2025-11-04 12:01:55.309179: 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`.
2025-11-04 12:01:55.320244: 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 00:00:1762254115.333930 1125391 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762254115.338125 1125391 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762254115.348675 1125391 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254115.348696 1125391 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254115.348698 1125391 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254115.348700 1125391 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:01:55.351844: 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(
2025-11-04 12:01:58,399	INFO worker.py:1927 -- Started a local Ray instance.
2025-11-04 12:01:59,081	INFO tune.py:253 -- Initializing Ray automatically. For cluster usage or custom Ray initialization, call `ray.init(...)` before `Tuner(...)`.
2025-11-04 12:01:59,149	INFO trial.py:182 -- Creating a new dirname dir_af39f_7c1e because trial dirname 'dir_af39f' already exists.
2025-11-04 12:01:59,152	INFO trial.py:182 -- Creating a new dirname dir_af39f_5f9e because trial dirname 'dir_af39f' already exists.
2025-11-04 12:01:59,154	INFO trial.py:182 -- Creating a new dirname dir_af39f_bb73 because trial dirname 'dir_af39f' already exists.
2025-11-04 12:01:59,157	INFO trial.py:182 -- Creating a new dirname dir_af39f_0ca2 because trial dirname 'dir_af39f' already exists.
2025-11-04 12:01:59,159	INFO trial.py:182 -- Creating a new dirname dir_af39f_e05b because trial dirname 'dir_af39f' already exists.
2025-11-04 12:01:59,162	INFO trial.py:182 -- Creating a new dirname dir_af39f_7c74 because trial dirname 'dir_af39f' already exists.
2025-11-04 12:01:59,164	INFO trial.py:182 -- Creating a new dirname dir_af39f_a49e because trial dirname 'dir_af39f' already exists.
2025-11-04 12:01:59,166	INFO trial.py:182 -- Creating a new dirname dir_af39f_dcac because trial dirname 'dir_af39f' already exists.
2025-11-04 12:01:59,169	INFO trial.py:182 -- Creating a new dirname dir_af39f_ca86 because trial dirname 'dir_af39f' already exists.
2025-11-04 12:01:59,171	INFO trial.py:182 -- Creating a new dirname dir_af39f_be10 because trial dirname 'dir_af39f' already exists.
2025-11-04 12:01:59,174	INFO trial.py:182 -- Creating a new dirname dir_af39f_c11b because trial dirname 'dir_af39f' already exists.
2025-11-04 12:01:59,176	INFO trial.py:182 -- Creating a new dirname dir_af39f_005b because trial dirname 'dir_af39f' already exists.
2025-11-04 12:01:59,180	INFO trial.py:182 -- Creating a new dirname dir_af39f_ce93 because trial dirname 'dir_af39f' already exists.
2025-11-04 12:01:59,183	INFO trial.py:182 -- Creating a new dirname dir_af39f_529b because trial dirname 'dir_af39f' already exists.
2025-11-04 12:01:59,186	INFO trial.py:182 -- Creating a new dirname dir_af39f_6eaf because trial dirname 'dir_af39f' already exists.
2025-11-04 12:01:59,189	INFO trial.py:182 -- Creating a new dirname dir_af39f_851c because trial dirname 'dir_af39f' already exists.
2025-11-04 12:01:59,196	INFO trial.py:182 -- Creating a new dirname dir_af39f_c40a because trial dirname 'dir_af39f' already exists.
2025-11-04 12:01:59,201	INFO trial.py:182 -- Creating a new dirname dir_af39f_e252 because trial dirname 'dir_af39f' already exists.
