 0.9931
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6051 - loss: 0.9895
[1m182/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6059 - loss: 0.9847
[1m214/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6070 - loss: 0.9801
[1m245/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6082 - loss: 0.9761
[1m274/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6089 - loss: 0.9733
[1m304/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6096 - loss: 0.9703
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6098 - loss: 0.9696 - val_accuracy: 0.6713 - val_loss: 0.6967
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.4688 - loss: 1.1825
[1m 25/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6126 - loss: 0.9098 
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6273 - loss: 0.8937
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6304 - loss: 0.8898
[1m112/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6310 - loss: 0.8885
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6316 - loss: 0.8874
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6321 - loss: 0.8860
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6323 - loss: 0.8852
[1m233/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6327 - loss: 0.8840
[1m261/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6332 - loss: 0.8826
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6338 - loss: 0.8810
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6341 - loss: 0.8803 - val_accuracy: 0.6759 - val_loss: 0.6721
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7812 - loss: 0.7446
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6514 - loss: 0.8596 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6507 - loss: 0.8544
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6500 - loss: 0.8504
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6493 - loss: 0.8477
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6487 - loss: 0.8471
[1m182/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6481 - loss: 0.8454
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6477 - loss: 0.8437
[1m240/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6476 - loss: 0.8427
[1m272/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6475 - loss: 0.8413
[1m301/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6474 - loss: 0.8398
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6474 - loss: 0.8393 - val_accuracy: 0.6829 - val_loss: 0.6511
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6562 - loss: 0.8887
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6401 - loss: 0.8600 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6496 - loss: 0.8315
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6551 - loss: 0.8182
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6566 - loss: 0.8140
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6582 - loss: 0.8100
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6600 - loss: 0.8067
[1m211/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6609 - loss: 0.8044
[1m241/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6614 - loss: 0.8028
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6619 - loss: 0.8014
[1m300/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6621 - loss: 0.8001
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6622 - loss: 0.7996 - val_accuracy: 0.6935 - val_loss: 0.6347
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6875 - loss: 0.7936
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6873 - loss: 0.7575 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6852 - loss: 0.7517
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6847 - loss: 0.7479
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6838 - loss: 0.7478
[1m154/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6830 - loss: 0.7477
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6827 - loss: 0.7475
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6823 - loss: 0.7476
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6818 - loss: 0.7482
[1m274/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6815 - loss: 0.7483
[1m304/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6812 - loss: 0.7482
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6811 - loss: 0.7482 - val_accuracy: 0.7026 - val_loss: 0.6296
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.7188 - loss: 0.7547
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6721 - loss: 0.7603 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6678 - loss: 0.7658
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6683 - loss: 0.7607
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6699 - loss: 0.7564
[1m145/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6716 - loss: 0.7544
[1m173/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6728 - loss: 0.7524
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6741 - loss: 0.7509
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6753 - loss: 0.7494
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6767 - loss: 0.7471
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6779 - loss: 0.7450
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6786 - loss: 0.7439 - val_accuracy: 0.6935 - val_loss: 0.6349
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.7812 - loss: 0.5899
[1m 32/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7199 - loss: 0.6461 
[1m 64/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7137 - loss: 0.6619
[1m 94/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7085 - loss: 0.6690
[1m124/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7049 - loss: 0.6752
[1m157/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7026 - loss: 0.6787
[1m185/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7014 - loss: 0.6800
[1m215/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7003 - loss: 0.6812
[1m243/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6996 - loss: 0.6824
[1m274/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6987 - loss: 0.6837
[1m300/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6982 - loss: 0.6849
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6980 - loss: 0.6854 - val_accuracy: 0.6903 - val_loss: 0.6345
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6562 - loss: 0.6921
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6949 - loss: 0.6601 
[1m 63/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7023 - loss: 0.6630
[1m 95/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7046 - loss: 0.6608
[1m123/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7046 - loss: 0.6632
[1m154/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7049 - loss: 0.6655
[1m185/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7045 - loss: 0.6683
[1m216/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7040 - loss: 0.6701
[1m245/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7037 - loss: 0.6713
[1m279/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7032 - loss: 0.6728
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7030 - loss: 0.6735 - val_accuracy: 0.6928 - val_loss: 0.6396
Epoch 10/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6562 - loss: 0.7916
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6831 - loss: 0.7348 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6948 - loss: 0.7048
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6986 - loss: 0.6932
[1m116/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7004 - loss: 0.6875
[1m146/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7011 - loss: 0.6844
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7009 - loss: 0.6833
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7008 - loss: 0.6824
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7008 - loss: 0.6818
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7010 - loss: 0.6813
[1m297/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7012 - loss: 0.6810
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7014 - loss: 0.6807 - val_accuracy: 0.6966 - val_loss: 0.6357
Epoch 11/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6250 - loss: 0.8857
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7025 - loss: 0.7042 
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7080 - loss: 0.6809
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7096 - loss: 0.6707
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7110 - loss: 0.6657
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7117 - loss: 0.6633
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7121 - loss: 0.6610
[1m204/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7124 - loss: 0.6589
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7124 - loss: 0.6581
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7125 - loss: 0.6575
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7125 - loss: 0.6573
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7125 - loss: 0.6571 - val_accuracy: 0.6945 - val_loss: 0.6274
Epoch 12/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.7500 - loss: 0.4485
[1m 32/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7099 - loss: 0.6353 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7177 - loss: 0.6339
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7217 - loss: 0.6340
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7223 - loss: 0.6356
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7223 - loss: 0.6363
[1m183/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7226 - loss: 0.6364
[1m215/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7229 - loss: 0.6358
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7233 - loss: 0.6348
[1m274/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7234 - loss: 0.6343
[1m303/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7234 - loss: 0.6341
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7233 - loss: 0.6341 - val_accuracy: 0.6994 - val_loss: 0.6424
Epoch 13/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6875 - loss: 0.7100
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7164 - loss: 0.6310 
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7214 - loss: 0.6235
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7249 - loss: 0.6180
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7266 - loss: 0.6150
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7274 - loss: 0.6133
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7279 - loss: 0.6127
[1m209/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7282 - loss: 0.6130
[1m239/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7284 - loss: 0.6132
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7286 - loss: 0.6131
[1m295/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7289 - loss: 0.6131
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7290 - loss: 0.6132 - val_accuracy: 0.7040 - val_loss: 0.6349
Epoch 14/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6875 - loss: 0.8942
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7187 - loss: 0.6302 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7297 - loss: 0.6150
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7354 - loss: 0.6058
[1m116/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7374 - loss: 0.6028
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7384 - loss: 0.6015
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7391 - loss: 0.6008
[1m203/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7396 - loss: 0.6002
[1m230/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7397 - loss: 0.6001
[1m257/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7395 - loss: 0.6004
[1m284/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7392 - loss: 0.6009
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7388 - loss: 0.6016 - val_accuracy: 0.7117 - val_loss: 0.6449
Epoch 15/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7188 - loss: 0.7481
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7012 - loss: 0.6527 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7146 - loss: 0.6365
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7199 - loss: 0.6294
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7238 - loss: 0.6244
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7249 - loss: 0.6224
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7259 - loss: 0.6200
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7269 - loss: 0.6177
[1m234/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7281 - loss: 0.6153
[1m259/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7289 - loss: 0.6137
[1m288/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7297 - loss: 0.6123
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7304 - loss: 0.6113 - val_accuracy: 0.7072 - val_loss: 0.6403
Epoch 16/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7500 - loss: 0.4650
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7421 - loss: 0.5893 
[1m 54/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7523 - loss: 0.5779
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7513 - loss: 0.5798
[1m113/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7505 - loss: 0.5804
[1m143/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7505 - loss: 0.5794
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7508 - loss: 0.5791
[1m203/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7512 - loss: 0.5788
[1m233/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7516 - loss: 0.5784
[1m265/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7518 - loss: 0.5786
[1m295/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7519 - loss: 0.5787
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7520 - loss: 0.5787 - val_accuracy: 0.7135 - val_loss: 0.6497

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 480ms/step2025-11-08 14:57:08.904241: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 23ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 23ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:43[0m 1s/step
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 886us/step
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 863us/step
[1m172/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 885us/step
[1m224/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 904us/step
[1m281/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 901us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 21ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 22ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m55/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 953us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 69.63 [%]
Global F1 score (validation) = 68.43 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[6.91054821e-01 2.79524773e-01 2.13396754e-02 8.08079354e-03]
 [4.96899039e-01 4.81439412e-01 1.50794033e-02 6.58212043e-03]
 [4.40578997e-01 4.91655022e-01 2.41942108e-02 4.35718112e-02]
 ...
 [5.81321765e-05 1.16351024e-04 5.34674968e-04 9.99290824e-01]
 [7.40718562e-04 7.37660157e-04 3.82738840e-03 9.94694233e-01]
 [4.08558082e-03 2.94588925e-03 9.62345600e-01 3.06229554e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 73.5 [%]
Global accuracy score (test) = 74.72 [%]
Global F1 score (train) = 71.8 [%]
Global F1 score (test) = 74.51 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.55      0.81      0.65       350
MODERATE-INTENSITY       0.61      0.37      0.46       350
         SEDENTARY       0.98      1.00      0.99       350
VIGOROUS-INTENSITY       0.95      0.83      0.88       299

          accuracy                           0.75      1349
         macro avg       0.77      0.75      0.75      1349
      weighted avg       0.76      0.75      0.74      1349


Accuracy capturado en la ejecución 12: 74.72 [%]
F1-score capturado en la ejecución 12: 74.51 [%]

=== EJECUCIÓN 13 ===

--- TRAIN (ejecución 13) ---

--- TEST (ejecución 13) ---
2025-11-08 14:57:19.771048: 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`.
2025-11-08 14:57:19.782627: 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 00:00:1762610239.795953  994505 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762610239.799933  994505 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762610239.809795  994505 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610239.809810  994505 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610239.809812  994505 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610239.809813  994505 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 14:57:19.812720: 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 00:00:1762610241.996653  994505 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762610244.472850  994604 service.cc:152] XLA service 0x73c340014e60 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762610244.472888  994604 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 14:57:24.526948: 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 00:00:1762610244.848960  994604 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762610247.197480  994604 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:27[0m 5s/step - accuracy: 0.2500 - loss: 1.8897
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2914 - loss: 1.8313  
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3495 - loss: 1.6635
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3780 - loss: 1.5840
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4008 - loss: 1.5225
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4188 - loss: 1.4741
[1m182/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4325 - loss: 1.4374
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4432 - loss: 1.4084
[1m241/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4523 - loss: 1.3840
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4607 - loss: 1.3619
[1m302/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4685 - loss: 1.3414
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4704 - loss: 1.3365
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 14ms/step - accuracy: 0.4707 - loss: 1.3359 - val_accuracy: 0.6819 - val_loss: 0.7334
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7500 - loss: 0.6119
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5847 - loss: 1.0035 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5882 - loss: 1.0019
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5923 - loss: 0.9933
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5968 - loss: 0.9820
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6018 - loss: 0.9718
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6051 - loss: 0.9652
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6073 - loss: 0.9607
[1m234/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6089 - loss: 0.9571
[1m264/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6107 - loss: 0.9532
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6121 - loss: 0.9494
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6130 - loss: 0.9470 - val_accuracy: 0.6675 - val_loss: 0.6983
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.4375 - loss: 1.5494
[1m 32/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6358 - loss: 0.9132 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6380 - loss: 0.8815
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6398 - loss: 0.8693
[1m123/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6416 - loss: 0.8611
[1m155/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6422 - loss: 0.8581
[1m187/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6431 - loss: 0.8550
[1m219/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6440 - loss: 0.8524
[1m247/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6448 - loss: 0.8500
[1m275/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6456 - loss: 0.8482
[1m302/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6462 - loss: 0.8467
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6464 - loss: 0.8462 - val_accuracy: 0.6900 - val_loss: 0.6706
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.7812 - loss: 0.6013
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6934 - loss: 0.7318 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6819 - loss: 0.7623
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6766 - loss: 0.7764
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6739 - loss: 0.7806
[1m145/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6728 - loss: 0.7817
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6722 - loss: 0.7831
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6713 - loss: 0.7849
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6705 - loss: 0.7863
[1m265/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6700 - loss: 0.7871
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6695 - loss: 0.7875
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6694 - loss: 0.7874 - val_accuracy: 0.6879 - val_loss: 0.6589
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.7188 - loss: 0.5826
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6728 - loss: 0.7606 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6736 - loss: 0.7601
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6738 - loss: 0.7606
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6736 - loss: 0.7618
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6740 - loss: 0.7634
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6740 - loss: 0.7647
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6741 - loss: 0.7648
[1m234/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6741 - loss: 0.7644
[1m265/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6737 - loss: 0.7643
[1m295/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6733 - loss: 0.7640
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6731 - loss: 0.7638 - val_accuracy: 0.6868 - val_loss: 0.6557
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7188 - loss: 0.7479
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6693 - loss: 0.7287 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6688 - loss: 0.7326
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6704 - loss: 0.7320
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6716 - loss: 0.7297
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6723 - loss: 0.7288
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6728 - loss: 0.7286
[1m209/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6733 - loss: 0.7283
[1m239/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6741 - loss: 0.7280
[1m270/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6746 - loss: 0.7276
[1m297/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6750 - loss: 0.7274
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6752 - loss: 0.7273 - val_accuracy: 0.6956 - val_loss: 0.6540
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.5938 - loss: 0.7788
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6849 - loss: 0.7059 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6782 - loss: 0.7137
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6772 - loss: 0.7152
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6774 - loss: 0.7160
[1m145/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6783 - loss: 0.7169
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6783 - loss: 0.7193
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6782 - loss: 0.7210
[1m236/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6785 - loss: 0.7214
[1m265/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6790 - loss: 0.7211
[1m296/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6796 - loss: 0.7203
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6800 - loss: 0.7199 - val_accuracy: 0.6826 - val_loss: 0.6623
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7500 - loss: 0.6726
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7188 - loss: 0.7002 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6975 - loss: 0.7131
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6916 - loss: 0.7136
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6901 - loss: 0.7107
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6900 - loss: 0.7081
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6903 - loss: 0.7059
[1m210/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6912 - loss: 0.7034
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6919 - loss: 0.7014
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6926 - loss: 0.6996
[1m299/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6932 - loss: 0.6978
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6934 - loss: 0.6973 - val_accuracy: 0.6889 - val_loss: 0.6536
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6875 - loss: 0.7061
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7187 - loss: 0.6959 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7151 - loss: 0.6811
[1m 92/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7136 - loss: 0.6787
[1m123/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7126 - loss: 0.6759
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7119 - loss: 0.6740
[1m182/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7112 - loss: 0.6727
[1m211/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7107 - loss: 0.6716
[1m241/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7101 - loss: 0.6709
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7097 - loss: 0.6706
[1m295/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7094 - loss: 0.6702
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7093 - loss: 0.6700 - val_accuracy: 0.6896 - val_loss: 0.6621
Epoch 10/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6562 - loss: 0.8720
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6993 - loss: 0.6723 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7017 - loss: 0.6607
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6997 - loss: 0.6632
[1m124/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7004 - loss: 0.6627
[1m155/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7016 - loss: 0.6622
[1m186/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7026 - loss: 0.6612
[1m217/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7033 - loss: 0.6604
[1m250/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7039 - loss: 0.6593
[1m281/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7046 - loss: 0.6582
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7051 - loss: 0.6574
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7051 - loss: 0.6574 - val_accuracy: 0.6945 - val_loss: 0.6673
Epoch 11/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.7188 - loss: 0.7858
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7256 - loss: 0.6581 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7218 - loss: 0.6505
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7195 - loss: 0.6493
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7200 - loss: 0.6466
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7206 - loss: 0.6441
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7209 - loss: 0.6419
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7215 - loss: 0.6399
[1m237/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7220 - loss: 0.6382
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7223 - loss: 0.6372
[1m297/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7225 - loss: 0.6367
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7226 - loss: 0.6366 - val_accuracy: 0.6994 - val_loss: 0.6685
Epoch 12/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6875 - loss: 0.6490
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7328 - loss: 0.5825 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7289 - loss: 0.5994
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7286 - loss: 0.6004
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7273 - loss: 0.6028
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7261 - loss: 0.6059
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7255 - loss: 0.6086
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7250 - loss: 0.6102
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7246 - loss: 0.6115
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7246 - loss: 0.6122
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7245 - loss: 0.6131
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7245 - loss: 0.6135 - val_accuracy: 0.7001 - val_loss: 0.6765
Epoch 13/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7812 - loss: 0.4640
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7555 - loss: 0.6071 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7500 - loss: 0.6210
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7467 - loss: 0.6185
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7457 - loss: 0.6154
[1m141/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7452 - loss: 0.6137
[1m173/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7449 - loss: 0.6124
[1m204/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7443 - loss: 0.6111
[1m230/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7438 - loss: 0.6100
[1m261/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7432 - loss: 0.6089
[1m290/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7426 - loss: 0.6085
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7421 - loss: 0.6082 - val_accuracy: 0.7005 - val_loss: 0.6755

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 493ms/step2025-11-08 14:57:41.032673: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 24ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 24ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:31[0m 1s/step
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 850us/step
[1m116/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 878us/step
[1m168/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 907us/step
[1m216/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 941us/step
[1m272/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 933us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 22ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 22ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m57/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 898us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 71.66 [%]
Global F1 score (validation) = 72.46 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[2.66682714e-01 6.46595478e-01 1.43071599e-02 7.24145696e-02]
 [1.09772965e-01 8.54250133e-01 5.17872488e-03 3.07982564e-02]
 [5.98707914e-01 3.23036253e-01 5.00387326e-02 2.82170903e-02]
 ...
 [8.46352836e-04 7.26409839e-04 1.40420604e-03 9.97023046e-01]
 [6.63394458e-04 7.45481579e-04 2.40637735e-03 9.96184647e-01]
 [1.50463097e-02 1.20723862e-02 5.40080488e-01 4.32800829e-01]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 77.12 [%]
Global accuracy score (test) = 73.98 [%]
Global F1 score (train) = 77.44 [%]
Global F1 score (test) = 74.69 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.58      0.57      0.58       350
MODERATE-INTENSITY       0.54      0.58      0.56       350
         SEDENTARY       0.98      0.99      0.98       350
VIGOROUS-INTENSITY       0.91      0.83      0.87       299

          accuracy                           0.74      1349
         macro avg       0.75      0.74      0.75      1349
      weighted avg       0.75      0.74      0.74      1349


Accuracy capturado en la ejecución 13: 73.98 [%]
F1-score capturado en la ejecución 13: 74.69 [%]

=== EJECUCIÓN 14 ===

--- TRAIN (ejecución 14) ---

--- TEST (ejecución 14) ---
2025-11-08 14:57:52.006996: 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`.
2025-11-08 14:57:52.018293: 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 00:00:1762610272.031477  996718 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762610272.035576  996718 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762610272.045282  996718 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610272.045299  996718 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610272.045301  996718 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610272.045302  996718 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 14:57:52.048424: 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 00:00:1762610274.239969  996718 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762610276.706947  996850 service.cc:152] XLA service 0x7c5cb8013ae0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762610276.706992  996850 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 14:57:56.756897: 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 00:00:1762610277.067655  996850 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762610279.430078  996850 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:27[0m 5s/step - accuracy: 0.2812 - loss: 2.2718
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2929 - loss: 1.8732  
[1m 54/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3422 - loss: 1.7321
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3729 - loss: 1.6433
[1m116/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3938 - loss: 1.5822
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4104 - loss: 1.5327
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4220 - loss: 1.4977
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4334 - loss: 1.4641
[1m233/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4420 - loss: 1.4385
[1m261/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4494 - loss: 1.4157
[1m291/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4567 - loss: 1.3937
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4609 - loss: 1.3810
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 14ms/step - accuracy: 0.4611 - loss: 1.3803 - val_accuracy: 0.6777 - val_loss: 0.7292
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.6250 - loss: 1.0091
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6136 - loss: 0.9823 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6178 - loss: 0.9622
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6187 - loss: 0.9430
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6184 - loss: 0.9352
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6183 - loss: 0.9303
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6180 - loss: 0.9266
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6178 - loss: 0.9236
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6177 - loss: 0.9219
[1m264/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6179 - loss: 0.9200
[1m294/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6183 - loss: 0.9181
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6185 - loss: 0.9172 - val_accuracy: 0.6843 - val_loss: 0.6400
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7188 - loss: 0.6478
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6490 - loss: 0.8401 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6507 - loss: 0.8637
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6494 - loss: 0.8714
[1m125/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6501 - loss: 0.8715
[1m158/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6503 - loss: 0.8697
[1m190/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6504 - loss: 0.8672
[1m222/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6505 - loss: 0.8644
[1m252/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6505 - loss: 0.8626
[1m282/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6502 - loss: 0.8610
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6499 - loss: 0.8598 - val_accuracy: 0.6980 - val_loss: 0.6285
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.6562 - loss: 0.7203
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6446 - loss: 0.7567 
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6557 - loss: 0.7664
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6570 - loss: 0.7767
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6565 - loss: 0.7835
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6565 - loss: 0.7854
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6564 - loss: 0.7867
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6563 - loss: 0.7879
[1m232/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6562 - loss: 0.7883
[1m258/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6563 - loss: 0.7884
[1m283/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6564 - loss: 0.7882
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6566 - loss: 0.7879 - val_accuracy: 0.7058 - val_loss: 0.6141
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.5000 - loss: 1.0563
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6442 - loss: 0.8433 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6555 - loss: 0.8050
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6604 - loss: 0.7948
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6626 - loss: 0.7914
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6641 - loss: 0.7872
[1m185/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6653 - loss: 0.7820
[1m218/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6662 - loss: 0.7780
[1m249/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6666 - loss: 0.7754
[1m279/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6670 - loss: 0.7733
[1m306/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6671 - loss: 0.7715
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6671 - loss: 0.7713 - val_accuracy: 0.7005 - val_loss: 0.6239
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7812 - loss: 0.5922
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6805 - loss: 0.7338 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6817 - loss: 0.7317
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6800 - loss: 0.7300
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6783 - loss: 0.7310
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6767 - loss: 0.7329
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6760 - loss: 0.7344
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6755 - loss: 0.7353
[1m240/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6752 - loss: 0.7357
[1m270/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6748 - loss: 0.7363
[1m300/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6746 - loss: 0.7370
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6746 - loss: 0.7372 - val_accuracy: 0.7040 - val_loss: 0.6151
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6875 - loss: 0.8240
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7210 - loss: 0.6876 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7039 - loss: 0.7134
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6934 - loss: 0.7244
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6887 - loss: 0.7264
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6853 - loss: 0.7263
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6831 - loss: 0.7261
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6818 - loss: 0.7262
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6811 - loss: 0.7256
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6808 - loss: 0.7249
[1m299/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6808 - loss: 0.7242
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6809 - loss: 0.7240 - val_accuracy: 0.6931 - val_loss: 0.6296
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6250 - loss: 0.6432
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6759 - loss: 0.6888 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6734 - loss: 0.7060
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6747 - loss: 0.7068
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6744 - loss: 0.7081
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6751 - loss: 0.7065
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6753 - loss: 0.7061
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6759 - loss: 0.7049
[1m244/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6763 - loss: 0.7046
[1m273/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6767 - loss: 0.7041
[1m303/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6773 - loss: 0.7039
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6775 - loss: 0.7038 - val_accuracy: 0.7121 - val_loss: 0.6284
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5000 - loss: 1.3174
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6822 - loss: 0.7567 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6978 - loss: 0.7158
[1m 92/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7027 - loss: 0.7031
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7043 - loss: 0.6964
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7046 - loss: 0.6930
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7046 - loss: 0.6914
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7043 - loss: 0.6905
[1m237/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7039 - loss: 0.6891
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7037 - loss: 0.6878
[1m296/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7037 - loss: 0.6866
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7037 - loss: 0.6860 - val_accuracy: 0.7110 - val_loss: 0.6189

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 504ms/step2025-11-08 14:58:10.392161: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 24ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 24ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:45[0m 1s/step
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 887us/step
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 862us/step
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 875us/step
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 862us/step
[1m297/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 851us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 17ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 22ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 22ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m59/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 866us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 70.15 [%]
Global F1 score (validation) = 71.25 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[2.79323786e-01 7.14050233e-01 7.31546548e-04 5.89443743e-03]
 [1.92136332e-01 6.61126196e-01 5.78875421e-03 1.40948713e-01]
 [6.98898852e-01 2.48842508e-01 2.95870658e-02 2.26715598e-02]
 ...
 [2.93915090e-03 3.84435314e-03 9.05557070e-03 9.84160960e-01]
 [9.64940293e-04 2.87517643e-04 3.65828699e-03 9.95089173e-01]
 [1.32667525e-02 1.21941203e-02 9.08667743e-01 6.58713654e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 75.77 [%]
Global accuracy score (test) = 72.5 [%]
Global F1 score (train) = 76.06 [%]
Global F1 score (test) = 73.55 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.53      0.61      0.57       350
MODERATE-INTENSITY       0.51      0.49      0.50       350
         SEDENTARY       0.98      0.98      0.98       350
VIGOROUS-INTENSITY       0.96      0.83      0.89       299

          accuracy                           0.72      1349
         macro avg       0.75      0.73      0.74      1349
      weighted avg       0.74      0.72      0.73      1349


Accuracy capturado en la ejecución 14: 72.5 [%]
F1-score capturado en la ejecución 14: 73.55 [%]

=== EJECUCIÓN 15 ===

--- TRAIN (ejecución 15) ---

--- TEST (ejecución 15) ---
2025-11-08 14:58:21.359998: 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`.
2025-11-08 14:58:21.371352: 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 00:00:1762610301.384417  998555 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762610301.388583  998555 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762610301.398243  998555 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610301.398258  998555 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610301.398260  998555 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610301.398261  998555 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 14:58:21.401395: 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 00:00:1762610303.610006  998555 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762610306.078683  998687 service.cc:152] XLA service 0x761290006850 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762610306.078711  998687 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 14:58:26.129577: 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 00:00:1762610306.451347  998687 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762610308.819729  998687 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:38[0m 5s/step - accuracy: 0.1875 - loss: 1.8349
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3098 - loss: 1.6619  
[1m 54/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3515 - loss: 1.5683
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3867 - loss: 1.4885
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4107 - loss: 1.4365
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4287 - loss: 1.3983
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4407 - loss: 1.3726
[1m211/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4514 - loss: 1.3492
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4598 - loss: 1.3309
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4674 - loss: 1.3139
[1m299/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4749 - loss: 1.2975
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4772 - loss: 1.2922
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 13ms/step - accuracy: 0.4774 - loss: 1.2917 - val_accuracy: 0.6640 - val_loss: 0.7032
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5000 - loss: 1.1354
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5655 - loss: 1.0313 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5808 - loss: 0.9942
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5881 - loss: 0.9796
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5926 - loss: 0.9731
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5961 - loss: 0.9695
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5995 - loss: 0.9651
[1m209/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6027 - loss: 0.9607
[1m237/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6051 - loss: 0.9566
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6073 - loss: 0.9522
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6091 - loss: 0.9484
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6097 - loss: 0.9469 - val_accuracy: 0.6787 - val_loss: 0.6463
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7188 - loss: 1.0207
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6488 - loss: 0.8570 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6481 - loss: 0.8485
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6469 - loss: 0.8490
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6455 - loss: 0.8511
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6449 - loss: 0.8511
[1m183/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6454 - loss: 0.8496
[1m214/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6458 - loss: 0.8485
[1m240/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6462 - loss: 0.8477
[1m270/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6467 - loss: 0.8467
[1m295/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6470 - loss: 0.8459
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6472 - loss: 0.8453 - val_accuracy: 0.6819 - val_loss: 0.6442
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.6875 - loss: 0.6578
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6295 - loss: 0.8134 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6357 - loss: 0.8228
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6426 - loss: 0.8182
[1m123/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6458 - loss: 0.8148
[1m154/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6475 - loss: 0.8122
[1m184/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6492 - loss: 0.8094
[1m211/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6509 - loss: 0.8070
[1m239/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6523 - loss: 0.8043
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6534 - loss: 0.8018
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6541 - loss: 0.8002
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6543 - loss: 0.7998 - val_accuracy: 0.6854 - val_loss: 0.6407
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6875 - loss: 0.6629
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6568 - loss: 0.7457 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6558 - loss: 0.7612
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6548 - loss: 0.7649
[1m116/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6550 - loss: 0.7658
[1m145/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6557 - loss: 0.7641
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6561 - loss: 0.7642
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6568 - loss: 0.7638
[1m237/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6571 - loss: 0.7640
[1m262/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6575 - loss: 0.7641
[1m289/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6579 - loss: 0.7642
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6582 - loss: 0.7640 - val_accuracy: 0.6900 - val_loss: 0.6397
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7188 - loss: 0.8472
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6766 - loss: 0.7573 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6814 - loss: 0.7477
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6850 - loss: 0.7360
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6853 - loss: 0.7333
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6859 - loss: 0.7301
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6867 - loss: 0.7275
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6872 - loss: 0.7256
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6876 - loss: 0.7243
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6878 - loss: 0.7240
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6879 - loss: 0.7236
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6880 - loss: 0.7235 - val_accuracy: 0.6868 - val_loss: 0.6375
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5938 - loss: 0.8964
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6612 - loss: 0.7040 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6750 - loss: 0.6963
[1m 83/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6796 - loss: 0.6935
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6823 - loss: 0.6931
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6843 - loss: 0.6925
[1m175/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6861 - loss: 0.6915
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6873 - loss: 0.6916
[1m236/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6878 - loss: 0.6924
[1m265/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6884 - loss: 0.6927
[1m295/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6887 - loss: 0.6931
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6889 - loss: 0.6934 - val_accuracy: 0.6854 - val_loss: 0.6342
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.7188 - loss: 0.5274
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6958 - loss: 0.6648 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6966 - loss: 0.6801
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6992 - loss: 0.6853
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6993 - loss: 0.6881
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6995 - loss: 0.6891
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6995 - loss: 0.6890
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6996 - loss: 0.6885
[1m239/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6996 - loss: 0.6884
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6993 - loss: 0.6883
[1m296/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6991 - loss: 0.6878
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6991 - loss: 0.6875 - val_accuracy: 0.6921 - val_loss: 0.6463
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7188 - loss: 0.7087
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7178 - loss: 0.6489 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7070 - loss: 0.6597
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7028 - loss: 0.6630
[1m124/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7015 - loss: 0.6648
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7012 - loss: 0.6663
[1m185/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7010 - loss: 0.6681
[1m217/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7007 - loss: 0.6698
[1m248/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7005 - loss: 0.6706
[1m278/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7005 - loss: 0.6710
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7006 - loss: 0.6710
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7006 - loss: 0.6710 - val_accuracy: 0.6910 - val_loss: 0.6449
Epoch 10/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5312 - loss: 0.5897
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6717 - loss: 0.6214 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6848 - loss: 0.6294
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6885 - loss: 0.6371
[1m124/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6912 - loss: 0.6415
[1m155/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6936 - loss: 0.6448
[1m186/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6955 - loss: 0.6466
[1m217/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6973 - loss: 0.6468
[1m246/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6989 - loss: 0.6467
[1m277/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7001 - loss: 0.6470
[1m309/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7011 - loss: 0.6475
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7012 - loss: 0.6475 - val_accuracy: 0.6900 - val_loss: 0.6449
Epoch 11/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6562 - loss: 0.4775
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7010 - loss: 0.6161 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7053 - loss: 0.6420
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7122 - loss: 0.6418
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7163 - loss: 0.6400
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7172 - loss: 0.6403
[1m183/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7177 - loss: 0.6409
[1m216/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7183 - loss: 0.6405
[1m246/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7187 - loss: 0.6398
[1m276/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7190 - loss: 0.6392
[1m306/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7192 - loss: 0.6385
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7192 - loss: 0.6385 - val_accuracy: 0.6942 - val_loss: 0.6462
Epoch 12/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.8750 - loss: 0.3957
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7585 - loss: 0.5932 
[1m 64/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7515 - loss: 0.6072
[1m 96/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7461 - loss: 0.6122
[1m129/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7421 - loss: 0.6150
[1m158/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7396 - loss: 0.6173
[1m189/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7373 - loss: 0.6190
[1m220/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7356 - loss: 0.6203
[1m253/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7346 - loss: 0.6210
[1m285/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7336 - loss: 0.6215
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7329 - loss: 0.6217 - val_accuracy: 0.6896 - val_loss: 0.6523

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 496ms/step2025-11-08 14:58:41.805923: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 24ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 25ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:39[0m 1s/step
[1m 54/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 950us/step
[1m111/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 919us/step
[1m172/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 884us/step
[1m233/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 868us/step
[1m292/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 864us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 17ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 22ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 23ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m52/89[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 995us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 70.08 [%]
Global F1 score (validation) = 71.33 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[6.1804795e-01 3.5575914e-01 1.4824029e-02 1.1368804e-02]
 [4.7709569e-01 4.9414945e-01 1.3359796e-02 1.5395065e-02]
 [3.7330574e-01 5.9390438e-01 6.1155544e-03 2.6674388e-02]
 ...
 [8.8123394e-05 1.1683931e-04 1.7402457e-03 9.9805480e-01]
 [2.1901361e-04 3.5318144e-04 1.0356425e-03 9.9839216e-01]
 [1.4459230e-03 1.9985999e-03 8.9953816e-01 9.7017258e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 73.68 [%]
Global accuracy score (test) = 70.57 [%]
Global F1 score (train) = 74.1 [%]
Global F1 score (test) = 71.83 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.52      0.47      0.49       350
MODERATE-INTENSITY       0.48      0.60      0.53       350
         SEDENTARY       0.98      0.97      0.97       350
VIGOROUS-INTENSITY       0.96      0.80      0.87       299

          accuracy                           0.71      1349
         macro avg       0.74      0.71      0.72      1349
      weighted avg       0.73      0.71      0.71      1349


Accuracy capturado en la ejecución 15: 70.57 [%]
F1-score capturado en la ejecución 15: 71.83 [%]

=== EJECUCIÓN 16 ===

--- TRAIN (ejecución 16) ---

--- TEST (ejecución 16) ---
2025-11-08 14:58:52.703901: 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`.
2025-11-08 14:58:52.715120: 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 00:00:1762610332.728351 1000674 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762610332.732601 1000674 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762610332.742394 1000674 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610332.742411 1000674 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610332.742413 1000674 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610332.742414 1000674 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 14:58:52.745573: 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 00:00:1762610334.963176 1000674 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762610337.425630 1000805 service.cc:152] XLA service 0x756680027720 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762610337.425684 1000805 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 14:58:57.482903: 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 00:00:1762610337.790769 1000805 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762610340.159259 1000805 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:23[0m 5s/step - accuracy: 0.1562 - loss: 2.1114
[1m 25/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2989 - loss: 1.7461  
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3684 - loss: 1.5755
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4018 - loss: 1.4905
[1m123/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4229 - loss: 1.4371
[1m155/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4394 - loss: 1.3957
[1m187/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4518 - loss: 1.3633
[1m218/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4615 - loss: 1.3376
[1m250/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4703 - loss: 1.3147
[1m282/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4778 - loss: 1.2952
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4837 - loss: 1.2799
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 14ms/step - accuracy: 0.4839 - loss: 1.2794 - val_accuracy: 0.6545 - val_loss: 0.7320
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6562 - loss: 0.8677
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5858 - loss: 1.0097 
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5923 - loss: 0.9976
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5985 - loss: 0.9795
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6031 - loss: 0.9652
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6067 - loss: 0.9533
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6087 - loss: 0.9458
[1m210/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6101 - loss: 0.9398
[1m241/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6111 - loss: 0.9358
[1m273/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6120 - loss: 0.9324
[1m301/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6129 - loss: 0.9294
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6132 - loss: 0.9284 - val_accuracy: 0.6745 - val_loss: 0.6685
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5938 - loss: 1.0016
[1m 32/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6532 - loss: 0.8724 
[1m 63/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6491 - loss: 0.8572
[1m 92/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6492 - loss: 0.8532
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6496 - loss: 0.8498
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6495 - loss: 0.8477
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6484 - loss: 0.8482
[1m211/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6478 - loss: 0.8482
[1m237/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6478 - loss: 0.8471
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6481 - loss: 0.8449
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6486 - loss: 0.8426
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6488 - loss: 0.8416 - val_accuracy: 0.6784 - val_loss: 0.6525
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6562 - loss: 0.8472
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6425 - loss: 0.8034 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6442 - loss: 0.8094
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6455 - loss: 0.8066
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6488 - loss: 0.8019
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6503 - loss: 0.8008
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6515 - loss: 0.8003
[1m209/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6526 - loss: 0.7996
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6539 - loss: 0.7984
[1m272/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6548 - loss: 0.7974
[1m305/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6557 - loss: 0.7963
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6559 - loss: 0.7961 - val_accuracy: 0.6836 - val_loss: 0.6384
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 23ms/step - accuracy: 0.7812 - loss: 0.6706
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6905 - loss: 0.7135 
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6804 - loss: 0.7318
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6770 - loss: 0.7408
[1m110/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6776 - loss: 0.7436
[1m141/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6792 - loss: 0.7418
[1m172/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6803 - loss: 0.7412
[1m202/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6805 - loss: 0.7413
[1m230/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6805 - loss: 0.7413
[1m260/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6803 - loss: 0.7415
[1m289/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6799 - loss: 0.7417
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6797 - loss: 0.7419 - val_accuracy: 0.6857 - val_loss: 0.6424
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7188 - loss: 0.5417
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6664 - loss: 0.7505 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6659 - loss: 0.7512
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6697 - loss: 0.7467
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6729 - loss: 0.7443
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6756 - loss: 0.7422
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6774 - loss: 0.7406
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6789 - loss: 0.7389
[1m234/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6797 - loss: 0.7382
[1m263/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6803 - loss: 0.7374
[1m295/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6806 - loss: 0.7368
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6807 - loss: 0.7365 - val_accuracy: 0.6886 - val_loss: 0.6373
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7188 - loss: 0.5632
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7086 - loss: 0.6754 
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7040 - loss: 0.6866
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7003 - loss: 0.6932
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6982 - loss: 0.6957
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6972 - loss: 0.6980
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6965 - loss: 0.7000
[1m210/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6957 - loss: 0.7017
[1m241/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6953 - loss: 0.7022
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6949 - loss: 0.7027
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6944 - loss: 0.7037
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6942 - loss: 0.7041 - val_accuracy: 0.6931 - val_loss: 0.6413
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.9062 - loss: 0.4121
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7089 - loss: 0.6430 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7010 - loss: 0.6665
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6995 - loss: 0.6721
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7010 - loss: 0.6733
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7015 - loss: 0.6744
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7021 - loss: 0.6746
[1m210/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7027 - loss: 0.6749
[1m241/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7026 - loss: 0.6757
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7025 - loss: 0.6766
[1m302/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7021 - loss: 0.6775
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7021 - loss: 0.6777 - val_accuracy: 0.6963 - val_loss: 0.6479
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.6250 - loss: 0.7964
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6881 - loss: 0.7554 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6970 - loss: 0.7229
[1m 92/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7011 - loss: 0.7052
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7031 - loss: 0.6950
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7042 - loss: 0.6886
[1m182/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7047 - loss: 0.6854
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7047 - loss: 0.6837
[1m243/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7044 - loss: 0.6826
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7040 - loss: 0.6819
[1m304/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7037 - loss: 0.6815
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7036 - loss: 0.6814 - val_accuracy: 0.6977 - val_loss: 0.6438
Epoch 10/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6875 - loss: 0.8251
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6990 - loss: 0.6981 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6951 - loss: 0.6878
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6987 - loss: 0.6791
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7018 - loss: 0.6736
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7038 - loss: 0.6695
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7052 - loss: 0.6661
[1m210/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7065 - loss: 0.6634
[1m239/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7079 - loss: 0.6609
[1m270/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7088 - loss: 0.6593
[1m301/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7097 - loss: 0.6580
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7099 - loss: 0.6577 - val_accuracy: 0.6945 - val_loss: 0.6581
Epoch 11/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.7500 - loss: 0.5737
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7192 - loss: 0.6338 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7169 - loss: 0.6438
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7202 - loss: 0.6419
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7223 - loss: 0.6413
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7232 - loss: 0.6401
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7238 - loss: 0.6393
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7235 - loss: 0.6398
[1m237/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7236 - loss: 0.6396
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7236 - loss: 0.6393
[1m296/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7234 - loss: 0.6392
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7232 - loss: 0.6390 - val_accuracy: 0.6917 - val_loss: 0.6491