2025-11-04 12:01:59,207	INFO trial.py:182 -- Creating a new dirname dir_af39f_d842 because trial dirname 'dir_af39f' 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     ESANN_hyperparameters_tuning   │
├─────────────────────────────────────────────────────────────────┤
│ Search algorithm                 BasicVariantGenerator          │
│ Scheduler                        AsyncHyperBandScheduler        │
│ Number of trials                 20                             │
╰─────────────────────────────────────────────────────────────────╯

View detailed results here: /mnt/nvme1n2/git/uniovi-simur-wearablepermed-data/output/Paper_results/cases_dataset_PI/case_PI_ESANN_acc_gyr_superclasses_CPA_METs/ESANN_hyperparameters_tuning
To visualize your results with TensorBoard, run: `tensorboard --logdir /tmp/ray/session_2025-11-04_12-01-57_698887_1125391/artifacts/2025-11-04_12-01-59/ESANN_hyperparameters_tuning/driver_artifacts`

Trial status: 20 PENDING
Current time: 2025-11-04 12:01:59. Total running time: 0s
Logical resource usage: 0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status       N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     tasa_aprendizaje     epochs │
├───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_af39f    PENDING            2   rmsprop         tanh                                  128                 32                  5          0.000531671         89 │
│ trial_af39f    PENDING            3   adam            relu                                   32                 32                  5          8.9631e-05          60 │
│ trial_af39f    PENDING            2   adam            tanh                                  128                 32                  5          2.05278e-05        115 │
│ trial_af39f    PENDING            2   adam            tanh                                  128                 64                  5          0.000263082         78 │
│ trial_af39f    PENDING            3   rmsprop         tanh                                   32                 32                  3          0.00135267          51 │
│ trial_af39f    PENDING            3   adam            relu                                  128                 64                  3          0.000113647        124 │
│ trial_af39f    PENDING            3   adam            relu                                   32                 32                  5          0.000608101         70 │
│ trial_af39f    PENDING            3   adam            relu                                   32                 32                  5          2.34078e-05        139 │
│ trial_af39f    PENDING            3   adam            tanh                                   32                 64                  5          6.10182e-05         70 │
│ trial_af39f    PENDING            3   rmsprop         tanh                                   32                 64                  3          4.80349e-05         99 │
│ trial_af39f    PENDING            3   rmsprop         relu                                  128                 32                  5          4.00548e-05        132 │
│ trial_af39f    PENDING            2   rmsprop         tanh                                   32                 64                  3          0.00160542         137 │
│ trial_af39f    PENDING            4   adam            tanh                                   64                 64                  3          0.000170953         52 │
│ trial_af39f    PENDING            3   rmsprop         relu                                   64                128                  5          5.18891e-05        146 │
│ trial_af39f    PENDING            4   adam            tanh                                   64                 32                  3          2.56847e-05         93 │
│ trial_af39f    PENDING            2   rmsprop         relu                                   64                128                  3          0.00143439          82 │
│ trial_af39f    PENDING            3   rmsprop         relu                                   32                128                  5          0.000409376         53 │
│ trial_af39f    PENDING            3   rmsprop         tanh                                   32                 64                  3          3.42484e-05        134 │
│ trial_af39f    PENDING            2   rmsprop         relu                                   64                 32                  3          4.34693e-05        131 │
│ trial_af39f    PENDING            4   adam            relu                                   64                 32                  3          0.0028724           66 │
╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯

Trial trial_af39f started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_af39f config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            70 │
│ funcion_activacion              tanh │
│ numero_filtros                    64 │
│ optimizador                     adam │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00006 │
╰──────────────────────────────────────╯
Trial trial_af39f started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_af39f config             │
├──────────────────────────────────────┤
│ N_capas                            4 │
│ epochs                            52 │
│ funcion_activacion              tanh │
│ numero_filtros                    64 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  64 │
│ tasa_aprendizaje             0.00017 │
╰──────────────────────────────────────╯
Trial trial_af39f started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_af39f config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                           131 │
│ funcion_activacion              relu │
│ numero_filtros                    32 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  64 │
│ tasa_aprendizaje             0.00004 │
╰──────────────────────────────────────╯
Trial trial_af39f started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_af39f config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                           139 │
│ funcion_activacion              relu │
│ numero_filtros                    32 │
│ optimizador                     adam │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00002 │
╰──────────────────────────────────────╯
Trial trial_af39f started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_af39f config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            78 │
│ funcion_activacion              tanh │
│ numero_filtros                    64 │
│ optimizador                     adam │
│ tamanho_filtro                     5 │
│ tamanho_minilote                 128 │
│ tasa_aprendizaje             0.00026 │
╰──────────────────────────────────────╯
Trial trial_af39f started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_af39f config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                           124 │
│ funcion_activacion              relu │
│ numero_filtros                    64 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                 128 │
│ tasa_aprendizaje             0.00011 │
╰──────────────────────────────────────╯
Trial trial_af39f started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_af39f config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            51 │
│ funcion_activacion              tanh │
│ numero_filtros                    32 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00135 │
╰──────────────────────────────────────╯
Trial trial_af39f started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_af39f config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            89 │
│ funcion_activacion              tanh │
│ numero_filtros                    32 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     5 │
│ tamanho_minilote                 128 │
│ tasa_aprendizaje             0.00053 │
╰──────────────────────────────────────╯
Trial trial_af39f started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_af39f config             │
├──────────────────────────────────────┤
│ N_capas                            4 │
│ epochs                            66 │
│ funcion_activacion              relu │
│ numero_filtros                    32 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  64 │
│ tasa_aprendizaje             0.00287 │
╰──────────────────────────────────────╯
Trial trial_af39f started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_af39f config             │
├──────────────────────────────────────┤
│ N_capas                            4 │
│ epochs                            93 │
│ funcion_activacion              tanh │
│ numero_filtros                    32 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  64 │
│ tasa_aprendizaje             0.00003 │
╰──────────────────────────────────────╯
Trial trial_af39f started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_af39f config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                           146 │
│ funcion_activacion              relu │
│ numero_filtros                   128 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  64 │
│ tasa_aprendizaje             0.00005 │
╰──────────────────────────────────────╯
Trial trial_af39f started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_af39f config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            82 │
│ funcion_activacion              relu │
│ numero_filtros                   128 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  64 │
│ tasa_aprendizaje             0.00143 │
╰──────────────────────────────────────╯
Trial trial_af39f started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_af39f config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            60 │
│ funcion_activacion              relu │
│ numero_filtros                    32 │
│ optimizador                     adam │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00009 │
╰──────────────────────────────────────╯
Trial trial_af39f started with configuration:
[36m(train_cnn_ray_tune pid=1127023)[0m 2025-11-04 12:02:02.410465: 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=1127028)[0m 2025-11-04 12:02:02.387120: 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=1127028)[0m WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
[36m(train_cnn_ray_tune pid=1127028)[0m E0000 00:00:1762254122.411692 1128165 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=1127028)[0m E0000 00:00:1762254122.420073 1128165 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=1127023)[0m W0000 00:00:1762254122.481431 1128226 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=1127023)[0m W0000 00:00:1762254122.481476 1128226 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=1127023)[0m W0000 00:00:1762254122.481479 1128226 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=1127023)[0m W0000 00:00:1762254122.481481 1128226 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=1127023)[0m 2025-11-04 12:02:02.486994: 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=1127023)[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=1127028)[0m /home/simur/git/uniovi-simur-wearablepermed-ml/.venv/lib/python3.12/site-packages/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
[36m(train_cnn_ray_tune pid=1127028)[0m   warnings.warn(
[36m(train_cnn_ray_tune pid=1127028)[0m 2025-11-04 12:02:05.746606: 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=1127028)[0m 2025-11-04 12:02:05.746652: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:167] env: CUDA_VISIBLE_DEVICES=""