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 493ms/step2025-11-08 14:59:12.541457: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 25ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 25ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:44[0m 1s/step
[1m 54/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 959us/step
[1m112/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 912us/step
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 878us/step
[1m228/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 890us/step
[1m291/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 870us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 21ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 22ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m54/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 950us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 69.21 [%]
Global F1 score (validation) = 70.21 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[6.0726106e-01 3.4127247e-01 3.0751046e-02 2.0715501e-02]
 [5.4007578e-01 4.1862687e-01 1.7989250e-02 2.3308177e-02]
 [6.0089839e-01 3.5721096e-01 2.1700175e-02 2.0190420e-02]
 ...
 [3.0032306e-05 3.3161043e-05 2.4411891e-04 9.9969274e-01]
 [2.7966482e-04 1.6004237e-04 1.7282064e-03 9.9783212e-01]
 [5.5373642e-03 4.2519253e-03 8.8817155e-01 1.0203917e-01]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 75.51 [%]
Global accuracy score (test) = 73.46 [%]
Global F1 score (train) = 75.87 [%]
Global F1 score (test) = 74.35 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.55      0.61      0.58       350
MODERATE-INTENSITY       0.53      0.52      0.52       350
         SEDENTARY       0.98      0.98      0.98       350
VIGOROUS-INTENSITY       0.94      0.84      0.89       299

          accuracy                           0.73      1349
         macro avg       0.75      0.74      0.74      1349
      weighted avg       0.74      0.73      0.74      1349


Accuracy capturado en la ejecución 16: 73.46 [%]
F1-score capturado en la ejecución 16: 74.35 [%]

=== EJECUCIÓN 17 ===

--- TRAIN (ejecución 17) ---

--- TEST (ejecución 17) ---
2025-11-08 14:59:23.414934: 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`.
2025-11-08 14:59:23.425959: 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 00:00:1762610363.438988 1002719 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762610363.443000 1002719 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762610363.453072 1002719 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610363.453089 1002719 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610363.453090 1002719 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610363.453091 1002719 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 14:59:23.456071: 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 00:00:1762610365.675271 1002719 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762610368.131895 1002848 service.cc:152] XLA service 0x7f0984002800 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762610368.131920 1002848 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 14:59:28.181244: 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 00:00:1762610368.491956 1002848 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762610370.842833 1002848 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:22[0m 5s/step - accuracy: 0.1562 - loss: 1.9514
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2966 - loss: 1.8154  
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3377 - loss: 1.7098
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3641 - loss: 1.6431
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3840 - loss: 1.5911
[1m145/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4000 - loss: 1.5489
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4129 - loss: 1.5130
[1m209/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4236 - loss: 1.4830
[1m240/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4325 - loss: 1.4577
[1m273/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4411 - loss: 1.4334
[1m303/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4482 - loss: 1.4139
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4498 - loss: 1.4096
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 13ms/step - accuracy: 0.4500 - loss: 1.4089 - val_accuracy: 0.6496 - val_loss: 0.7563
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.5000 - loss: 1.2083
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5956 - loss: 1.0339 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6037 - loss: 1.0103
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6090 - loss: 0.9943
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6106 - loss: 0.9865
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6102 - loss: 0.9827
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6097 - loss: 0.9800
[1m211/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6097 - loss: 0.9771
[1m245/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6098 - loss: 0.9745
[1m276/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6103 - loss: 0.9713
[1m305/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6110 - loss: 0.9684
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6112 - loss: 0.9679 - val_accuracy: 0.6636 - val_loss: 0.7223
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6875 - loss: 0.6197
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6358 - loss: 0.8626 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6351 - loss: 0.8743
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6339 - loss: 0.8802
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6331 - loss: 0.8835
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6330 - loss: 0.8840
[1m183/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6334 - loss: 0.8827
[1m214/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6338 - loss: 0.8809
[1m244/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6343 - loss: 0.8790
[1m272/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6347 - loss: 0.8772
[1m303/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6353 - loss: 0.8753
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6354 - loss: 0.8750 - val_accuracy: 0.6675 - val_loss: 0.6872
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5312 - loss: 1.0974
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6616 - loss: 0.8178 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6610 - loss: 0.8162
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6616 - loss: 0.8132
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6605 - loss: 0.8130
[1m143/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6596 - loss: 0.8127
[1m172/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6585 - loss: 0.8131
[1m202/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6580 - loss: 0.8131
[1m232/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6576 - loss: 0.8126
[1m261/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6573 - loss: 0.8119
[1m289/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6571 - loss: 0.8110
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6570 - loss: 0.8107 - val_accuracy: 0.6650 - val_loss: 0.6906
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 23ms/step - accuracy: 0.6562 - loss: 0.6697
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6977 - loss: 0.7228 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6889 - loss: 0.7381
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6810 - loss: 0.7460
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6760 - loss: 0.7543
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6744 - loss: 0.7583
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6729 - loss: 0.7613
[1m204/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6711 - loss: 0.7645
[1m234/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6700 - loss: 0.7665
[1m264/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6694 - loss: 0.7676
[1m295/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6690 - loss: 0.7686
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6689 - loss: 0.7688 - val_accuracy: 0.6808 - val_loss: 0.6612
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6875 - loss: 0.8961
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6773 - loss: 0.7542 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6834 - loss: 0.7350
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6836 - loss: 0.7341
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6843 - loss: 0.7321
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6848 - loss: 0.7311
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6851 - loss: 0.7306
[1m211/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6851 - loss: 0.7304
[1m240/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6851 - loss: 0.7303
[1m272/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6848 - loss: 0.7309
[1m302/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6846 - loss: 0.7313
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6845 - loss: 0.7314 - val_accuracy: 0.6777 - val_loss: 0.6656
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.6562 - loss: 0.9208
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6451 - loss: 0.7763 
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6532 - loss: 0.7641
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6615 - loss: 0.7541
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6653 - loss: 0.7495
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6680 - loss: 0.7453
[1m173/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6710 - loss: 0.7406
[1m202/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6730 - loss: 0.7374
[1m231/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6745 - loss: 0.7351
[1m263/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6758 - loss: 0.7335
[1m291/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6767 - loss: 0.7325
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6773 - loss: 0.7318 - val_accuracy: 0.6703 - val_loss: 0.6607
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7812 - loss: 0.6001
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6946 - loss: 0.7258 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6910 - loss: 0.7340
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6895 - loss: 0.7369
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6887 - loss: 0.7350
[1m146/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6885 - loss: 0.7323
[1m173/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6889 - loss: 0.7299
[1m204/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6890 - loss: 0.7277
[1m234/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6890 - loss: 0.7262
[1m266/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6892 - loss: 0.7246
[1m295/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6895 - loss: 0.7232
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6896 - loss: 0.7225 - val_accuracy: 0.6826 - val_loss: 0.6519
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7500 - loss: 0.5736
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6951 - loss: 0.6895 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7030 - loss: 0.6908
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7076 - loss: 0.6904
[1m123/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7113 - loss: 0.6855
[1m154/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7130 - loss: 0.6826
[1m185/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7129 - loss: 0.6813
[1m218/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7127 - loss: 0.6800
[1m249/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7124 - loss: 0.6792
[1m276/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7125 - loss: 0.6785
[1m309/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7126 - loss: 0.6773
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7127 - loss: 0.6773 - val_accuracy: 0.6699 - val_loss: 0.6674
Epoch 10/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.6562 - loss: 0.8811
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7108 - loss: 0.6781 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7155 - loss: 0.6606
[1m 92/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7164 - loss: 0.6612
[1m123/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7173 - loss: 0.6598
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7179 - loss: 0.6595
[1m182/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7181 - loss: 0.6596
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7180 - loss: 0.6597
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7180 - loss: 0.6595
[1m273/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7180 - loss: 0.6590
[1m304/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7179 - loss: 0.6587
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7179 - loss: 0.6586 - val_accuracy: 0.6847 - val_loss: 0.6615
Epoch 11/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.8438 - loss: 0.4264
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7675 - loss: 0.5960 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7552 - loss: 0.6108
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7490 - loss: 0.6212
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7450 - loss: 0.6246
[1m155/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7414 - loss: 0.6274
[1m186/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7394 - loss: 0.6292
[1m219/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7376 - loss: 0.6311
[1m252/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7363 - loss: 0.6320
[1m285/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7348 - loss: 0.6331
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7339 - loss: 0.6336 - val_accuracy: 0.6829 - val_loss: 0.6770
Epoch 12/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6875 - loss: 0.8086
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7326 - loss: 0.6280 
[1m 63/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7343 - loss: 0.6294
[1m 94/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7365 - loss: 0.6248
[1m124/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7376 - loss: 0.6214
[1m155/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7384 - loss: 0.6188
[1m185/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7386 - loss: 0.6180
[1m215/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7389 - loss: 0.6176
[1m244/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7391 - loss: 0.6174
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7392 - loss: 0.6172
[1m297/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7392 - loss: 0.6172
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7391 - loss: 0.6172 - val_accuracy: 0.6721 - val_loss: 0.6944
Epoch 13/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6875 - loss: 0.6436
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7086 - loss: 0.6577 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7177 - loss: 0.6379
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7216 - loss: 0.6304
[1m113/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7244 - loss: 0.6246
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7266 - loss: 0.6199
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7281 - loss: 0.6170
[1m203/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7294 - loss: 0.6152
[1m231/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7306 - loss: 0.6137
[1m260/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7316 - loss: 0.6122
[1m291/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7324 - loss: 0.6112
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7327 - loss: 0.6109 - val_accuracy: 0.6938 - val_loss: 0.6895

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 490ms/step2025-11-08 14:59:44.525304: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 24ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 24ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:35[0m 1s/step
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 935us/step
[1m111/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 919us/step
[1m171/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 892us/step
[1m228/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 889us/step
[1m288/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 877us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 21ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 22ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m53/89[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 978us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 69.24 [%]
Global F1 score (validation) = 69.44 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[6.5047532e-01 3.1009701e-01 2.1966716e-02 1.7460918e-02]
 [6.5625322e-01 3.0570477e-01 2.1591539e-02 1.6450433e-02]
 [6.4761889e-01 3.0049348e-01 3.2716405e-02 1.9171210e-02]
 ...
 [8.3356036e-04 1.1353205e-03 1.2049007e-02 9.8598212e-01]
 [1.1470891e-03 3.2382962e-04 5.0921142e-03 9.9343699e-01]
 [1.4667699e-02 8.9139938e-03 8.8874972e-01 8.7668605e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 74.95 [%]
Global accuracy score (test) = 73.68 [%]
Global F1 score (train) = 74.69 [%]
Global F1 score (test) = 74.23 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.54      0.72      0.62       350
MODERATE-INTENSITY       0.53      0.42      0.47       350
         SEDENTARY       0.98      0.99      0.98       350
VIGOROUS-INTENSITY       0.97      0.84      0.90       299

          accuracy                           0.74      1349
         macro avg       0.76      0.74      0.74      1349
      weighted avg       0.75      0.74      0.74      1349


Accuracy capturado en la ejecución 17: 73.68 [%]
F1-score capturado en la ejecución 17: 74.23 [%]

=== EJECUCIÓN 18 ===

--- TRAIN (ejecución 18) ---

--- TEST (ejecución 18) ---
2025-11-08 14:59:55.494855: 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`.
2025-11-08 14:59:55.506012: 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 00:00:1762610395.519049 1004954 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762610395.523107 1004954 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762610395.532900 1004954 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610395.532916 1004954 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610395.532917 1004954 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610395.532918 1004954 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 14:59:55.536009: 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 00:00:1762610397.727914 1004954 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762610400.167326 1005050 service.cc:152] XLA service 0x7e3f14016fc0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762610400.167351 1005050 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 15:00:00.216773: 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 00:00:1762610400.528050 1005050 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762610402.859132 1005050 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:12[0m 5s/step - accuracy: 0.1562 - loss: 2.1754
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2978 - loss: 1.7170  
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3629 - loss: 1.5881
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3965 - loss: 1.5167
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4198 - loss: 1.4622
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4338 - loss: 1.4285
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4458 - loss: 1.3991
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4556 - loss: 1.3748
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4650 - loss: 1.3504
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4730 - loss: 1.3291
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4796 - loss: 1.3117
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4822 - loss: 1.3050
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 14ms/step - accuracy: 0.4824 - loss: 1.3044 - val_accuracy: 0.6489 - val_loss: 0.7178
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6250 - loss: 0.8401
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6390 - loss: 0.9012 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6375 - loss: 0.9106
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6364 - loss: 0.9190
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6367 - loss: 0.9191
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6358 - loss: 0.9200
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6351 - loss: 0.9201
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6346 - loss: 0.9195
[1m236/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6340 - loss: 0.9183
[1m266/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6335 - loss: 0.9169
[1m295/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6329 - loss: 0.9162
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6326 - loss: 0.9160 - val_accuracy: 0.6780 - val_loss: 0.6614
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.6250 - loss: 0.6024
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6236 - loss: 0.9046 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6278 - loss: 0.9041
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6305 - loss: 0.9020
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6328 - loss: 0.8956
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6355 - loss: 0.8877
[1m175/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6372 - loss: 0.8821
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6387 - loss: 0.8766
[1m233/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6398 - loss: 0.8717
[1m260/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6408 - loss: 0.8675
[1m291/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6417 - loss: 0.8638
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6422 - loss: 0.8619 - val_accuracy: 0.6784 - val_loss: 0.6639
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.8125 - loss: 0.5845
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6474 - loss: 0.8602 
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6496 - loss: 0.8454
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6516 - loss: 0.8364
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6529 - loss: 0.8278
[1m145/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6538 - loss: 0.8205
[1m173/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6544 - loss: 0.8156
[1m204/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6545 - loss: 0.8124
[1m236/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6545 - loss: 0.8102
[1m263/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6546 - loss: 0.8084
[1m291/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6548 - loss: 0.8066
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6549 - loss: 0.8055 - val_accuracy: 0.6896 - val_loss: 0.6407
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.5938 - loss: 0.8467
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6380 - loss: 0.8355 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6417 - loss: 0.8226
[1m 92/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6453 - loss: 0.8122
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6483 - loss: 0.8038
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6510 - loss: 0.7964
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6530 - loss: 0.7911
[1m209/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6543 - loss: 0.7880
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6556 - loss: 0.7852
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6566 - loss: 0.7827
[1m296/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6574 - loss: 0.7807
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6578 - loss: 0.7797 - val_accuracy: 0.6833 - val_loss: 0.6413
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6562 - loss: 0.8101
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6715 - loss: 0.7363 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6804 - loss: 0.7175
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6794 - loss: 0.7184
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6777 - loss: 0.7234
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6765 - loss: 0.7274
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6760 - loss: 0.7299
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6759 - loss: 0.7315
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6757 - loss: 0.7331
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6756 - loss: 0.7343
[1m297/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6754 - loss: 0.7351
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6753 - loss: 0.7355 - val_accuracy: 0.6812 - val_loss: 0.6572
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.7500 - loss: 0.6445
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6783 - loss: 0.7214 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6698 - loss: 0.7318
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6656 - loss: 0.7367
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6647 - loss: 0.7376
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6662 - loss: 0.7340
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6672 - loss: 0.7314
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6683 - loss: 0.7291
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6695 - loss: 0.7275
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6708 - loss: 0.7264
[1m302/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6719 - loss: 0.7251
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6722 - loss: 0.7247 - val_accuracy: 0.6893 - val_loss: 0.6440
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6562 - loss: 0.6088
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6512 - loss: 0.7739 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6699 - loss: 0.7390
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6752 - loss: 0.7242
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6768 - loss: 0.7187
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6786 - loss: 0.7165
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6805 - loss: 0.7144
[1m209/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6823 - loss: 0.7122
[1m237/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6834 - loss: 0.7104
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6843 - loss: 0.7086
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6849 - loss: 0.7071
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6851 - loss: 0.7066 - val_accuracy: 0.6850 - val_loss: 0.6517
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.8438 - loss: 0.5145
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7089 - loss: 0.6283 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7102 - loss: 0.6316
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7092 - loss: 0.6366
[1m116/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7070 - loss: 0.6419
[1m145/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7052 - loss: 0.6467
[1m172/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7040 - loss: 0.6497
[1m202/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7031 - loss: 0.6519
[1m233/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7026 - loss: 0.6539
[1m264/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7022 - loss: 0.6561
[1m294/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7017 - loss: 0.6580
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7015 - loss: 0.6590 - val_accuracy: 0.6893 - val_loss: 0.6568

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 491ms/step2025-11-08 15:00:13.873553: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 25ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 25ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:37[0m 1s/step
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 900us/step
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 857us/step
[1m182/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 835us/step
[1m246/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 824us/step
[1m306/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 827us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 17ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 22ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 22ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m62/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 822us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 69.73 [%]
Global F1 score (validation) = 70.23 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[7.75721520e-02 1.01194605e-01 1.29799852e-02 8.08253288e-01]
 [7.22328842e-01 2.13038862e-01 4.74850759e-02 1.71471573e-02]
 [6.73400939e-01 2.76237726e-01 3.23233046e-02 1.80380624e-02]
 ...
 [1.78556261e-03 1.15443615e-03 7.69590028e-03 9.89364147e-01]
 [5.51943784e-04 2.30113015e-04 4.21992224e-03 9.94997978e-01]
 [3.33245285e-03 3.44882696e-03 9.46118057e-01 4.71006818e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 75.84 [%]
Global accuracy score (test) = 74.72 [%]
Global F1 score (train) = 76.07 [%]
Global F1 score (test) = 75.07 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.55      0.74      0.63       350
MODERATE-INTENSITY       0.59      0.45      0.51       350
         SEDENTARY       0.98      0.99      0.98       350
VIGOROUS-INTENSITY       0.93      0.83      0.88       299

          accuracy                           0.75      1349
         macro avg       0.76      0.75      0.75      1349
      weighted avg       0.76      0.75      0.75      1349


Accuracy capturado en la ejecución 18: 74.72 [%]
F1-score capturado en la ejecución 18: 75.07 [%]

=== EJECUCIÓN 19 ===

--- TRAIN (ejecución 19) ---

--- TEST (ejecución 19) ---
2025-11-08 15:00:24.888893: 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`.
2025-11-08 15:00:24.900709: 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 00:00:1762610424.914777 1006843 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762610424.919062 1006843 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762610424.929749 1006843 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610424.929768 1006843 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610424.929770 1006843 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610424.929771 1006843 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 15:00:24.933111: 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 00:00:1762610427.128563 1006843 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762610429.569069 1006972 service.cc:152] XLA service 0x74e4a40156c0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762610429.569111 1006972 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 15:00:29.624074: 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 00:00:1762610429.936751 1006972 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762610432.281070 1006972 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:16[0m 5s/step - accuracy: 0.1875 - loss: 2.4268
[1m 25/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3340 - loss: 1.7097  
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3817 - loss: 1.5833
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4078 - loss: 1.5206
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4277 - loss: 1.4742
[1m143/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4416 - loss: 1.4413
[1m171/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4525 - loss: 1.4150
[1m202/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4628 - loss: 1.3894
[1m230/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4710 - loss: 1.3691
[1m259/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4784 - loss: 1.3501
[1m288/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4850 - loss: 1.3329
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4895 - loss: 1.3213
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 14ms/step - accuracy: 0.4897 - loss: 1.3208 - val_accuracy: 0.6654 - val_loss: 0.7761
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7188 - loss: 0.7034
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5968 - loss: 1.0281 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6003 - loss: 1.0179
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6066 - loss: 1.0017
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6107 - loss: 0.9897
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6135 - loss: 0.9795
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6155 - loss: 0.9716
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6171 - loss: 0.9645
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6183 - loss: 0.9597
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6196 - loss: 0.9551
[1m299/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6205 - loss: 0.9512
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6209 - loss: 0.9497 - val_accuracy: 0.6773 - val_loss: 0.6775
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6875 - loss: 0.6836
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6635 - loss: 0.8426 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6554 - loss: 0.8583
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6526 - loss: 0.8618
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6508 - loss: 0.8629
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6492 - loss: 0.8630
[1m184/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6480 - loss: 0.8637
[1m215/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6469 - loss: 0.8645
[1m246/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6465 - loss: 0.8641
[1m277/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6465 - loss: 0.8629
[1m305/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6466 - loss: 0.8615
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6466 - loss: 0.8612 - val_accuracy: 0.6994 - val_loss: 0.6486
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6875 - loss: 0.8655
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6433 - loss: 0.8856 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6549 - loss: 0.8577
[1m 92/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6598 - loss: 0.8483
[1m124/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6615 - loss: 0.8433
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6611 - loss: 0.8408
[1m186/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6611 - loss: 0.8369
[1m214/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6609 - loss: 0.8340
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6610 - loss: 0.8311
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6615 - loss: 0.8277
[1m301/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6620 - loss: 0.8244
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6622 - loss: 0.8235 - val_accuracy: 0.6850 - val_loss: 0.6479
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7188 - loss: 0.6963
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6987 - loss: 0.7609 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6910 - loss: 0.7615
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6855 - loss: 0.7611
[1m125/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6824 - loss: 0.7605
[1m154/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6810 - loss: 0.7598
[1m186/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6798 - loss: 0.7594
[1m215/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6785 - loss: 0.7600
[1m241/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6773 - loss: 0.7613
[1m272/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6760 - loss: 0.7627
[1m303/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6751 - loss: 0.7633
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6750 - loss: 0.7635 - val_accuracy: 0.6879 - val_loss: 0.6505
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.6250 - loss: 0.7052
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6718 - loss: 0.7488 
[1m 63/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6715 - loss: 0.7507
[1m 97/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6699 - loss: 0.7539
[1m127/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6690 - loss: 0.7565
[1m159/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6687 - loss: 0.7555
[1m190/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6692 - loss: 0.7535
[1m219/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6701 - loss: 0.7517
[1m249/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6712 - loss: 0.7499
[1m279/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6722 - loss: 0.7481
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6729 - loss: 0.7469 - val_accuracy: 0.7005 - val_loss: 0.6402
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6250 - loss: 0.7844
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6607 - loss: 0.7322 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6732 - loss: 0.7126
[1m 92/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6776 - loss: 0.7084
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6797 - loss: 0.7090
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6817 - loss: 0.7091
[1m182/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6833 - loss: 0.7090
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6842 - loss: 0.7093
[1m243/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6847 - loss: 0.7098
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6853 - loss: 0.7096
[1m300/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6860 - loss: 0.7091
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6863 - loss: 0.7090 - val_accuracy: 0.6952 - val_loss: 0.6384
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.7812 - loss: 0.3824
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7129 - loss: 0.6161 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7075 - loss: 0.6417
[1m 94/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7057 - loss: 0.6581
[1m124/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7057 - loss: 0.6654
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7053 - loss: 0.6693
[1m182/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7054 - loss: 0.6717
[1m211/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7056 - loss: 0.6730
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7059 - loss: 0.6740
[1m270/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7062 - loss: 0.6746
[1m300/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7061 - loss: 0.6758
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7061 - loss: 0.6763 - val_accuracy: 0.6994 - val_loss: 0.6429
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7500 - loss: 0.6994
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7080 - loss: 0.6646 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6992 - loss: 0.6794
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7005 - loss: 0.6765
[1m123/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7021 - loss: 0.6744
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7025 - loss: 0.6748
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7028 - loss: 0.6754
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7031 - loss: 0.6757
[1m239/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7033 - loss: 0.6758
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7036 - loss: 0.6759
[1m299/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7037 - loss: 0.6761
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7037 - loss: 0.6762 - val_accuracy: 0.7029 - val_loss: 0.6407
Epoch 10/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7188 - loss: 0.4971
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7062 - loss: 0.6623 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7094 - loss: 0.6621
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7109 - loss: 0.6630
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7113 - loss: 0.6623
[1m146/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7117 - loss: 0.6619
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7118 - loss: 0.6612
[1m203/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7123 - loss: 0.6600
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7129 - loss: 0.6584
[1m265/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7132 - loss: 0.6576
[1m294/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7133 - loss: 0.6571
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7134 - loss: 0.6568 - val_accuracy: 0.6984 - val_loss: 0.6491
Epoch 11/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6562 - loss: 0.6031
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6875 - loss: 0.6573 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6911 - loss: 0.6652
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6957 - loss: 0.6631
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6995 - loss: 0.6593
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7024 - loss: 0.6566
[1m186/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7048 - loss: 0.6550
[1m217/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7064 - loss: 0.6536
[1m248/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7076 - loss: 0.6523
[1m276/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7086 - loss: 0.6511
[1m307/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7094 - loss: 0.6498
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7095 - loss: 0.6497 - val_accuracy: 0.6994 - val_loss: 0.6618
Epoch 12/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7188 - loss: 0.6714
[1m 24/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7048 - loss: 0.6577 
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7067 - loss: 0.6507
[1m 83/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7102 - loss: 0.6433
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7141 - loss: 0.6362
[1m143/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7166 - loss: 0.6333
[1m172/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7186 - loss: 0.6312
[1m201/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7200 - loss: 0.6299
[1m231/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7211 - loss: 0.6289
[1m260/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7219 - loss: 0.6283
[1m290/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7224 - loss: 0.6277
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7226 - loss: 0.6275 - val_accuracy: 0.7037 - val_loss: 0.6496

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 501ms/step2025-11-08 15:00:45.273536: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 24ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 24ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:48[0m 1s/step
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 875us/step
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 868us/step
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 867us/step
[1m232/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 875us/step
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 865us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 17ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 22ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 22ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m55/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 933us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 69.52 [%]
Global F1 score (validation) = 69.8 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[2.5491896e-01 3.9317459e-01 1.4339410e-02 3.3756706e-01]
 [5.3939992e-01 4.1285047e-01 3.4037009e-02 1.3712644e-02]
 [4.9054065e-01 4.7600889e-01 1.9764073e-02 1.3686364e-02]
 ...
 [6.1907212e-04 1.9965491e-03 1.2469749e-02 9.8491454e-01]
 [1.1978844e-04 3.1987761e-04 2.8233097e-03 9.9673706e-01]
 [2.0366858e-03 3.4269199e-03 8.5541075e-01 1.3912562e-01]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 72.57 [%]
Global accuracy score (test) = 71.76 [%]
Global F1 score (train) = 72.15 [%]
Global F1 score (test) = 71.49 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.61      0.31      0.41       350
MODERATE-INTENSITY       0.49      0.79      0.60       350
         SEDENTARY       0.98      0.99      0.99       350
VIGOROUS-INTENSITY       0.94      0.79      0.86       299

          accuracy                           0.72      1349
         macro avg       0.76      0.72      0.71      1349
      weighted avg       0.75      0.72      0.71      1349


Accuracy capturado en la ejecución 19: 71.76 [%]
F1-score capturado en la ejecución 19: 71.49 [%]

=== EJECUCIÓN 20 ===

--- TRAIN (ejecución 20) ---

--- TEST (ejecución 20) ---
2025-11-08 15:00:56.252579: 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`.
2025-11-08 15:00:56.263830: 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 00:00:1762610456.276933 1008984 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762610456.281061 1008984 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762610456.290919 1008984 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610456.290936 1008984 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610456.290937 1008984 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610456.290938 1008984 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 15:00:56.294042: 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 00:00:1762610458.540936 1008984 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762610460.997692 1009090 service.cc:152] XLA service 0x7634f8002f50 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762610460.997724 1009090 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 15:01:01.049207: 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 00:00:1762610461.371935 1009090 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762610463.732406 1009090 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:33[0m 5s/step - accuracy: 0.1562 - loss: 2.3429
[1m 21/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.2616 - loss: 1.9952  
[1m 53/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3255 - loss: 1.7830
[1m 81/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3605 - loss: 1.6811
[1m111/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3840 - loss: 1.6152
[1m138/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4002 - loss: 1.5683
[1m170/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4157 - loss: 1.5234
[1m200/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4283 - loss: 1.4868
[1m232/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4402 - loss: 1.4521
[1m264/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4506 - loss: 1.4221
[1m292/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4584 - loss: 1.3997
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4629 - loss: 1.3865
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 14ms/step - accuracy: 0.4631 - loss: 1.3858 - val_accuracy: 0.6643 - val_loss: 0.7269
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 23ms/step - accuracy: 0.5938 - loss: 1.1511
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6283 - loss: 0.9988 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6237 - loss: 0.9817
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6196 - loss: 0.9723
[1m116/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6181 - loss: 0.9670
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6180 - loss: 0.9626
[1m170/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6190 - loss: 0.9586
[1m200/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6203 - loss: 0.9531
[1m229/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6213 - loss: 0.9483
[1m261/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6220 - loss: 0.9445
[1m290/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6228 - loss: 0.9412
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6235 - loss: 0.9386 - val_accuracy: 0.6756 - val_loss: 0.6774
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5312 - loss: 1.1136
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6384 - loss: 0.8611 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6462 - loss: 0.8480
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6475 - loss: 0.8459
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6477 - loss: 0.8443
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6483 - loss: 0.8416
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6490 - loss: 0.8394
[1m211/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6492 - loss: 0.8387
[1m240/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6493 - loss: 0.8382
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6494 - loss: 0.8377
[1m301/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6498 - loss: 0.8368
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6499 - loss: 0.8365 - val_accuracy: 0.6815 - val_loss: 0.6644
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6250 - loss: 0.6888
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6687 - loss: 0.7634 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6654 - loss: 0.7637
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6649 - loss: 0.7664
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6646 - loss: 0.7709
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6644 - loss: 0.7737
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6640 - loss: 0.7774
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6633 - loss: 0.7809
[1m244/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6627 - loss: 0.7830
[1m276/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6628 - loss: 0.7836
[1m308/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6630 - loss: 0.7837
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6630 - loss: 0.7837 - val_accuracy: 0.6850 - val_loss: 0.6559
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7500 - loss: 0.4826
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7162 - loss: 0.6672 
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6990 - loss: 0.6982
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6912 - loss: 0.7119
[1m111/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6878 - loss: 0.7209
[1m142/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6857 - loss: 0.7274
[1m169/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6845 - loss: 0.7311
[1m198/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6834 - loss: 0.7340
[1m229/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6825 - loss: 0.7360
[1m259/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6816 - loss: 0.7381
[1m291/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6807 - loss: 0.7402
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6803 - loss: 0.7412 - val_accuracy: 0.6861 - val_loss: 0.6678
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7188 - loss: 0.9561
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6831 - loss: 0.7345 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6779 - loss: 0.7370
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6769 - loss: 0.7344
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6777 - loss: 0.7288
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6781 - loss: 0.7256
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6778 - loss: 0.7252
[1m210/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6779 - loss: 0.7244
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6780 - loss: 0.7239
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6781 - loss: 0.7238
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6782 - loss: 0.7239
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6782 - loss: 0.7241 - val_accuracy: 0.6921 - val_loss: 0.6624
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.6562 - loss: 0.6321
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7082 - loss: 0.6796 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6945 - loss: 0.7024
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6936 - loss: 0.6996
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6913 - loss: 0.7011
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6899 - loss: 0.7008
[1m182/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6891 - loss: 0.7001
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6887 - loss: 0.7000
[1m244/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6882 - loss: 0.7007
[1m272/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6874 - loss: 0.7018
[1m302/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6868 - loss: 0.7026
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6867 - loss: 0.7027 - val_accuracy: 0.6945 - val_loss: 0.6697
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7500 - loss: 0.6101
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6948 - loss: 0.6604 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6963 - loss: 0.6774
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6966 - loss: 0.6825
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6969 - loss: 0.6822
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6973 - loss: 0.6814
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6968 - loss: 0.6820
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6959 - loss: 0.6831
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6949 - loss: 0.6839
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6942 - loss: 0.6840
[1m300/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6936 - loss: 0.6843
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6934 - loss: 0.6843 - val_accuracy: 0.6977 - val_loss: 0.6645
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.6250 - loss: 0.7789
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7018 - loss: 0.6552 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6952 - loss: 0.6738
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6938 - loss: 0.6813
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6942 - loss: 0.6831
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6952 - loss: 0.6830
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6962 - loss: 0.6820
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6977 - loss: 0.6794
[1m240/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6993 - loss: 0.6769
[1m266/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7002 - loss: 0.6756
[1m299/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7014 - loss: 0.6741
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7018 - loss: 0.6737 - val_accuracy: 0.6924 - val_loss: 0.6692

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 495ms/step2025-11-08 15:01:14.720818: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 25ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 25ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:46[0m 1s/step
[1m 51/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m110/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 922us/step
[1m169/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 900us/step
[1m228/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 890us/step
[1m288/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 879us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 21ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 22ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m57/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 895us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 68.54 [%]
Global F1 score (validation) = 69.39 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[4.7891980e-01 4.3506837e-01 1.6131645e-02 6.9880135e-02]
 [3.4206051e-01 5.8149505e-01 2.5243193e-02 5.1201295e-02]
 [6.5264976e-01 3.0230054e-01 3.4613442e-02 1.0436257e-02]
 ...
 [3.8356660e-03 1.5900692e-03 2.6173793e-02 9.6840042e-01]
 [2.4749059e-04 1.4246276e-04 2.7258538e-02 9.7235149e-01]
 [8.4184408e-03 4.3834611e-03 8.8188165e-01 1.0531642e-01]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 75.39 [%]
Global accuracy score (test) = 74.35 [%]
Global F1 score (train) = 75.78 [%]
Global F1 score (test) = 75.09 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.54      0.71      0.62       350
MODERATE-INTENSITY       0.57      0.46      0.51       350
         SEDENTARY       0.98      0.98      0.98       350
VIGOROUS-INTENSITY       0.98      0.83      0.90       299

          accuracy                           0.74      1349
         macro avg       0.77      0.75      0.75      1349
      weighted avg       0.76      0.74      0.75      1349


Accuracy capturado en la ejecución 20: 74.35 [%]
F1-score capturado en la ejecución 20: 75.09 [%]