[36m(train_cnn_ray_tune pid=1127028)[0m 2025-11-04 12:02:05.746661: 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=1127028)[0m 2025-11-04 12:02:05.746667: 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=1127028)[0m 2025-11-04 12:02:05.746672: 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=1127028)[0m 2025-11-04 12:02:05.746676: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:190] hostname: simur-MS-7B94
[36m(train_cnn_ray_tune pid=1127028)[0m 2025-11-04 12:02:05.746905: 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=1127028)[0m 2025-11-04 12:02:05.746937: 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=1127028)[0m 2025-11-04 12:02:05.746942: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:291] kernel version seems to match DSO: 570.133.7
╭──────────────────────────────────────╮
│ Trial trial_af39f config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                           132 │
│ funcion_activacion              relu │
│ numero_filtros                    32 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     5 │
│ tamanho_minilote                 128 │
│ tasa_aprendizaje             0.00004 │
╰──────────────────────────────────────╯
Trial trial_af39f started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_af39f config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                           137 │
│ funcion_activacion              tanh │
│ numero_filtros                    64 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00161 │
╰──────────────────────────────────────╯
Trial trial_af39f started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_af39f config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            70 │
│ funcion_activacion              relu │
│ numero_filtros                    32 │
│ optimizador                     adam │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00061 │
╰──────────────────────────────────────╯
Trial trial_af39f started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_af39f config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                           115 │
│ funcion_activacion              tanh │
│ numero_filtros                    32 │
│ optimizador                     adam │
│ tamanho_filtro                     5 │
│ tamanho_minilote                 128 │
│ tasa_aprendizaje             0.00002 │
╰──────────────────────────────────────╯
Trial trial_af39f started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_af39f config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                           134 │
│ funcion_activacion              tanh │
│ numero_filtros                    64 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00003 │
╰──────────────────────────────────────╯
Trial trial_af39f started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_af39f config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            99 │
│ funcion_activacion              tanh │
│ numero_filtros                    64 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00005 │
╰──────────────────────────────────────╯
Trial trial_af39f started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_af39f config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            53 │
│ funcion_activacion              relu │
│ numero_filtros                   128 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00041 │
╰──────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1127028)[0m Model: "sequential"
[36m(train_cnn_ray_tune pid=1127028)[0m ┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
[36m(train_cnn_ray_tune pid=1127028)[0m ┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
[36m(train_cnn_ray_tune pid=1127028)[0m ┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
[36m(train_cnn_ray_tune pid=1127028)[0m │ conv1d (Conv1D)                 │ (None, 6, 64)          │        80,064 │
[36m(train_cnn_ray_tune pid=1127028)[0m ├─────────────────────────────────┼────────────────────────┼───────────────┤
[36m(train_cnn_ray_tune pid=1127028)[0m │ layer_normalization             │ (None, 6, 64)          │           128 │
[36m(train_cnn_ray_tune pid=1127028)[0m │ (LayerNormalization)            │                        │               │
[36m(train_cnn_ray_tune pid=1127028)[0m ├─────────────────────────────────┼────────────────────────┼───────────────┤
[36m(train_cnn_ray_tune pid=1127028)[0m │ dropout (Dropout)               │ (None, 6, 64)          │             0 │
[36m(train_cnn_ray_tune pid=1127028)[0m ├─────────────────────────────────┼────────────────────────┼───────────────┤
[36m(train_cnn_ray_tune pid=1127028)[0m │ conv1d_1 (Conv1D)               │ (None, 6, 64)          │        20,544 │
[36m(train_cnn_ray_tune pid=1127028)[0m ├─────────────────────────────────┼────────────────────────┼───────────────┤
[36m(train_cnn_ray_tune pid=1127028)[0m │ layer_normalization_1           │ (None, 6, 64)          │           128 │
[36m(train_cnn_ray_tune pid=1127028)[0m │ (LayerNormalization)            │                        │               │
[36m(train_cnn_ray_tune pid=1127028)[0m ├─────────────────────────────────┼────────────────────────┼───────────────┤
[36m(train_cnn_ray_tune pid=1127028)[0m │ dropout_1 (Dropout)             │ (None, 6, 64)          │             0 │
[36m(train_cnn_ray_tune pid=1127028)[0m ├─────────────────────────────────┼────────────────────────┼───────────────┤
[36m(train_cnn_ray_tune pid=1127028)[0m │ conv1d_2 (Conv1D)               │ (None, 6, 64)          │        20,544 │
[36m(train_cnn_ray_tune pid=1127028)[0m ├─────────────────────────────────┼────────────────────────┼───────────────┤
[36m(train_cnn_ray_tune pid=1127028)[0m │ layer_normalization_2           │ (None, 6, 64)          │           128 │
[36m(train_cnn_ray_tune pid=1127028)[0m │ (LayerNormalization)            │                        │               │