=== EJECUCIÓN 21 ===

--- TRAIN (ejecución 21) ---

--- TEST (ejecución 21) ---
2025-11-08 15:01:25.681698: 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`.
2025-11-08 15:01:25.693501: 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 00:00:1762610485.707673 1010801 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762610485.711713 1010801 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762610485.722056 1010801 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610485.722080 1010801 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610485.722081 1010801 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610485.722082 1010801 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 15:01:25.725023: 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 00:00:1762610487.959491 1010801 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762610490.432312 1010941 service.cc:152] XLA service 0x7b4628016660 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762610490.432341 1010941 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 15:01:30.485619: 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 00:00:1762610490.813338 1010941 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762610493.166792 1010941 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:36[0m 5s/step - accuracy: 0.1562 - loss: 2.0750
[1m 24/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3023 - loss: 1.8334  
[1m 54/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3439 - loss: 1.7220
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3741 - loss: 1.6419
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3972 - loss: 1.5805
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4163 - loss: 1.5287
[1m173/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4282 - loss: 1.4969
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4411 - loss: 1.4623
[1m236/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4514 - loss: 1.4344
[1m266/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4603 - loss: 1.4106
[1m297/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4683 - loss: 1.3891
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4714 - loss: 1.3808
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 14ms/step - accuracy: 0.4716 - loss: 1.3802 - val_accuracy: 0.6548 - val_loss: 0.7618
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.6250 - loss: 0.7727
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6110 - loss: 0.9142 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5990 - loss: 0.9530
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5974 - loss: 0.9619
[1m124/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5985 - loss: 0.9663
[1m155/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5991 - loss: 0.9697
[1m184/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5999 - loss: 0.9708
[1m214/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6013 - loss: 0.9702
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6025 - loss: 0.9689
[1m274/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6038 - loss: 0.9672
[1m304/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6051 - loss: 0.9652
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6053 - loss: 0.9648 - val_accuracy: 0.6724 - val_loss: 0.6801
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6562 - loss: 0.7445
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6513 - loss: 0.8887 
[1m 54/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6559 - loss: 0.8702
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6536 - loss: 0.8621
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6512 - loss: 0.8600
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6498 - loss: 0.8599
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6495 - loss: 0.8594
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6494 - loss: 0.8588
[1m237/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6494 - loss: 0.8582
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6492 - loss: 0.8583
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6491 - loss: 0.8581
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6491 - loss: 0.8580 - val_accuracy: 0.6928 - val_loss: 0.6506
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.4062 - loss: 1.5563
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6261 - loss: 0.9220 
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6426 - loss: 0.8739
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6459 - loss: 0.8568
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6465 - loss: 0.8509
[1m145/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6467 - loss: 0.8460
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6471 - loss: 0.8412
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6475 - loss: 0.8370
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6481 - loss: 0.8332
[1m263/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6486 - loss: 0.8303
[1m292/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6488 - loss: 0.8279
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6489 - loss: 0.8266 - val_accuracy: 0.6903 - val_loss: 0.6525
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5938 - loss: 0.8278
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6580 - loss: 0.7758 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6616 - loss: 0.7834
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6602 - loss: 0.7925
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6597 - loss: 0.7946
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6603 - loss: 0.7935
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6606 - loss: 0.7921
[1m209/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6605 - loss: 0.7905
[1m240/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6608 - loss: 0.7888
[1m270/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6612 - loss: 0.7872
[1m299/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6617 - loss: 0.7856
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6618 - loss: 0.7850 - val_accuracy: 0.6935 - val_loss: 0.6356
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 26ms/step - accuracy: 0.7500 - loss: 0.8999
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7070 - loss: 0.7463 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6937 - loss: 0.7476
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6905 - loss: 0.7430
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6883 - loss: 0.7405
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6870 - loss: 0.7380
[1m183/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6858 - loss: 0.7365
[1m214/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6854 - loss: 0.7355
[1m241/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6849 - loss: 0.7354
[1m274/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6841 - loss: 0.7354
[1m301/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6837 - loss: 0.7353
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6835 - loss: 0.7352 - val_accuracy: 0.6994 - val_loss: 0.6365
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7500 - loss: 0.5473
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6939 - loss: 0.7018 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6959 - loss: 0.6995
[1m 95/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6938 - loss: 0.7042
[1m126/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6917 - loss: 0.7077
[1m158/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6907 - loss: 0.7068
[1m188/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6904 - loss: 0.7048
[1m221/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6897 - loss: 0.7035
[1m248/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6890 - loss: 0.7032
[1m278/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6882 - loss: 0.7035
[1m309/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6874 - loss: 0.7040
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6874 - loss: 0.7040 - val_accuracy: 0.7107 - val_loss: 0.6329
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6562 - loss: 0.8086
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7084 - loss: 0.6768 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7031 - loss: 0.6915
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7013 - loss: 0.6976
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7002 - loss: 0.7001
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6998 - loss: 0.7003
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6996 - loss: 0.7001
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6992 - loss: 0.6999
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6988 - loss: 0.6996
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6986 - loss: 0.6992
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6983 - loss: 0.6990
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6982 - loss: 0.6989 - val_accuracy: 0.7037 - val_loss: 0.6303
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7812 - loss: 0.4749
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7184 - loss: 0.6716 
[1m 63/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7095 - loss: 0.6865
[1m 95/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7056 - loss: 0.6902
[1m126/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7047 - loss: 0.6904
[1m154/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7040 - loss: 0.6891
[1m185/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7035 - loss: 0.6883
[1m217/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7032 - loss: 0.6879
[1m246/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7030 - loss: 0.6874
[1m275/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7028 - loss: 0.6871
[1m304/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7026 - loss: 0.6866
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7025 - loss: 0.6865 - val_accuracy: 0.7117 - val_loss: 0.6353
Epoch 10/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5938 - loss: 1.2297
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6693 - loss: 0.7374 
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6820 - loss: 0.7096
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6872 - loss: 0.6967
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6905 - loss: 0.6888
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6930 - loss: 0.6849
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6944 - loss: 0.6830
[1m209/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6956 - loss: 0.6815
[1m237/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6966 - loss: 0.6801
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6976 - loss: 0.6787
[1m300/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6984 - loss: 0.6775
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6986 - loss: 0.6770 - val_accuracy: 0.7022 - val_loss: 0.6452
Epoch 11/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.7500 - loss: 0.5508
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7102 - loss: 0.6139 
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7105 - loss: 0.6317
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7095 - loss: 0.6403
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7093 - loss: 0.6435
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7093 - loss: 0.6452
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7095 - loss: 0.6454
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7099 - loss: 0.6448
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7100 - loss: 0.6443
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7101 - loss: 0.6437
[1m297/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7102 - loss: 0.6433
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7102 - loss: 0.6432 - val_accuracy: 0.7086 - val_loss: 0.6304
Epoch 12/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7812 - loss: 0.5163
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7178 - loss: 0.5912 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7197 - loss: 0.5957
[1m 92/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7192 - loss: 0.6003
[1m125/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7189 - loss: 0.6044
[1m155/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7185 - loss: 0.6082
[1m187/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7185 - loss: 0.6109
[1m216/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7183 - loss: 0.6131
[1m244/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7180 - loss: 0.6150
[1m275/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7177 - loss: 0.6169
[1m302/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7174 - loss: 0.6183
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7173 - loss: 0.6187 - val_accuracy: 0.7086 - val_loss: 0.6364
Epoch 13/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7812 - loss: 0.5425
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7484 - loss: 0.5984 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7422 - loss: 0.5965
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7402 - loss: 0.5943
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7394 - loss: 0.5968
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7389 - loss: 0.5996
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7383 - loss: 0.6022
[1m209/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7375 - loss: 0.6044
[1m240/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7368 - loss: 0.6059
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7363 - loss: 0.6069
[1m297/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7357 - loss: 0.6076
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7354 - loss: 0.6080 - val_accuracy: 0.7065 - val_loss: 0.6398

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 511ms/step2025-11-08 15:01:46.976361: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 24ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 24ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:52[0m 1s/step
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 932us/step
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 869us/step
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 874us/step
[1m233/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 869us/step
[1m289/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 875us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 21ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 22ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m56/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 917us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 69.31 [%]
Global F1 score (validation) = 68.75 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[6.5710306e-01 3.2096833e-01 1.2518780e-02 9.4098868e-03]
 [7.2218192e-01 2.5411680e-01 1.4870058e-02 8.8312812e-03]
 [3.6215052e-01 5.9104884e-01 5.7982425e-03 4.1002497e-02]
 ...
 [8.6000880e-05 5.9084261e-05 5.2357314e-04 9.9933130e-01]
 [5.2490650e-05 6.0752871e-05 8.2082185e-04 9.9906594e-01]
 [1.2962741e-02 6.2937126e-03 8.5479599e-01 1.2594752e-01]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 74.15 [%]
Global accuracy score (test) = 71.76 [%]
Global F1 score (train) = 73.62 [%]
Global F1 score (test) = 72.32 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.52      0.76      0.62       350
MODERATE-INTENSITY       0.52      0.39      0.45       350
         SEDENTARY       0.98      0.97      0.97       350
VIGOROUS-INTENSITY       0.97      0.76      0.85       299

          accuracy                           0.72      1349
         macro avg       0.75      0.72      0.72      1349
      weighted avg       0.74      0.72      0.72      1349


Accuracy capturado en la ejecución 21: 71.76 [%]
F1-score capturado en la ejecución 21: 72.32 [%]

=== EJECUCIÓN 22 ===

--- TRAIN (ejecución 22) ---

--- TEST (ejecución 22) ---
2025-11-08 15:01:57.876522: 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`.
2025-11-08 15:01:57.887865: 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 00:00:1762610517.901135 1013041 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762610517.905335 1013041 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762610517.915284 1013041 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610517.915302 1013041 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610517.915303 1013041 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610517.915304 1013041 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 15:01:57.918586: 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 00:00:1762610520.143009 1013041 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762610522.639889 1013155 service.cc:152] XLA service 0x78f5d40064f0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762610522.639931 1013155 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 15:02:02.691799: 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 00:00:1762610522.999600 1013155 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762610525.373771 1013155 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:39[0m 5s/step - accuracy: 0.2188 - loss: 1.6820
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3432 - loss: 1.6918  
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3836 - loss: 1.5908
[1m 82/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4054 - loss: 1.5293
[1m112/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4248 - loss: 1.4775
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4414 - loss: 1.4325
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4558 - loss: 1.3945
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4673 - loss: 1.3639
[1m239/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4765 - loss: 1.3389
[1m270/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4844 - loss: 1.3173
[1m301/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4914 - loss: 1.2981
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4932 - loss: 1.2930
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 13ms/step - accuracy: 0.4934 - loss: 1.2925 - val_accuracy: 0.6440 - val_loss: 0.7307
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.5000 - loss: 1.2919
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6106 - loss: 0.9646 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6007 - loss: 0.9710
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6001 - loss: 0.9686
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6020 - loss: 0.9638
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6040 - loss: 0.9578
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6054 - loss: 0.9524
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6068 - loss: 0.9471
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6083 - loss: 0.9424
[1m265/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6097 - loss: 0.9383
[1m294/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6107 - loss: 0.9348
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6113 - loss: 0.9328 - val_accuracy: 0.6664 - val_loss: 0.6714
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.5312 - loss: 1.0058
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6274 - loss: 0.8517 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6312 - loss: 0.8489
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6301 - loss: 0.8537
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6317 - loss: 0.8538
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6337 - loss: 0.8529
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6351 - loss: 0.8507
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6360 - loss: 0.8492
[1m236/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6366 - loss: 0.8478
[1m262/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6373 - loss: 0.8464
[1m294/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6382 - loss: 0.8450
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6386 - loss: 0.8441 - val_accuracy: 0.6696 - val_loss: 0.6755
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5625 - loss: 0.9702
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6342 - loss: 0.8200 
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6439 - loss: 0.8073
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6485 - loss: 0.8011
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6499 - loss: 0.7982
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6520 - loss: 0.7944
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6533 - loss: 0.7926
[1m214/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6540 - loss: 0.7914
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6543 - loss: 0.7908
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6549 - loss: 0.7900
[1m302/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6554 - loss: 0.7893
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6556 - loss: 0.7890 - val_accuracy: 0.6808 - val_loss: 0.6666
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.5625 - loss: 1.0104
[1m 32/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6526 - loss: 0.7730 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6586 - loss: 0.7736
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6620 - loss: 0.7693
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6634 - loss: 0.7661
[1m154/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6635 - loss: 0.7661
[1m184/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6637 - loss: 0.7652
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6643 - loss: 0.7646
[1m243/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6648 - loss: 0.7644
[1m273/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6651 - loss: 0.7641
[1m302/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6656 - loss: 0.7636
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6658 - loss: 0.7634 - val_accuracy: 0.6861 - val_loss: 0.6583
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.6875 - loss: 0.9504
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6698 - loss: 0.7804 
[1m 53/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6711 - loss: 0.7611
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6735 - loss: 0.7567
[1m113/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6744 - loss: 0.7564
[1m143/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6772 - loss: 0.7521
[1m173/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6787 - loss: 0.7497
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6797 - loss: 0.7474
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6801 - loss: 0.7457
[1m266/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6806 - loss: 0.7442
[1m300/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6809 - loss: 0.7430
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6810 - loss: 0.7427 - val_accuracy: 0.6868 - val_loss: 0.6644
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.8125 - loss: 0.5797
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7003 - loss: 0.6866 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6928 - loss: 0.7059
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6898 - loss: 0.7137
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6852 - loss: 0.7196
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6825 - loss: 0.7214
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6819 - loss: 0.7213
[1m215/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6810 - loss: 0.7225
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6804 - loss: 0.7232
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6802 - loss: 0.7234
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6800 - loss: 0.7232
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6799 - loss: 0.7229 - val_accuracy: 0.6914 - val_loss: 0.6402
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6562 - loss: 0.8516
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6716 - loss: 0.7245 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6816 - loss: 0.7039
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6858 - loss: 0.7019
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6880 - loss: 0.7004
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6889 - loss: 0.7010
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6896 - loss: 0.7008
[1m209/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6901 - loss: 0.7002
[1m239/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6902 - loss: 0.7000
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6903 - loss: 0.6994
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6905 - loss: 0.6987
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6907 - loss: 0.6985 - val_accuracy: 0.6735 - val_loss: 0.6845
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6875 - loss: 0.5806
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7117 - loss: 0.6649 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7081 - loss: 0.6734
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7083 - loss: 0.6729
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7096 - loss: 0.6689
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7095 - loss: 0.6697
[1m182/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7091 - loss: 0.6706
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7087 - loss: 0.6705
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7083 - loss: 0.6705
[1m273/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7078 - loss: 0.6708
[1m303/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7074 - loss: 0.6713
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7073 - loss: 0.6714 - val_accuracy: 0.6808 - val_loss: 0.6700
Epoch 10/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7812 - loss: 0.4693
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7032 - loss: 0.6956 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6960 - loss: 0.6992
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6951 - loss: 0.6940
[1m124/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6971 - loss: 0.6869
[1m158/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6990 - loss: 0.6818
[1m189/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7004 - loss: 0.6792
[1m218/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7014 - loss: 0.6775
[1m250/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7023 - loss: 0.6759
[1m284/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7033 - loss: 0.6741
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7041 - loss: 0.6726 - val_accuracy: 0.6970 - val_loss: 0.6530
Epoch 11/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.6562 - loss: 0.5860
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6973 - loss: 0.6212 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7027 - loss: 0.6387
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7045 - loss: 0.6440
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7065 - loss: 0.6445
[1m154/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7092 - loss: 0.6432
[1m186/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7111 - loss: 0.6429
[1m217/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7121 - loss: 0.6430
[1m245/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7131 - loss: 0.6427
[1m275/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7135 - loss: 0.6429
[1m304/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7138 - loss: 0.6429
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7138 - loss: 0.6429 - val_accuracy: 0.6917 - val_loss: 0.6690
Epoch 12/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7188 - loss: 0.7217
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7196 - loss: 0.6790 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7331 - loss: 0.6339
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7392 - loss: 0.6180
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7404 - loss: 0.6149
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7413 - loss: 0.6130
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7412 - loss: 0.6123
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7403 - loss: 0.6132
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7394 - loss: 0.6138
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7387 - loss: 0.6145
[1m299/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7384 - loss: 0.6150
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7382 - loss: 0.6152 - val_accuracy: 0.6942 - val_loss: 0.6699

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 485ms/step2025-11-08 15:02:18.261257: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 25ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 25ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:52[0m 1s/step
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 917us/step
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 887us/step
[1m172/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 887us/step
[1m226/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 900us/step
[1m283/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 895us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 17ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 20ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 21ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m52/89[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 991us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 69.31 [%]
Global F1 score (validation) = 70.28 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[6.03773534e-01 3.64077926e-01 4.52512596e-03 2.76234616e-02]
 [4.41005677e-01 5.37343800e-01 8.92335922e-03 1.27272373e-02]
 [5.35926104e-01 4.32006150e-01 1.99110154e-02 1.21567054e-02]
 ...
 [2.63193593e-04 6.48106972e-04 4.81746625e-03 9.94271219e-01]
 [2.26595002e-04 6.16228150e-04 5.08173043e-03 9.94075418e-01]
 [1.08928885e-02 5.56454062e-03 9.31620479e-01 5.19220643e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 75.59 [%]
Global accuracy score (test) = 72.35 [%]
Global F1 score (train) = 75.86 [%]
Global F1 score (test) = 73.19 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.54      0.48      0.51       350
MODERATE-INTENSITY       0.51      0.61      0.55       350
         SEDENTARY       0.98      0.99      0.98       350
VIGOROUS-INTENSITY       0.93      0.83      0.88       299

          accuracy                           0.72      1349
         macro avg       0.74      0.73      0.73      1349
      weighted avg       0.73      0.72      0.73      1349


Accuracy capturado en la ejecución 22: 72.35 [%]
F1-score capturado en la ejecución 22: 73.19 [%]

=== EJECUCIÓN 23 ===

--- TRAIN (ejecución 23) ---

--- TEST (ejecución 23) ---
2025-11-08 15:02:29.271627: 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`.
2025-11-08 15:02:29.283001: 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 00:00:1762610549.296232 1015166 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762610549.300252 1015166 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762610549.310363 1015166 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610549.310382 1015166 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610549.310383 1015166 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610549.310385 1015166 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 15:02:29.313681: 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 00:00:1762610551.530962 1015166 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762610553.976090 1015294 service.cc:152] XLA service 0x7926740026b0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762610553.976134 1015294 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 15:02:34.028208: 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 00:00:1762610554.349583 1015294 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762610556.728233 1015294 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:33[0m 5s/step - accuracy: 0.0312 - loss: 2.2286
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2496 - loss: 1.8659  
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3094 - loss: 1.7285
[1m 81/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3435 - loss: 1.6448
[1m109/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3698 - loss: 1.5800
[1m137/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3887 - loss: 1.5317
[1m168/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4053 - loss: 1.4899
[1m199/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4191 - loss: 1.4548
[1m229/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4308 - loss: 1.4251
[1m260/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4413 - loss: 1.3986
[1m291/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4508 - loss: 1.3744
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4562 - loss: 1.3607
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 14ms/step - accuracy: 0.4564 - loss: 1.3600 - val_accuracy: 0.6724 - val_loss: 0.6849
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7500 - loss: 0.6657
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6415 - loss: 0.9131 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6312 - loss: 0.9148
[1m 82/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6279 - loss: 0.9174
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6269 - loss: 0.9174
[1m140/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6269 - loss: 0.9158
[1m171/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6268 - loss: 0.9131
[1m199/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6271 - loss: 0.9103
[1m226/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6273 - loss: 0.9083
[1m254/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6280 - loss: 0.9058
[1m284/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6288 - loss: 0.9031
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6294 - loss: 0.9008
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6295 - loss: 0.9007 - val_accuracy: 0.6787 - val_loss: 0.6449
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.5625 - loss: 0.8379
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6107 - loss: 0.8651 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6163 - loss: 0.8632
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6199 - loss: 0.8584
[1m116/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6214 - loss: 0.8556
[1m143/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6229 - loss: 0.8537
[1m171/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6248 - loss: 0.8508
[1m202/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6268 - loss: 0.8482
[1m234/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6286 - loss: 0.8460
[1m264/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6302 - loss: 0.8435
[1m294/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6318 - loss: 0.8411
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6328 - loss: 0.8396 - val_accuracy: 0.6900 - val_loss: 0.6231
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.5312 - loss: 1.1207
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6587 - loss: 0.8279 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6585 - loss: 0.8333
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6622 - loss: 0.8230
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6650 - loss: 0.8130
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6667 - loss: 0.8053
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6677 - loss: 0.8004
[1m210/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6683 - loss: 0.7965
[1m239/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6685 - loss: 0.7935
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6687 - loss: 0.7905
[1m299/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6689 - loss: 0.7879
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6690 - loss: 0.7869 - val_accuracy: 0.6931 - val_loss: 0.6205
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6250 - loss: 1.0248
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6749 - loss: 0.7598 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6735 - loss: 0.7524
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6752 - loss: 0.7467
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6751 - loss: 0.7440
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6745 - loss: 0.7428
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6741 - loss: 0.7422
[1m210/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6738 - loss: 0.7429
[1m236/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6742 - loss: 0.7424
[1m266/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6746 - loss: 0.7416
[1m297/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6748 - loss: 0.7407
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6748 - loss: 0.7404 - val_accuracy: 0.6956 - val_loss: 0.6185
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6875 - loss: 0.6427
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6812 - loss: 0.7380 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6822 - loss: 0.7317
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6846 - loss: 0.7253
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6849 - loss: 0.7233
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6859 - loss: 0.7205
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6862 - loss: 0.7198
[1m211/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6864 - loss: 0.7194
[1m241/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6865 - loss: 0.7189
[1m270/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6869 - loss: 0.7180
[1m295/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6872 - loss: 0.7174
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6874 - loss: 0.7170 - val_accuracy: 0.6843 - val_loss: 0.6311
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7812 - loss: 0.5820
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6798 - loss: 0.7244 
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6857 - loss: 0.7125
[1m 82/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6905 - loss: 0.7070
[1m112/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6924 - loss: 0.7053
[1m143/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6940 - loss: 0.7034
[1m173/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6950 - loss: 0.7021
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6956 - loss: 0.7016
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6955 - loss: 0.7019
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6955 - loss: 0.7017
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6959 - loss: 0.7009
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6960 - loss: 0.7005 - val_accuracy: 0.7015 - val_loss: 0.6233
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6562 - loss: 0.6140
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7034 - loss: 0.6789 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7095 - loss: 0.6658
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7131 - loss: 0.6587
[1m123/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7131 - loss: 0.6561
[1m155/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7133 - loss: 0.6555
[1m182/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7134 - loss: 0.6561
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7129 - loss: 0.6573
[1m241/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7124 - loss: 0.6585
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7119 - loss: 0.6598
[1m303/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7116 - loss: 0.6606
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7116 - loss: 0.6608 - val_accuracy: 0.6994 - val_loss: 0.6245
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7812 - loss: 0.4056
[1m 25/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7063 - loss: 0.6632 
[1m 52/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7098 - loss: 0.6508
[1m 82/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7117 - loss: 0.6435
[1m112/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7119 - loss: 0.6419
[1m140/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7123 - loss: 0.6404
[1m168/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7128 - loss: 0.6397
[1m200/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7134 - loss: 0.6392
[1m230/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7138 - loss: 0.6390
[1m259/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7141 - loss: 0.6393
[1m290/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7144 - loss: 0.6394
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7144 - loss: 0.6398 - val_accuracy: 0.7026 - val_loss: 0.6226
Epoch 10/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.7500 - loss: 0.4715
[1m 32/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6976 - loss: 0.6542 
[1m 63/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7001 - loss: 0.6541
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7032 - loss: 0.6528
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7052 - loss: 0.6502
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7068 - loss: 0.6479
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7083 - loss: 0.6456
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7099 - loss: 0.6433
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7108 - loss: 0.6420
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7115 - loss: 0.6412
[1m297/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7121 - loss: 0.6404
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7124 - loss: 0.6400 - val_accuracy: 0.6991 - val_loss: 0.6367