[36m(train_cnn_ray_tune pid=1127028)[0m ├─────────────────────────────────┼────────────────────────┼───────────────┤
[36m(train_cnn_ray_tune pid=1127028)[0m │ dropout_2 (Dropout)             │ (None, 6, 64)          │             0 │
[36m(train_cnn_ray_tune pid=1127028)[0m ├─────────────────────────────────┼────────────────────────┼───────────────┤
[36m(train_cnn_ray_tune pid=1127028)[0m │ global_average_pooling1d        │ (None, 64)             │             0 │
[36m(train_cnn_ray_tune pid=1127028)[0m │ (GlobalAveragePooling1D)        │                        │               │
[36m(train_cnn_ray_tune pid=1127028)[0m ├─────────────────────────────────┼────────────────────────┼───────────────┤
[36m(train_cnn_ray_tune pid=1127028)[0m │ dropout_3 (Dropout)             │ (None, 64)             │             0 │
[36m(train_cnn_ray_tune pid=1127028)[0m ├─────────────────────────────────┼────────────────────────┼───────────────┤
[36m(train_cnn_ray_tune pid=1127028)[0m │ dense (Dense)                   │ (None, 4)              │           260 │
[36m(train_cnn_ray_tune pid=1127028)[0m └─────────────────────────────────┴────────────────────────┴───────────────┘
[36m(train_cnn_ray_tune pid=1127028)[0m  Total params: 121,796 (475.77 KB)
[36m(train_cnn_ray_tune pid=1127028)[0m  Trainable params: 121,796 (475.77 KB)
[36m(train_cnn_ray_tune pid=1127028)[0m  Non-trainable params: 0 (0.00 B)
[36m(train_cnn_ray_tune pid=1127028)[0m Epoch 1/70
[36m(train_cnn_ray_tune pid=1127012)[0m  Total params: 325,508 (1.24 MB)
[36m(train_cnn_ray_tune pid=1127012)[0m  Trainable params: 325,508 (1.24 MB)
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:44[0m 2s/step - accuracy: 0.2266 - loss: 2.1706
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m 3/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 26ms/step - accuracy: 0.2517 - loss: 2.0877
[1m 6/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 23ms/step - accuracy: 0.2637 - loss: 2.0673
[36m(train_cnn_ray_tune pid=1127021)[0m 
[1m  4/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 24ms/step - accuracy: 0.3135 - loss: 2.1345
[1m  7/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 23ms/step - accuracy: 0.3284 - loss: 2.0757
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10:48[0m 2s/step - accuracy: 0.3125 - loss: 1.8191
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 18ms/step - accuracy: 0.3086 - loss: 1.8612 
[1m  8/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 16ms/step - accuracy: 0.3052 - loss: 1.9217
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m 9/78[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 21ms/step - accuracy: 0.2719 - loss: 2.0475
[1m12/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 20ms/step - accuracy: 0.2783 - loss: 2.0319
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m16/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 19ms/step - accuracy: 0.2830 - loss: 2.0193
[36m(train_cnn_ray_tune pid=1127021)[0m 
[1m 16/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.3525 - loss: 1.9724
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m20/78[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 19ms/step - accuracy: 0.2858 - loss: 2.0085
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m23/78[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 19ms/step - accuracy: 0.2881 - loss: 1.9991
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 26ms/step - accuracy: 0.1840 - loss: 2.4022 
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 23ms/step - accuracy: 0.1992 - loss: 2.3518
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m27/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 18ms/step - accuracy: 0.2909 - loss: 1.9846
[1m30/78[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 18ms/step - accuracy: 0.2932 - loss: 1.9742
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m34/78[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 18ms/step - accuracy: 0.2962 - loss: 1.9616
[1m37/78[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 18ms/step - accuracy: 0.2986 - loss: 1.9529
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m40/78[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 18ms/step - accuracy: 0.3012 - loss: 1.9443
[1m43/78[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 18ms/step - accuracy: 0.3036 - loss: 1.9360
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3:35[0m 3s/step - accuracy: 0.1641 - loss: 2.4143
[1m 4/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 19ms/step - accuracy: 0.2090 - loss: 2.3466
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m45/78[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 18ms/step - accuracy: 0.3052 - loss: 1.9308
[1m48/78[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 19ms/step - accuracy: 0.3075 - loss: 1.9237
[36m(train_cnn_ray_tune pid=1127030)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.3314 - loss: 2.2079 
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m  7/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 37ms/step - accuracy: 0.2898 - loss: 2.1853
[1m  9/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 35ms/step - accuracy: 0.2874 - loss: 2.1779
[36m(train_cnn_ray_tune pid=1127030)[0m Model: "sequential"[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=1127030)[0m ┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1127030)[0m ┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1127030)[0m ┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1127030)[0m │ global_average_pooling1d        │ (None, 64)             │             0 │[32m [repeated 108x across cluster][0m
[36m(train_cnn_ray_tune pid=1127030)[0m ├─────────────────────────────────┼────────────────────────┼───────────────┤[32m [repeated 200x across cluster][0m