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 497ms/step2025-11-08 15:02:48.470955: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 25ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 25ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:37[0m 1s/step
[1m 45/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m103/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 987us/step
[1m160/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 952us/step
[1m219/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 926us/step
[1m275/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 921us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 22ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 23ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m60/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 850us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 971us/step
Global accuracy score (validation) = 69.42 [%]
Global F1 score (validation) = 68.15 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[6.8560094e-01 2.6931450e-01 3.1253900e-02 1.3830680e-02]
 [3.8631943e-01 5.8784199e-01 7.9904580e-03 1.7848115e-02]
 [4.2303446e-01 3.8856015e-01 1.7341765e-02 1.7106371e-01]
 ...
 [4.7268788e-04 1.4805463e-04 1.1619087e-03 9.9821740e-01]
 [3.6482824e-04 2.4353495e-04 1.7077784e-03 9.9768376e-01]
 [8.5820695e-03 4.7773127e-03 9.0840298e-01 7.8237653e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 75.13 [%]
Global accuracy score (test) = 70.27 [%]
Global F1 score (train) = 74.56 [%]
Global F1 score (test) = 70.04 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.48      0.78      0.60       350
MODERATE-INTENSITY       0.51      0.27      0.36       350
         SEDENTARY       0.98      0.95      0.97       350
VIGOROUS-INTENSITY       0.95      0.83      0.88       299

          accuracy                           0.70      1349
         macro avg       0.73      0.71      0.70      1349
      weighted avg       0.72      0.70      0.69      1349


Accuracy capturado en la ejecución 23: 70.27 [%]
F1-score capturado en la ejecución 23: 70.04 [%]

=== EJECUCIÓN 24 ===

--- TRAIN (ejecución 24) ---

--- TEST (ejecución 24) ---
2025-11-08 15:02:59.363947: 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`.
2025-11-08 15:02:59.375306: 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 00:00:1762610579.388331 1017094 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762610579.392449 1017094 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762610579.402129 1017094 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610579.402145 1017094 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610579.402146 1017094 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610579.402148 1017094 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 15:02:59.405231: 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 00:00:1762610581.602515 1017094 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762610584.040121 1017208 service.cc:152] XLA service 0x721f0c015450 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762610584.040148 1017208 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 15:03:04.089576: 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 00:00:1762610584.397337 1017208 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762610586.748552 1017208 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:15[0m 5s/step - accuracy: 0.3125 - loss: 1.3511
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3578 - loss: 1.5946  
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3917 - loss: 1.5281
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4134 - loss: 1.4819
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4291 - loss: 1.4472
[1m155/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4436 - loss: 1.4134
[1m187/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4551 - loss: 1.3862
[1m219/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4646 - loss: 1.3625
[1m248/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4719 - loss: 1.3435
[1m277/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4784 - loss: 1.3270
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4847 - loss: 1.3107
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 13ms/step - accuracy: 0.4848 - loss: 1.3102 - val_accuracy: 0.6419 - val_loss: 0.7288
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 23ms/step - accuracy: 0.5938 - loss: 0.8375
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6065 - loss: 0.9425 
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6082 - loss: 0.9491
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6072 - loss: 0.9592
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6063 - loss: 0.9639
[1m142/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6067 - loss: 0.9654
[1m171/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6073 - loss: 0.9663
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6085 - loss: 0.9657
[1m234/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6097 - loss: 0.9638
[1m264/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6111 - loss: 0.9610
[1m294/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6124 - loss: 0.9583
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6131 - loss: 0.9569 - val_accuracy: 0.6735 - val_loss: 0.6623
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 19ms/step - accuracy: 0.5312 - loss: 1.4088
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6309 - loss: 0.8688 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6320 - loss: 0.8715
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6332 - loss: 0.8712
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6340 - loss: 0.8695
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6355 - loss: 0.8666
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6376 - loss: 0.8641
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6395 - loss: 0.8621
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6410 - loss: 0.8598
[1m272/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6423 - loss: 0.8577
[1m299/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6432 - loss: 0.8562
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6436 - loss: 0.8555 - val_accuracy: 0.6812 - val_loss: 0.6522
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.5312 - loss: 1.2391
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6032 - loss: 0.8920 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6255 - loss: 0.8574
[1m 92/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6342 - loss: 0.8496
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6383 - loss: 0.8442
[1m154/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6422 - loss: 0.8373
[1m183/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6447 - loss: 0.8320
[1m215/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6466 - loss: 0.8274
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6481 - loss: 0.8241
[1m273/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6495 - loss: 0.8210
[1m302/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6505 - loss: 0.8184
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6508 - loss: 0.8177 - val_accuracy: 0.6787 - val_loss: 0.6580
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6250 - loss: 1.1490
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6400 - loss: 0.8540 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6430 - loss: 0.8320
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6457 - loss: 0.8195
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6472 - loss: 0.8119
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6494 - loss: 0.8041
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6517 - loss: 0.7984
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6540 - loss: 0.7933
[1m239/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6558 - loss: 0.7900
[1m272/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6576 - loss: 0.7872
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6588 - loss: 0.7857
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6593 - loss: 0.7850 - val_accuracy: 0.6896 - val_loss: 0.6472
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.4375 - loss: 0.9705
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6364 - loss: 0.7960 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6602 - loss: 0.7632
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6702 - loss: 0.7522
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6733 - loss: 0.7488
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6741 - loss: 0.7478
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6744 - loss: 0.7466
[1m211/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6745 - loss: 0.7459
[1m241/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6743 - loss: 0.7462
[1m270/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6741 - loss: 0.7466
[1m299/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6740 - loss: 0.7466
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6741 - loss: 0.7466 - val_accuracy: 0.6903 - val_loss: 0.6376
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.6250 - loss: 0.7045
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6894 - loss: 0.6803 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6981 - loss: 0.6779
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7011 - loss: 0.6772
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7030 - loss: 0.6784
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7026 - loss: 0.6835
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7018 - loss: 0.6871
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7012 - loss: 0.6906
[1m236/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7006 - loss: 0.6932
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6997 - loss: 0.6954
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6990 - loss: 0.6973
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6987 - loss: 0.6980 - val_accuracy: 0.6956 - val_loss: 0.6379
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6562 - loss: 0.6089
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6636 - loss: 0.7103 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6717 - loss: 0.7182
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6775 - loss: 0.7204
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6810 - loss: 0.7200
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6837 - loss: 0.7179
[1m182/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6851 - loss: 0.7156
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6862 - loss: 0.7130
[1m240/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6870 - loss: 0.7111
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6876 - loss: 0.7099
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6879 - loss: 0.7089
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6880 - loss: 0.7086 - val_accuracy: 0.6921 - val_loss: 0.6402
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6250 - loss: 0.8405
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7126 - loss: 0.6829 
[1m 54/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7072 - loss: 0.6760
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7020 - loss: 0.6784
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7007 - loss: 0.6778
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7018 - loss: 0.6749
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7029 - loss: 0.6731
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7030 - loss: 0.6735
[1m236/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7029 - loss: 0.6736
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7029 - loss: 0.6736
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7028 - loss: 0.6740
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7027 - loss: 0.6744 - val_accuracy: 0.6956 - val_loss: 0.6361
Epoch 10/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.5938 - loss: 0.8627
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6689 - loss: 0.7137 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6844 - loss: 0.6921
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6924 - loss: 0.6833
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6962 - loss: 0.6788
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6983 - loss: 0.6772
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6993 - loss: 0.6765
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6998 - loss: 0.6763
[1m243/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7001 - loss: 0.6755
[1m273/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7004 - loss: 0.6748
[1m304/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7009 - loss: 0.6738
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7011 - loss: 0.6735 - val_accuracy: 0.6970 - val_loss: 0.6296
Epoch 11/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7812 - loss: 0.5646
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7206 - loss: 0.6047 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7157 - loss: 0.6178
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7156 - loss: 0.6202
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7145 - loss: 0.6228
[1m145/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7132 - loss: 0.6259
[1m175/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7124 - loss: 0.6285
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7126 - loss: 0.6299
[1m237/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7128 - loss: 0.6315
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7131 - loss: 0.6324
[1m301/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7135 - loss: 0.6334
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7136 - loss: 0.6337 - val_accuracy: 0.6854 - val_loss: 0.6466
Epoch 12/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 27ms/step - accuracy: 0.6250 - loss: 0.7104
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7120 - loss: 0.6146 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7220 - loss: 0.6112
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7279 - loss: 0.6062
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7301 - loss: 0.6059
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7306 - loss: 0.6067
[1m182/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7316 - loss: 0.6075
[1m214/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7320 - loss: 0.6092
[1m237/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7321 - loss: 0.6105
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7319 - loss: 0.6123
[1m299/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7318 - loss: 0.6135
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7318 - loss: 0.6139 - val_accuracy: 0.6952 - val_loss: 0.6383
Epoch 13/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7500 - loss: 0.5709
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7334 - loss: 0.5816 
[1m 54/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7365 - loss: 0.5872
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7354 - loss: 0.5976
[1m116/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7342 - loss: 0.6027
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7341 - loss: 0.6045
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7334 - loss: 0.6056
[1m209/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7328 - loss: 0.6065
[1m240/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7322 - loss: 0.6074
[1m266/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7317 - loss: 0.6081
[1m294/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7315 - loss: 0.6088
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7314 - loss: 0.6093 - val_accuracy: 0.6938 - val_loss: 0.6418
Epoch 14/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7812 - loss: 0.6305
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7400 - loss: 0.6321 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7332 - loss: 0.6251
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7313 - loss: 0.6245
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7310 - loss: 0.6233
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7313 - loss: 0.6220
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7313 - loss: 0.6216
[1m211/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7316 - loss: 0.6209
[1m241/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7320 - loss: 0.6202
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7323 - loss: 0.6194
[1m299/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7325 - loss: 0.6184
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7326 - loss: 0.6180 - val_accuracy: 0.7110 - val_loss: 0.6372
Epoch 15/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7500 - loss: 0.5175
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7549 - loss: 0.5668 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7583 - loss: 0.5631
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7568 - loss: 0.5662
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7557 - loss: 0.5685
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7547 - loss: 0.5700
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7536 - loss: 0.5714
[1m211/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7525 - loss: 0.5730
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7515 - loss: 0.5752
[1m273/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7507 - loss: 0.5770
[1m303/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7502 - loss: 0.5784
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7501 - loss: 0.5787 - val_accuracy: 0.7110 - val_loss: 0.6551

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 502ms/step2025-11-08 15:03:21.889492: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 24ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 25ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:39[0m 1s/step
[1m 52/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 991us/step
[1m108/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 947us/step
[1m163/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 935us/step
[1m221/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 916us/step
[1m278/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 910us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 21ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 22ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m58/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 890us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 992us/step
Global accuracy score (validation) = 69.8 [%]
Global F1 score (validation) = 70.63 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[0.28170913 0.69578224 0.00397068 0.01853795]
 [0.71105087 0.24589624 0.03275813 0.01029488]
 [0.38035113 0.5927205  0.01040715 0.0165212 ]
 ...
 [0.00252091 0.00266085 0.02098402 0.9738342 ]
 [0.00142621 0.00130407 0.00553058 0.9917392 ]
 [0.00882144 0.00901822 0.9276364  0.05452406]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 75.08 [%]
Global accuracy score (test) = 75.02 [%]
Global F1 score (train) = 75.36 [%]
Global F1 score (test) = 75.78 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.55      0.67      0.61       350
MODERATE-INTENSITY       0.57      0.49      0.53       350
         SEDENTARY       0.98      0.99      0.99       350
VIGOROUS-INTENSITY       0.97      0.86      0.91       299

          accuracy                           0.75      1349
         macro avg       0.77      0.75      0.76      1349
      weighted avg       0.76      0.75      0.75      1349


Accuracy capturado en la ejecución 24: 75.02 [%]
F1-score capturado en la ejecución 24: 75.78 [%]

=== EJECUCIÓN 25 ===

--- TRAIN (ejecución 25) ---

--- TEST (ejecución 25) ---
2025-11-08 15:03:32.851560: 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`.
2025-11-08 15:03:32.862782: 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 00:00:1762610612.875770 1019499 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762610612.879687 1019499 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762610612.889499 1019499 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610612.889516 1019499 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610612.889517 1019499 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610612.889519 1019499 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 15:03:32.892589: 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 00:00:1762610615.077434 1019499 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762610617.527954 1019631 service.cc:152] XLA service 0x7a0c78003260 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762610617.527991 1019631 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 15:03:37.585739: 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 00:00:1762610617.896316 1019631 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762610620.276291 1019631 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:37[0m 5s/step - accuracy: 0.2188 - loss: 1.7342
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2944 - loss: 1.8075  
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3467 - loss: 1.7013
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3773 - loss: 1.6253
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3994 - loss: 1.5671
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4157 - loss: 1.5195
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4268 - loss: 1.4863
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4389 - loss: 1.4506
[1m237/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4490 - loss: 1.4204
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4580 - loss: 1.3940
[1m295/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4649 - loss: 1.3740
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4684 - loss: 1.3637
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 13ms/step - accuracy: 0.4687 - loss: 1.3630 - val_accuracy: 0.6619 - val_loss: 0.7266
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.6250 - loss: 0.8613
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6226 - loss: 0.9620 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6214 - loss: 0.9530
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6215 - loss: 0.9473
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6205 - loss: 0.9454
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6202 - loss: 0.9416
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6204 - loss: 0.9371
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6208 - loss: 0.9325
[1m237/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6211 - loss: 0.9291
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6211 - loss: 0.9263
[1m296/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6213 - loss: 0.9238
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6214 - loss: 0.9224 - val_accuracy: 0.6713 - val_loss: 0.6597
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 27ms/step - accuracy: 0.7500 - loss: 0.8310
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6448 - loss: 0.8516 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6467 - loss: 0.8370
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6468 - loss: 0.8375
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6475 - loss: 0.8338
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6476 - loss: 0.8311
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6476 - loss: 0.8299
[1m210/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6474 - loss: 0.8291
[1m240/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6472 - loss: 0.8283
[1m270/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6472 - loss: 0.8273
[1m300/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6472 - loss: 0.8267
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6471 - loss: 0.8266 - val_accuracy: 0.6826 - val_loss: 0.6363
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.6875 - loss: 0.6556
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6614 - loss: 0.7966 
[1m 54/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6587 - loss: 0.8033
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6576 - loss: 0.8047
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6589 - loss: 0.7998
[1m143/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6590 - loss: 0.7981
[1m170/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6594 - loss: 0.7965
[1m197/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6595 - loss: 0.7950
[1m223/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6595 - loss: 0.7936
[1m254/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6596 - loss: 0.7921
[1m286/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6595 - loss: 0.7914
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6596 - loss: 0.7904 - val_accuracy: 0.6921 - val_loss: 0.6301
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7188 - loss: 0.7200
[1m 24/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7107 - loss: 0.6939 
[1m 54/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6927 - loss: 0.7267
[1m 82/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6888 - loss: 0.7322
[1m113/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6862 - loss: 0.7351
[1m145/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6839 - loss: 0.7373
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6825 - loss: 0.7391
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6817 - loss: 0.7404
[1m236/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6811 - loss: 0.7412
[1m264/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6804 - loss: 0.7419
[1m295/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6799 - loss: 0.7424
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6796 - loss: 0.7425 - val_accuracy: 0.6756 - val_loss: 0.6332
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7188 - loss: 0.7289
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6462 - loss: 0.7773 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6547 - loss: 0.7514
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6586 - loss: 0.7421
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6605 - loss: 0.7392
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6618 - loss: 0.7382
[1m184/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6629 - loss: 0.7374
[1m216/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6639 - loss: 0.7368
[1m246/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6649 - loss: 0.7368
[1m270/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6656 - loss: 0.7366
[1m299/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6664 - loss: 0.7362
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6668 - loss: 0.7359 - val_accuracy: 0.6928 - val_loss: 0.6301
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6875 - loss: 0.9726
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6692 - loss: 0.7908 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6681 - loss: 0.7609
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6675 - loss: 0.7525
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6680 - loss: 0.7488
[1m143/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6687 - loss: 0.7453
[1m170/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6695 - loss: 0.7421
[1m200/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6705 - loss: 0.7387
[1m224/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6714 - loss: 0.7363
[1m254/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6723 - loss: 0.7339
[1m284/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6734 - loss: 0.7319
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6745 - loss: 0.7301 - val_accuracy: 0.6914 - val_loss: 0.6391
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7812 - loss: 0.4477
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7056 - loss: 0.6311 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7003 - loss: 0.6467
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6970 - loss: 0.6607
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6965 - loss: 0.6674
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6961 - loss: 0.6712
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6956 - loss: 0.6735
[1m210/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6956 - loss: 0.6747
[1m241/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6954 - loss: 0.6765
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6953 - loss: 0.6775
[1m300/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6952 - loss: 0.6783
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6952 - loss: 0.6786 - val_accuracy: 0.6893 - val_loss: 0.6374
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.7500 - loss: 0.4458
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7099 - loss: 0.6415 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7037 - loss: 0.6567
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7025 - loss: 0.6615
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7020 - loss: 0.6626
[1m146/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7020 - loss: 0.6642
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7028 - loss: 0.6648
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7031 - loss: 0.6655
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7033 - loss: 0.6655
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7034 - loss: 0.6653
[1m297/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7035 - loss: 0.6650
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7035 - loss: 0.6649 - val_accuracy: 0.6886 - val_loss: 0.6520