[36m(train_cnn_ray_tune pid=1127030)[0m │ layer_normalization             │ (None, 6, 64)          │           128 │[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1127030)[0m │ (LayerNormalization)            │                        │               │[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=1127030)[0m │ dropout (Dropout)               │ (None, 6, 64)          │             0 │[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1127030)[0m │ dropout_3 (Dropout)             │ (None, 64)             │             0 │[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=1127030)[0m │ (GlobalAveragePooling1D)        │                        │               │[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1127030)[0m │ dense (Dense)                   │ (None, 4)              │           260 │[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1127030)[0m └─────────────────────────────────┴────────────────────────┴───────────────┘[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1127030)[0m  Total params: 73,412 (286.77 KB)[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=1127030)[0m  Trainable params: 73,412 (286.77 KB)[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=1127030)[0m  Non-trainable params: 0 (0.00 B)[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1127019)[0m Epoch 1/99[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 24/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 37ms/step - accuracy: 0.2965 - loss: 2.0923
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 37ms/step - accuracy: 0.2977 - loss: 2.0841
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.2992 - loss: 2.0760
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.3003 - loss: 2.0700
[36m(train_cnn_ray_tune pid=1127031)[0m  Total params: 325,508 (1.24 MB)
[36m(train_cnn_ray_tune pid=1127031)[0m  Trainable params: 325,508 (1.24 MB)
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m5s[0m 33ms/step - accuracy: 0.3249 - loss: 1.8691 - val_accuracy: 0.5183 - val_loss: 1.0245
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m6s[0m 27ms/step - accuracy: 0.2665 - loss: 2.0803 - val_accuracy: 0.4515 - val_loss: 1.2537
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  4/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.3096 - loss: 1.9248  
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m 3/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 38ms/step - accuracy: 0.4549 - loss: 1.4964 
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 113ms/step - accuracy: 0.5000 - loss: 1.3691[32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 5/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 36ms/step - accuracy: 0.2689 - loss: 2.0031
[1m 7/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 33ms/step - accuracy: 0.2725 - loss: 1.9865[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=1127019)[0m 
[1m148/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m4s[0m 28ms/step - accuracy: 0.2570 - loss: 2.0689
[1m150/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m4s[0m 28ms/step - accuracy: 0.2569 - loss: 2.0689[32m [repeated 288x across cluster][0m
[36m(train_cnn_ray_tune pid=1127019)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15:40[0m 3s/step - accuracy: 0.2812 - loss: 2.0675
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.2344 - loss: 2.1737 
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.2539 - loss: 2.1195
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m68/78[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 48ms/step - accuracy: 0.2633 - loss: 2.1088[32m [repeated 98x across cluster][0m
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m5s[0m 27ms/step - accuracy: 0.2848 - loss: 1.9604[32m [repeated 217x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 36ms/step - accuracy: 0.2326 - loss: 2.1303 
[1m  5/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 38ms/step - accuracy: 0.2341 - loss: 2.1615[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m 74/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m3s[0m 41ms/step - accuracy: 0.2578 - loss: 2.1193
[1m 75/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m3s[0m 41ms/step - accuracy: 0.2579 - loss: 2.1186
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m3s[0m 42ms/step - accuracy: 0.2581 - loss: 2.1180
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 86ms/step - accuracy: 0.3828 - loss: 1.5469
[1m 3/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 29ms/step - accuracy: 0.3911 - loss: 1.5563[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 33ms/step - accuracy: 0.2630 - loss: 1.9779 [32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 33ms/step - accuracy: 0.2897 - loss: 2.0728
[1m  8/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2867 - loss: 2.0630 [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m Epoch 3/115[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 61ms/step - accuracy: 0.2645 - loss: 2.0970 - val_accuracy: 0.4761 - val_loss: 1.1696[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m4s[0m 26ms/step - accuracy: 0.2952 - loss: 1.9348 - val_accuracy: 0.4695 - val_loss: 1.1853[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m 3/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 44ms/step - accuracy: 0.2930 - loss: 1.9615 
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 84ms/step - accuracy: 0.4688 - loss: 1.2212[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m45/78[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 25ms/step - accuracy: 0.2975 - loss: 1.9595
[1m47/78[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 25ms/step - accuracy: 0.2977 - loss: 1.9595[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 94/155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 19ms/step - accuracy: 0.3122 - loss: 1.9161
[1m 96/155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 19ms/step - accuracy: 0.3121 - loss: 1.9157[32m [repeated 342x across cluster][0m
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m 5/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 30ms/step - accuracy: 0.4767 - loss: 1.2364[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=1127021)[0m 
[1m145/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 32ms/step - accuracy: 0.6168 - loss: 0.8845[32m [repeated 224x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m  2/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 63ms/step - accuracy: 0.3672 - loss: 1.5557  
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 60ms/step - accuracy: 0.3594 - loss: 1.5902
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 33ms/step - accuracy: 0.2778 - loss: 1.9565 
[1m  5/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 31ms/step - accuracy: 0.2764 - loss: 1.9745[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m127/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m3s[0m 19ms/step - accuracy: 0.4976 - loss: 1.1476
[1m131/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m3s[0m 19ms/step - accuracy: 0.4980 - loss: 1.1469
[1m134/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m3s[0m 19ms/step - accuracy: 0.4983 - loss: 1.1464[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 97ms/step - accuracy: 0.2188 - loss: 2.1429
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 30ms/step - accuracy: 0.2552 - loss: 2.0621 [32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1127019)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 35ms/step - accuracy: 0.2500 - loss: 2.3122
[36m(train_cnn_ray_tune pid=1127021)[0m Epoch 3/82[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m 3/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 29ms/step - accuracy: 0.3802 - loss: 1.6059 
[1m 6/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 28ms/step - accuracy: 0.3858 - loss: 1.5686
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 28ms/step - accuracy: 0.4751 - loss: 1.2594 - val_accuracy: 0.5990 - val_loss: 0.8905[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m14s[0m 33ms/step - accuracy: 0.2690 - loss: 1.9866 - val_accuracy: 0.4754 - val_loss: 1.1353[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 37ms/step - accuracy: 0.3983 - loss: 1.5355
[1m  7/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.4065 - loss: 1.5072
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m  9/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.4191 - loss: 1.4785
[1m 11/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 35ms/step - accuracy: 0.4273 - loss: 1.4573
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 81ms/step - accuracy: 0.5156 - loss: 1.0502[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m19/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 25ms/step - accuracy: 0.5145 - loss: 1.1359
[1m21/78[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 25ms/step - accuracy: 0.5142 - loss: 1.1376[32m [repeated 100x across cluster][0m
[36m(train_cnn_ray_tune pid=1127019)[0m 
[1m159/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m3s[0m 24ms/step - accuracy: 0.2945 - loss: 1.9118
[1m162/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m3s[0m 24ms/step - accuracy: 0.2946 - loss: 1.9117[32m [repeated 315x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 15/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.4370 - loss: 1.4297
[1m 17/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.4401 - loss: 1.4194
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m45/78[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 34ms/step - accuracy: 0.3492 - loss: 1.7219[32m [repeated 98x across cluster][0m
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m116/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m1s[0m 36ms/step - accuracy: 0.3144 - loss: 1.8731[32m [repeated 198x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 21/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 38ms/step - accuracy: 0.4441 - loss: 1.4079
[1m 23/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 38ms/step - accuracy: 0.4447 - loss: 1.4053
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 37ms/step - accuracy: 0.5356 - loss: 1.1298 
[1m  5/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.5214 - loss: 1.1362[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 25/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 38ms/step - accuracy: 0.4457 - loss: 1.4034
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 38ms/step - accuracy: 0.4473 - loss: 1.3999
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 37ms/step - accuracy: 0.4489 - loss: 1.3964
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 37ms/step - accuracy: 0.4501 - loss: 1.3927
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m130/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.2509 - loss: 1.9661
[1m132/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.2509 - loss: 1.9659
[1m134/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.2510 - loss: 1.9658[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 33/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 37ms/step - accuracy: 0.4514 - loss: 1.3894
[1m 35/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 37ms/step - accuracy: 0.4521 - loss: 1.3879
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 71ms/step - accuracy: 0.2656 - loss: 1.7619
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 26ms/step - accuracy: 0.2917 - loss: 1.6982 [32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 39/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 37ms/step - accuracy: 0.4537 - loss: 1.3852
[1m 41/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 38ms/step - accuracy: 0.4543 - loss: 1.3846