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 484ms/step2025-11-08 15:03:51.157135: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 25ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 25ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:45[0m 1s/step
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 934us/step
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 899us/step
[1m169/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 906us/step
[1m223/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 915us/step
[1m281/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 905us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 17ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 21ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 21ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m55/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 929us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 70.44 [%]
Global F1 score (validation) = 71.31 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[5.2204907e-01 3.9726675e-01 8.4167477e-03 7.2267339e-02]
 [3.8785174e-01 5.7230002e-01 5.4715564e-03 3.4376625e-02]
 [3.9868441e-01 5.6682158e-01 1.5221011e-02 1.9273030e-02]
 ...
 [1.6813519e-04 1.4683371e-03 1.4446452e-03 9.9691892e-01]
 [5.6091420e-05 4.7646819e-05 2.9117847e-04 9.9960506e-01]
 [2.5280394e-02 1.0887369e-02 6.4062959e-01 3.2320264e-01]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 77.45 [%]
Global accuracy score (test) = 72.57 [%]
Global F1 score (train) = 77.7 [%]
Global F1 score (test) = 73.19 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.53      0.70      0.60       350
MODERATE-INTENSITY       0.53      0.43      0.47       350
         SEDENTARY       0.98      0.98      0.98       350
VIGOROUS-INTENSITY       0.94      0.81      0.87       299

          accuracy                           0.73      1349
         macro avg       0.75      0.73      0.73      1349
      weighted avg       0.74      0.73      0.73      1349


Accuracy capturado en la ejecución 25: 72.57 [%]
F1-score capturado en la ejecución 25: 73.19 [%]

=== EJECUCIÓN 26 ===

--- TRAIN (ejecución 26) ---

--- TEST (ejecución 26) ---
2025-11-08 15:04:02.186683: 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`.
2025-11-08 15:04:02.197853: 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 00:00:1762610642.210915 1021339 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762610642.214883 1021339 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762610642.225123 1021339 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610642.225141 1021339 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610642.225143 1021339 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610642.225145 1021339 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 15:04:02.228338: 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 00:00:1762610644.444441 1021339 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762610646.917055 1021470 service.cc:152] XLA service 0x77ee14017bb0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762610646.917104 1021470 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 15:04:06.981838: 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 00:00:1762610647.302495 1021470 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762610649.650596 1021470 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:34[0m 5s/step - accuracy: 0.0938 - loss: 2.6359
[1m 24/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2398 - loss: 2.0589  
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2921 - loss: 1.8965
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3307 - loss: 1.7885
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7094
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3784 - loss: 1.6507
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3932 - loss: 1.6077
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4081 - loss: 1.5644
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4200 - loss: 1.5299
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4302 - loss: 1.5006
[1m299/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4399 - loss: 1.4721
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4430 - loss: 1.4631
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 13ms/step - accuracy: 0.4432 - loss: 1.4623 - val_accuracy: 0.6436 - val_loss: 0.7380
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6562 - loss: 0.9727
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5682 - loss: 1.0745 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5801 - loss: 1.0376
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5882 - loss: 1.0135
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5931 - loss: 1.0010
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5964 - loss: 0.9918
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5990 - loss: 0.9849
[1m209/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6012 - loss: 0.9787
[1m241/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6030 - loss: 0.9734
[1m272/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6043 - loss: 0.9691
[1m303/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6055 - loss: 0.9653
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6057 - loss: 0.9644 - val_accuracy: 0.6787 - val_loss: 0.6852
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 23ms/step - accuracy: 0.7812 - loss: 0.6399
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6444 - loss: 0.8732 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6354 - loss: 0.8988
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6339 - loss: 0.8972
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6334 - loss: 0.8933
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6336 - loss: 0.8911
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6337 - loss: 0.8901
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6342 - loss: 0.8881
[1m243/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6353 - loss: 0.8845
[1m273/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6363 - loss: 0.8810
[1m300/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6370 - loss: 0.8785
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6373 - loss: 0.8776 - val_accuracy: 0.6759 - val_loss: 0.6658
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5000 - loss: 0.9428
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6335 - loss: 0.8129 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6392 - loss: 0.8170
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6421 - loss: 0.8165
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6438 - loss: 0.8175
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6453 - loss: 0.8172
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6468 - loss: 0.8158
[1m204/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6481 - loss: 0.8148
[1m230/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6492 - loss: 0.8140
[1m261/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6503 - loss: 0.8123
[1m288/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6510 - loss: 0.8110
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6516 - loss: 0.8099 - val_accuracy: 0.6784 - val_loss: 0.6585
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6875 - loss: 0.7045
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6736 - loss: 0.6926 
[1m 54/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6674 - loss: 0.7296
[1m 82/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6662 - loss: 0.7443
[1m112/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6644 - loss: 0.7519
[1m141/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6627 - loss: 0.7583
[1m168/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6621 - loss: 0.7608
[1m197/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6618 - loss: 0.7625
[1m223/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6614 - loss: 0.7640
[1m253/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6609 - loss: 0.7654
[1m283/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6606 - loss: 0.7661
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6605 - loss: 0.7662
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6605 - loss: 0.7662 - val_accuracy: 0.6886 - val_loss: 0.6401
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6250 - loss: 0.6029
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6677 - loss: 0.6749 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6723 - loss: 0.6930
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6762 - loss: 0.6990
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6780 - loss: 0.7034
[1m146/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6786 - loss: 0.7085
[1m175/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6788 - loss: 0.7127
[1m204/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6786 - loss: 0.7149
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6785 - loss: 0.7167
[1m263/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6782 - loss: 0.7185
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6778 - loss: 0.7201
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6775 - loss: 0.7210 - val_accuracy: 0.6970 - val_loss: 0.6339
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6875 - loss: 0.7851
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6835 - loss: 0.7274 
[1m 63/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6812 - loss: 0.7379
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6831 - loss: 0.7354
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6849 - loss: 0.7315
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6854 - loss: 0.7293
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6860 - loss: 0.7273
[1m211/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6867 - loss: 0.7255
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6875 - loss: 0.7233
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6881 - loss: 0.7219
[1m299/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6885 - loss: 0.7210
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6886 - loss: 0.7207 - val_accuracy: 0.6886 - val_loss: 0.6557
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6875 - loss: 0.6989
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6875 - loss: 0.6771 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6968 - loss: 0.6734
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6991 - loss: 0.6782
[1m121/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6994 - loss: 0.6829
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7001 - loss: 0.6851
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7005 - loss: 0.6865
[1m210/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7009 - loss: 0.6864
[1m239/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7012 - loss: 0.6861
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7012 - loss: 0.6859
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7013 - loss: 0.6854
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7013 - loss: 0.6852 - val_accuracy: 0.6998 - val_loss: 0.6412
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.7500 - loss: 0.5330
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7101 - loss: 0.6529 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7072 - loss: 0.6561
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7070 - loss: 0.6602
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7054 - loss: 0.6639
[1m146/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7038 - loss: 0.6678
[1m175/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7029 - loss: 0.6695
[1m203/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7025 - loss: 0.6699
[1m234/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7023 - loss: 0.6700
[1m260/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7024 - loss: 0.6705
[1m291/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7024 - loss: 0.6710
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7024 - loss: 0.6712 - val_accuracy: 0.7047 - val_loss: 0.6448
Epoch 10/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7500 - loss: 0.5595
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6795 - loss: 0.6852 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6900 - loss: 0.6748
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6942 - loss: 0.6713
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6971 - loss: 0.6678
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6992 - loss: 0.6654
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7014 - loss: 0.6635
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7034 - loss: 0.6614
[1m235/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7052 - loss: 0.6593
[1m264/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7066 - loss: 0.6579
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7076 - loss: 0.6570
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7082 - loss: 0.6565 - val_accuracy: 0.7047 - val_loss: 0.6548
Epoch 11/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.6562 - loss: 0.7907
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7087 - loss: 0.7068 
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7118 - loss: 0.6899
[1m 85/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7120 - loss: 0.6826
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7134 - loss: 0.6744
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7140 - loss: 0.6687
[1m170/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7145 - loss: 0.6650
[1m200/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7149 - loss: 0.6617
[1m228/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7150 - loss: 0.6592
[1m259/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7154 - loss: 0.6568
[1m286/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7159 - loss: 0.6550
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7163 - loss: 0.6537 - val_accuracy: 0.7040 - val_loss: 0.6646

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 492ms/step2025-11-08 15:04:22.086048: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 25ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 25ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:43[0m 1s/step
[1m 53/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 976us/step
[1m107/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 957us/step
[1m167/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 915us/step
[1m228/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 893us/step
[1m290/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 877us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 22ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 22ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m52/89[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 981us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 69.7 [%]
Global F1 score (validation) = 70.36 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[6.13976300e-01 3.41167420e-01 2.68351361e-02 1.80211775e-02]
 [6.11810386e-01 3.54874492e-01 1.58656873e-02 1.74494833e-02]
 [6.14113808e-01 3.41417819e-01 2.66443957e-02 1.78240109e-02]
 ...
 [1.04332896e-04 1.83497483e-04 1.12830021e-03 9.98583913e-01]
 [9.04850531e-05 2.16706394e-04 5.12919039e-04 9.99179900e-01]
 [3.56569490e-03 4.16824315e-03 6.45324230e-01 3.46941918e-01]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 73.64 [%]
Global accuracy score (test) = 73.09 [%]
Global F1 score (train) = 73.65 [%]
Global F1 score (test) = 73.79 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.57      0.49      0.53       350
MODERATE-INTENSITY       0.51      0.60      0.55       350
         SEDENTARY       0.98      0.98      0.98       350
VIGOROUS-INTENSITY       0.91      0.87      0.89       299

          accuracy                           0.73      1349
         macro avg       0.74      0.74      0.74      1349
      weighted avg       0.74      0.73      0.73      1349


Accuracy capturado en la ejecución 26: 73.09 [%]
F1-score capturado en la ejecución 26: 73.79 [%]

=== EJECUCIÓN 27 ===

--- TRAIN (ejecución 27) ---

--- TEST (ejecución 27) ---
2025-11-08 15:04:33.034171: 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`.
2025-11-08 15:04:33.045790: 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 00:00:1762610673.059047 1023383 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762610673.063012 1023383 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762610673.073196 1023383 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610673.073213 1023383 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610673.073215 1023383 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610673.073216 1023383 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 15:04:33.076133: 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 00:00:1762610675.293904 1023383 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762610677.797075 1023514 service.cc:152] XLA service 0x721d90015310 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762610677.797105 1023514 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 15:04:37.857056: 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 00:00:1762610678.193190 1023514 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762610680.608801 1023514 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24:06[0m 5s/step - accuracy: 0.2812 - loss: 1.6507
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3610 - loss: 1.6094  
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3961 - loss: 1.5196
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4159 - loss: 1.4671
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4307 - loss: 1.4260
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4430 - loss: 1.3929
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4538 - loss: 1.3641
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4630 - loss: 1.3395
[1m239/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4714 - loss: 1.3183
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4784 - loss: 1.3005
[1m296/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4843 - loss: 1.2850
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4871 - loss: 1.2777
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 13ms/step - accuracy: 0.4873 - loss: 1.2772 - val_accuracy: 0.6685 - val_loss: 0.7661
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.5938 - loss: 0.8040
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6352 - loss: 0.8432 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6381 - loss: 0.8554
[1m 92/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6350 - loss: 0.8720
[1m123/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6326 - loss: 0.8834
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6311 - loss: 0.8896
[1m183/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6295 - loss: 0.8948
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6286 - loss: 0.8979
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6278 - loss: 0.9003
[1m274/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6272 - loss: 0.9020
[1m306/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6268 - loss: 0.9027
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6268 - loss: 0.9027 - val_accuracy: 0.6819 - val_loss: 0.6692
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.6250 - loss: 0.8167
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6021 - loss: 0.8801 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6144 - loss: 0.8635
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6239 - loss: 0.8527
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6305 - loss: 0.8434
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6341 - loss: 0.8378
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6365 - loss: 0.8345
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6388 - loss: 0.8318
[1m236/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6401 - loss: 0.8301
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6411 - loss: 0.8284
[1m296/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6417 - loss: 0.8275
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6420 - loss: 0.8271 - val_accuracy: 0.6791 - val_loss: 0.6771
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.5938 - loss: 0.8569
[1m 33/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6597 - loss: 0.8299 
[1m 65/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6700 - loss: 0.8054
[1m 97/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6710 - loss: 0.7979
[1m126/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6714 - loss: 0.7938
[1m159/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6714 - loss: 0.7901
[1m190/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6711 - loss: 0.7888
[1m222/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6706 - loss: 0.7880
[1m255/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6702 - loss: 0.7875
[1m287/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6700 - loss: 0.7872
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6698 - loss: 0.7869 - val_accuracy: 0.6893 - val_loss: 0.6426
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7188 - loss: 0.6826
[1m 25/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6927 - loss: 0.7230 
[1m 54/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6873 - loss: 0.7358
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6878 - loss: 0.7345
[1m116/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6865 - loss: 0.7380
[1m145/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6845 - loss: 0.7405
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6826 - loss: 0.7429
[1m200/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6812 - loss: 0.7446
[1m228/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6799 - loss: 0.7459
[1m255/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6789 - loss: 0.7468
[1m287/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6783 - loss: 0.7473
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6780 - loss: 0.7474 - val_accuracy: 0.6910 - val_loss: 0.6479
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.8438 - loss: 0.4663
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7134 - loss: 0.6304 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6976 - loss: 0.6644
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6914 - loss: 0.6805
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6889 - loss: 0.6890
[1m151/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6871 - loss: 0.6958
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6861 - loss: 0.6996
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6857 - loss: 0.7018
[1m237/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6852 - loss: 0.7038
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6848 - loss: 0.7059
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6846 - loss: 0.7076
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6845 - loss: 0.7084 - val_accuracy: 0.6868 - val_loss: 0.6441
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.8125 - loss: 0.4589
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6898 - loss: 0.6551 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6916 - loss: 0.6684
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6921 - loss: 0.6746
[1m123/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6921 - loss: 0.6797
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6931 - loss: 0.6814
[1m183/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6936 - loss: 0.6834
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6938 - loss: 0.6854
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6939 - loss: 0.6870
[1m273/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6939 - loss: 0.6883
[1m302/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6941 - loss: 0.6890
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6942 - loss: 0.6890 - val_accuracy: 0.6900 - val_loss: 0.6432
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6250 - loss: 0.6789
[1m 32/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6842 - loss: 0.7044 
[1m 64/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6925 - loss: 0.6968
[1m 95/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6952 - loss: 0.6936
[1m124/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6962 - loss: 0.6924
[1m156/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6965 - loss: 0.6932
[1m185/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6969 - loss: 0.6932
[1m214/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6975 - loss: 0.6931
[1m247/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6982 - loss: 0.6924
[1m280/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6987 - loss: 0.6921
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6993 - loss: 0.6918 - val_accuracy: 0.6907 - val_loss: 0.6566
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7188 - loss: 0.5851
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7112 - loss: 0.6631 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7117 - loss: 0.6656
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7114 - loss: 0.6657
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7121 - loss: 0.6634
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7124 - loss: 0.6638
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7138 - loss: 0.6634
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7147 - loss: 0.6630
[1m243/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7151 - loss: 0.6625
[1m273/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7151 - loss: 0.6621
[1m304/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7149 - loss: 0.6618
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7148 - loss: 0.6618 - val_accuracy: 0.6949 - val_loss: 0.6570

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 485ms/step2025-11-08 15:04:51.481518: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 24ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 24ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:45[0m 1s/step
[1m 48/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m 96/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step
[1m155/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 985us/step
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 954us/step
[1m272/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 933us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 21ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 21ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m53/89[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 976us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 70.44 [%]
Global F1 score (validation) = 70.84 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[6.3049370e-01 3.2961988e-01 2.2410071e-02 1.7476348e-02]
 [4.9589345e-01 3.8591558e-01 2.0305857e-02 9.7885057e-02]
 [5.7248276e-01 3.7773022e-01 2.8197171e-02 2.1589795e-02]
 ...
 [4.9775682e-04 6.4410036e-04 3.3254435e-03 9.9553275e-01]
 [8.0026849e-04 7.1579480e-04 8.5180048e-03 9.8996598e-01]
 [3.0409100e-03 3.9929166e-03 9.7114253e-01 2.1823561e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 75.0 [%]
Global accuracy score (test) = 73.46 [%]
Global F1 score (train) = 75.2 [%]
Global F1 score (test) = 74.21 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.52      0.67      0.59       350
MODERATE-INTENSITY       0.57      0.46      0.51       350
         SEDENTARY       0.98      0.98      0.98       350
VIGOROUS-INTENSITY       0.95      0.84      0.89       299

          accuracy                           0.73      1349
         macro avg       0.76      0.74      0.74      1349
      weighted avg       0.75      0.73      0.74      1349


Accuracy capturado en la ejecución 27: 73.46 [%]
F1-score capturado en la ejecución 27: 74.21 [%]

=== EJECUCIÓN 28 ===

--- TRAIN (ejecución 28) ---

--- TEST (ejecución 28) ---
2025-11-08 15:05:02.338944: 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`.
2025-11-08 15:05:02.350143: 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 00:00:1762610702.363316 1025223 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762610702.367475 1025223 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762610702.377198 1025223 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610702.377214 1025223 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610702.377215 1025223 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610702.377216 1025223 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 15:05:02.380469: 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 00:00:1762610704.603243 1025223 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762610707.086407 1025352 service.cc:152] XLA service 0x766b4c015470 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762610707.086451 1025352 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 15:05:07.164204: 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 00:00:1762610707.489185 1025352 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762610709.877414 1025352 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:53[0m 5s/step - accuracy: 0.2500 - loss: 1.9960
[1m 24/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2938 - loss: 1.7003  
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3404 - loss: 1.6010
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3708 - loss: 1.5311
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3941 - loss: 1.4763
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4117 - loss: 1.4352
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4253 - loss: 1.4024
[1m202/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4359 - loss: 1.3763
[1m233/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4460 - loss: 1.3508
[1m262/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4541 - loss: 1.3303
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4618 - loss: 1.3107
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4657 - loss: 1.3011
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 13ms/step - accuracy: 0.4659 - loss: 1.3005 - val_accuracy: 0.6436 - val_loss: 0.7526
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.5625 - loss: 1.1522
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6374 - loss: 0.8900 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6273 - loss: 0.9008
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6261 - loss: 0.9035
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6253 - loss: 0.9045
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6240 - loss: 0.9060
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6235 - loss: 0.9051
[1m211/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6235 - loss: 0.9029
[1m239/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6235 - loss: 0.9006
[1m270/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6241 - loss: 0.8976
[1m301/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6246 - loss: 0.8948
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6247 - loss: 0.8941 - val_accuracy: 0.6703 - val_loss: 0.6747
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.5312 - loss: 0.9861
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.5983 - loss: 0.8891 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6165 - loss: 0.8632
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6261 - loss: 0.8473
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6298 - loss: 0.8433
[1m146/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6323 - loss: 0.8400
[1m171/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6337 - loss: 0.8372
[1m201/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6349 - loss: 0.8341
[1m234/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6361 - loss: 0.8316
[1m263/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6367 - loss: 0.8303
[1m296/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6374 - loss: 0.8289
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6376 - loss: 0.8285 - val_accuracy: 0.6717 - val_loss: 0.6591
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6875 - loss: 0.7466
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6382 - loss: 0.8272 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6467 - loss: 0.8102
[1m 95/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6475 - loss: 0.8068
[1m126/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6489 - loss: 0.8040
[1m157/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6493 - loss: 0.8044
[1m186/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6495 - loss: 0.8043
[1m218/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6505 - loss: 0.8025
[1m246/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6514 - loss: 0.8011
[1m276/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6521 - loss: 0.7996
[1m308/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6526 - loss: 0.7976
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6527 - loss: 0.7974 - val_accuracy: 0.6801 - val_loss: 0.6610
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6875 - loss: 0.6546
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6989 - loss: 0.7305 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6900 - loss: 0.7423
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6878 - loss: 0.7393
[1m124/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6862 - loss: 0.7393
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6844 - loss: 0.7413
[1m185/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6825 - loss: 0.7439
[1m218/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6809 - loss: 0.7460
[1m248/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6797 - loss: 0.7476
[1m281/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6790 - loss: 0.7482
[1m309/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6785 - loss: 0.7487
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6785 - loss: 0.7487 - val_accuracy: 0.6784 - val_loss: 0.6581
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.4062 - loss: 0.8870
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6237 - loss: 0.7643 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6419 - loss: 0.7561
[1m 92/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6523 - loss: 0.7482
[1m124/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6582 - loss: 0.7448
[1m154/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6616 - loss: 0.7434
[1m186/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6639 - loss: 0.7429
[1m218/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6659 - loss: 0.7417
[1m248/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6672 - loss: 0.7409
[1m276/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6683 - loss: 0.7401
[1m307/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6692 - loss: 0.7393
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6694 - loss: 0.7392 - val_accuracy: 0.6773 - val_loss: 0.6582
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6562 - loss: 0.6831
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6923 - loss: 0.7116 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6902 - loss: 0.7201
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6915 - loss: 0.7182
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6917 - loss: 0.7167
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6915 - loss: 0.7165
[1m182/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6912 - loss: 0.7163
[1m210/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6906 - loss: 0.7165
[1m241/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6900 - loss: 0.7159
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6896 - loss: 0.7152
[1m300/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6894 - loss: 0.7145
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6894 - loss: 0.7143 - val_accuracy: 0.6868 - val_loss: 0.6595
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7812 - loss: 0.4425
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7002 - loss: 0.6668 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6962 - loss: 0.6797
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6927 - loss: 0.6847
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6910 - loss: 0.6872
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6904 - loss: 0.6884
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6899 - loss: 0.6892
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6892 - loss: 0.6906
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6889 - loss: 0.6908
[1m270/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6888 - loss: 0.6911
[1m300/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6888 - loss: 0.6913
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6888 - loss: 0.6914 - val_accuracy: 0.6900 - val_loss: 0.6555
Epoch 9/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.6875 - loss: 0.5823
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6985 - loss: 0.6609 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6896 - loss: 0.6758
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6893 - loss: 0.6779
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6906 - loss: 0.6768
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6923 - loss: 0.6766
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6935 - loss: 0.6760
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6946 - loss: 0.6752
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6955 - loss: 0.6747
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6958 - loss: 0.6748
[1m302/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6961 - loss: 0.6746
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6963 - loss: 0.6745 - val_accuracy: 0.6864 - val_loss: 0.6583
Epoch 10/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.7500 - loss: 0.5503
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6956 - loss: 0.6510 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6959 - loss: 0.6615
[1m 92/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7008 - loss: 0.6563
[1m124/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7032 - loss: 0.6540
[1m154/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7039 - loss: 0.6545
[1m184/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7038 - loss: 0.6547
[1m215/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7042 - loss: 0.6543
[1m244/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7042 - loss: 0.6544
[1m275/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7044 - loss: 0.6548
[1m306/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7045 - loss: 0.6551
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7045 - loss: 0.6552 - val_accuracy: 0.6931 - val_loss: 0.6546
Epoch 11/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.8438 - loss: 0.5867
[1m 32/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7236 - loss: 0.6359 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7191 - loss: 0.6435
[1m 94/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7165 - loss: 0.6480
[1m127/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7157 - loss: 0.6495
[1m159/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7145 - loss: 0.6505
[1m189/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7139 - loss: 0.6498
[1m219/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7134 - loss: 0.6490
[1m247/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7131 - loss: 0.6490
[1m278/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7129 - loss: 0.6486
[1m308/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7126 - loss: 0.6484
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7126 - loss: 0.6484 - val_accuracy: 0.6931 - val_loss: 0.6558
Epoch 12/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6562 - loss: 0.7771
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7226 - loss: 0.6259 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7281 - loss: 0.6114
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7283 - loss: 0.6100
[1m119/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7276 - loss: 0.6133
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7271 - loss: 0.6168
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7272 - loss: 0.6181
[1m211/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7272 - loss: 0.6187
[1m240/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7274 - loss: 0.6189
[1m272/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7276 - loss: 0.6190
[1m301/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7278 - loss: 0.6189
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7278 - loss: 0.6190 - val_accuracy: 0.6907 - val_loss: 0.6584
Epoch 13/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.9375 - loss: 0.3209
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7695 - loss: 0.5158 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7500 - loss: 0.5650
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7418 - loss: 0.5877
[1m124/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7375 - loss: 0.5996
[1m153/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7351 - loss: 0.6058
[1m182/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7333 - loss: 0.6097
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7322 - loss: 0.6122
[1m244/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7312 - loss: 0.6137
[1m275/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7305 - loss: 0.6146
[1m305/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7301 - loss: 0.6150
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7300 - loss: 0.6151 - val_accuracy: 0.6917 - val_loss: 0.6585
Epoch 14/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.8438 - loss: 0.5183
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7519 - loss: 0.5953 
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7492 - loss: 0.5983
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7444 - loss: 0.6041
[1m116/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7417 - loss: 0.6069
[1m146/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7403 - loss: 0.6074
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7394 - loss: 0.6073
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7383 - loss: 0.6073
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7372 - loss: 0.6074
[1m270/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7361 - loss: 0.6075
[1m299/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.7354 - loss: 0.6072
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7352 - loss: 0.6071 - val_accuracy: 0.6805 - val_loss: 0.6621
Epoch 15/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.8750 - loss: 0.5286
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7583 - loss: 0.5659 
[1m 58/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7536 - loss: 0.5712
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7492 - loss: 0.5766
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7475 - loss: 0.5792
[1m146/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7461 - loss: 0.5813
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7449 - loss: 0.5830
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7441 - loss: 0.5838
[1m236/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7438 - loss: 0.5843
[1m266/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7433 - loss: 0.5847
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.7430 - loss: 0.5850
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.7429 - loss: 0.5853 - val_accuracy: 0.6819 - val_loss: 0.6632

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 516ms/step2025-11-08 15:05:25.080276: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 25ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 26ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:29[0m 1s/step
[1m 53/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 965us/step
[1m112/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 908us/step
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 877us/step
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 852us/step
[1m297/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 851us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 21ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 21ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m54/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 952us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step  
Global accuracy score (validation) = 68.96 [%]
Global F1 score (validation) = 66.72 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[5.5656272e-01 2.9501036e-01 7.0317280e-03 1.4139523e-01]
 [5.9504640e-01 3.7438354e-01 4.8022936e-03 2.5767781e-02]
 [7.5923234e-01 2.0012312e-01 2.3713734e-02 1.6930766e-02]
 ...
 [9.2876790e-04 8.0718304e-04 9.8252716e-03 9.8843879e-01]
 [2.5410068e-04 2.9783914e-04 9.3715591e-03 9.9007660e-01]
 [2.6483119e-03 1.6611750e-03 8.9244258e-01 1.0324794e-01]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 72.85 [%]
Global accuracy score (test) = 71.98 [%]
Global F1 score (train) = 71.11 [%]
Global F1 score (test) = 70.34 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.51      0.87      0.64       350
MODERATE-INTENSITY       0.56      0.21      0.31       350
         SEDENTARY       0.98      0.99      0.98       350
VIGOROUS-INTENSITY       0.95      0.82      0.88       299

          accuracy                           0.72      1349
         macro avg       0.75      0.72      0.70      1349
      weighted avg       0.74      0.72      0.70      1349


Accuracy capturado en la ejecución 28: 71.98 [%]
F1-score capturado en la ejecución 28: 70.34 [%]

=== EJECUCIÓN 29 ===

--- TRAIN (ejecución 29) ---

--- TEST (ejecución 29) ---
2025-11-08 15:05:36.035499: 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`.
2025-11-08 15:05:36.046764: 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 00:00:1762610736.059778 1027641 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762610736.063934 1027641 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762610736.073632 1027641 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610736.073649 1027641 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610736.073651 1027641 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762610736.073652 1027641 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-08 15:05:36.076819: 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 00:00:1762610738.295016 1027641 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..
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762610740.768165 1027740 service.cc:152] XLA service 0x7e2b140026b0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762610740.768195 1027740 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-08 15:05:40.821774: 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 00:00:1762610741.132018 1027740 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762610743.529662 1027740 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23:43[0m 5s/step - accuracy: 0.2500 - loss: 2.0762
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3300 - loss: 1.7539  
[1m 55/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3685 - loss: 1.6398
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3991 - loss: 1.5578
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4195 - loss: 1.5006
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4364 - loss: 1.4522
[1m174/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4476 - loss: 1.4192
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4590 - loss: 1.3864
[1m236/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4685 - loss: 1.3594
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4768 - loss: 1.3365
[1m296/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4834 - loss: 1.3182
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.4864 - loss: 1.3100
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 13ms/step - accuracy: 0.4866 - loss: 1.3094 - val_accuracy: 0.6738 - val_loss: 0.6981
Epoch 2/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.7500 - loss: 0.5980
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6248 - loss: 0.9180 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6144 - loss: 0.9435
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6105 - loss: 0.9563
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6087 - loss: 0.9605
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6073 - loss: 0.9626
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6071 - loss: 0.9627
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6075 - loss: 0.9609
[1m239/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6084 - loss: 0.9580
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6093 - loss: 0.9551
[1m299/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6103 - loss: 0.9519
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6108 - loss: 0.9507 - val_accuracy: 0.6956 - val_loss: 0.6452
Epoch 3/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5625 - loss: 1.0166
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6508 - loss: 0.8391 
[1m 59/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6544 - loss: 0.8249
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6531 - loss: 0.8233
[1m123/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6509 - loss: 0.8280
[1m152/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6501 - loss: 0.8293
[1m183/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6492 - loss: 0.8307
[1m214/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6485 - loss: 0.8319
[1m245/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6477 - loss: 0.8330
[1m276/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6473 - loss: 0.8334
[1m305/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6470 - loss: 0.8334
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6469 - loss: 0.8334 - val_accuracy: 0.6931 - val_loss: 0.6411
Epoch 4/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6875 - loss: 0.8616
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6466 - loss: 0.8042 
[1m 53/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6540 - loss: 0.7889
[1m 83/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6555 - loss: 0.7850
[1m113/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6546 - loss: 0.7863
[1m142/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6539 - loss: 0.7899
[1m169/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6535 - loss: 0.7929
[1m197/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6534 - loss: 0.7950
[1m228/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6534 - loss: 0.7964
[1m258/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6535 - loss: 0.7970
[1m289/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.6537 - loss: 0.7974
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6539 - loss: 0.7977 - val_accuracy: 0.6935 - val_loss: 0.6415
Epoch 5/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6875 - loss: 0.7229
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6670 - loss: 0.7459 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6744 - loss: 0.7417
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6787 - loss: 0.7374
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6807 - loss: 0.7362
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6810 - loss: 0.7361
[1m179/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6811 - loss: 0.7365
[1m211/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6810 - loss: 0.7368
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6807 - loss: 0.7382
[1m273/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6802 - loss: 0.7399
[1m305/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6798 - loss: 0.7414
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6797 - loss: 0.7416 - val_accuracy: 0.6893 - val_loss: 0.6494
Epoch 6/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.6875 - loss: 0.6841
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6762 - loss: 0.7070 
[1m 54/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6861 - loss: 0.7139
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6866 - loss: 0.7164
[1m115/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6879 - loss: 0.7151
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6874 - loss: 0.7159
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6868 - loss: 0.7168
[1m203/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6860 - loss: 0.7177
[1m232/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6855 - loss: 0.7181
[1m264/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6850 - loss: 0.7185
[1m296/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6843 - loss: 0.7194
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6841 - loss: 0.7198 - val_accuracy: 0.6935 - val_loss: 0.6458
Epoch 7/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.5000 - loss: 0.9644
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6681 - loss: 0.7816 
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6689 - loss: 0.7647
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6720 - loss: 0.7570
[1m116/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6736 - loss: 0.7533
[1m146/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6761 - loss: 0.7471
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6776 - loss: 0.7435
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6792 - loss: 0.7402
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6805 - loss: 0.7372
[1m266/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6815 - loss: 0.7349
[1m296/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6825 - loss: 0.7328
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6829 - loss: 0.7320 - val_accuracy: 0.6861 - val_loss: 0.6556
Epoch 8/27

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.7188 - loss: 0.6096
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6534 - loss: 0.7329 
[1m 63/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6706 - loss: 0.7137
[1m 93/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6776 - loss: 0.7087
[1m124/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6815 - loss: 0.7064
[1m155/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6842 - loss: 0.7044
[1m186/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6862 - loss: 0.7015
[1m215/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6875 - loss: 0.6992
[1m245/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6884 - loss: 0.6981
[1m278/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6895 - loss: 0.6972
[1m304/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.6900 - loss: 0.6968
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 2ms/step - accuracy: 0.6901 - loss: 0.6966 - val_accuracy: 0.6928 - val_loss: 0.6503

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 489ms/step2025-11-08 15:05:53.730600: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_141', 8 bytes spill stores, 8 bytes spill loads


[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 24ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 25ms/step
Saved model to disk.
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:38[0m 1s/step
[1m 51/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m111/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 921us/step
[1m168/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 908us/step
[1m226/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 896us/step
[1m282/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 897us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 21ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 21ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m49/89[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step
Global accuracy score (validation) = 68.86 [%]
Global F1 score (validation) = 70.06 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[3.5322973e-01 5.3044808e-01 4.3300919e-02 7.3021293e-02]
 [3.3992839e-01 6.1664325e-01 1.6094945e-02 2.7333437e-02]
 [4.7449750e-01 4.9539554e-01 1.6467903e-02 1.3639081e-02]
 ...
 [1.3989934e-03 2.6618910e-03 1.0871577e-02 9.8506755e-01]
 [1.2412184e-04 1.3618785e-04 2.2461282e-03 9.9749362e-01]
 [3.3088678e-03 4.3794448e-03 9.8160237e-01 1.0709277e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 75.77 [%]
Global accuracy score (test) = 73.91 [%]
Global F1 score (train) = 76.2 [%]
Global F1 score (test) = 74.93 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.57      0.54      0.55       350
MODERATE-INTENSITY       0.54      0.63      0.58       350
         SEDENTARY       0.98      0.99      0.98       350
VIGOROUS-INTENSITY       0.97      0.80      0.88       299

          accuracy                           0.74      1349
         macro avg       0.76      0.74      0.75      1349
      weighted avg       0.76      0.74      0.74      1349


Accuracy capturado en la ejecución 29: 73.91 [%]
F1-score capturado en la ejecución 29: 74.93 [%]

=== EJECUCIÓN 30 ===

--- TRAIN (ejecución 30) ---

--- TEST (ejecución 30) ---
['LIGHT-INTENSITY' 'MODERATE-INTENSITY' 'SEDENTARY' 'VIGOROUS-INTENSITY']
4
Mapeo de etiquetas: {'LIGHT-INTENSITY': 0, 'MODERATE-INTENSITY': 1, 'SEDENTARY': 2, 'VIGOROUS-INTENSITY': 3}
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
This activity can't be balanced (in a downsampling way)
Loaded model from disk.
(1349, 3, 250)
(9904, 3, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:43[0m 1s/step
[1m 52/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 993us/step
[1m109/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 934us/step
[1m164/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 929us/step
[1m222/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 912us/step
[1m274/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 924us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 4ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 21ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 22ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m59/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 866us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 987us/step
Global accuracy score (validation) = 68.68 [%]
Global F1 score (validation) = 69.34 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[5.8253145e-01 3.5427722e-01 2.3715269e-02 3.9476015e-02]
 [4.2911711e-01 4.9145138e-01 2.3279864e-02 5.6151688e-02]
 [6.0630912e-01 3.6033008e-01 2.3411775e-02 9.9491160e-03]
 ...
 [2.4458591e-04 5.3762813e-04 1.5984240e-03 9.9761933e-01]
 [1.2795537e-04 8.4879888e-05 1.1556845e-03 9.9863142e-01]
 [1.9900615e-03 2.1237121e-03 9.2645723e-01 6.9428980e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 73.38 [%]
Global accuracy score (test) = 72.57 [%]
Global F1 score (train) = 73.68 [%]
Global F1 score (test) = 73.64 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.54      0.58      0.56       350
MODERATE-INTENSITY       0.50      0.52      0.51       350
         SEDENTARY       0.98      0.99      0.99       350
VIGOROUS-INTENSITY       0.96      0.83      0.89       299

          accuracy                           0.73      1349
         macro avg       0.75      0.73      0.74      1349
      weighted avg       0.74      0.73      0.73      1349


Accuracy capturado en la ejecución 30: 72.57 [%]
F1-score capturado en la ejecución 30: 73.64 [%]

=== RESUMEN FINAL ===
Accuracies: [72.05, 73.61, 74.72, 73.24, 71.98, 72.2, 72.72, 72.94, 72.42, 72.2, 72.2, 74.72, 73.98, 72.5, 70.57, 73.46, 73.68, 74.72, 71.76, 74.35, 71.76, 72.35, 70.27, 75.02, 72.57, 73.09, 73.46, 71.98, 73.91, 72.57]
F1-scores: [72.5, 74.57, 75.57, 73.99, 73.28, 72.55, 73.63, 73.55, 73.4, 73.22, 73.19, 74.51, 74.69, 73.55, 71.83, 74.35, 74.23, 75.07, 71.49, 75.09, 72.32, 73.19, 70.04, 75.78, 73.19, 73.79, 74.21, 70.34, 74.93, 73.64]
Accuracy mean: 72.9000 | std: 1.1603
F1 mean: 73.5230 | std: 1.3505

Resultados guardados en /mnt/nvme1n2/git/uniovi-simur-wearablepermed-data/output/Paper_results/cases_dataset_PI/case_PI_CAPTURE24_acc_superclasses_CPA_METs/metrics_test.npz