[36m(train_cnn_ray_tune pid=1127021)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 40ms/step - accuracy: 0.6441 - loss: 0.7430 [32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m Epoch 7/115[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m 3/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 28ms/step - accuracy: 0.4848 - loss: 1.1919 
[1m 5/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 27ms/step - accuracy: 0.4846 - loss: 1.1897
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 32ms/step - accuracy: 0.5084 - loss: 1.1529 - val_accuracy: 0.6103 - val_loss: 0.8683[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m  2/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 54ms/step - accuracy: 0.2852 - loss: 1.7743  
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m4s[0m 24ms/step - accuracy: 0.3366 - loss: 1.7524 - val_accuracy: 0.5081 - val_loss: 1.0936[32m [repeated 9x across cluster][0m

Trial status: 20 RUNNING
Current time: 2025-11-04 12:02:29. 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     tasa_aprendizaje     epochs │
├───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_af39f    RUNNING            2   rmsprop         tanh                                  128                 32                  5          0.000531671         89 │
│ trial_af39f    RUNNING            3   adam            relu                                   32                 32                  5          8.9631e-05          60 │
│ trial_af39f    RUNNING            2   adam            tanh                                  128                 32                  5          2.05278e-05        115 │
│ trial_af39f    RUNNING            2   adam            tanh                                  128                 64                  5          0.000263082         78 │
│ trial_af39f    RUNNING            3   rmsprop         tanh                                   32                 32                  3          0.00135267          51 │
│ trial_af39f    RUNNING            3   adam            relu                                  128                 64                  3          0.000113647        124 │
│ trial_af39f    RUNNING            3   adam            relu                                   32                 32                  5          0.000608101         70 │
│ trial_af39f    RUNNING            3   adam            relu                                   32                 32                  5          2.34078e-05        139 │
│ trial_af39f    RUNNING            3   adam            tanh                                   32                 64                  5          6.10182e-05         70 │
│ trial_af39f    RUNNING            3   rmsprop         tanh                                   32                 64                  3          4.80349e-05         99 │
│ trial_af39f    RUNNING            3   rmsprop         relu                                  128                 32                  5          4.00548e-05        132 │
│ trial_af39f    RUNNING            2   rmsprop         tanh                                   32                 64                  3          0.00160542         137 │
│ trial_af39f    RUNNING            4   adam            tanh                                   64                 64                  3          0.000170953         52 │
│ trial_af39f    RUNNING            3   rmsprop         relu                                   64                128                  5          5.18891e-05        146 │
│ trial_af39f    RUNNING            4   adam            tanh                                   64                 32                  3          2.56847e-05         93 │
│ trial_af39f    RUNNING            2   rmsprop         relu                                   64                128                  3          0.00143439          82 │
│ trial_af39f    RUNNING            3   rmsprop         relu                                   32                128                  5          0.000409376         53 │
│ trial_af39f    RUNNING            3   rmsprop         tanh                                   32                 64                  3          3.42484e-05        134 │
│ trial_af39f    RUNNING            2   rmsprop         relu                                   64                 32                  3          4.34693e-05        131 │
│ trial_af39f    RUNNING            4   adam            relu                                   64                 32                  3          0.0028724           66 │
╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 75ms/step - accuracy: 0.3125 - loss: 1.6644[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 17ms/step - accuracy: 0.2703 - loss: 1.7604 
[1m  7/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 20ms/step - accuracy: 0.2651 - loss: 1.7971
[1m  9/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 23ms/step - accuracy: 0.2594 - loss: 1.8313
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m73/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 24ms/step - accuracy: 0.3407 - loss: 1.8261
[1m75/78[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 24ms/step - accuracy: 0.3407 - loss: 1.8267[32m [repeated 110x across cluster][0m
[36m(train_cnn_ray_tune pid=1127019)[0m 
[1m 11/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.3027 - loss: 1.8747
[1m 13/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.3065 - loss: 1.8668[32m [repeated 330x across cluster][0m
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m39/78[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 21ms/step - accuracy: 0.5384 - loss: 1.0703[32m [repeated 94x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m  6/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 28ms/step - accuracy: 0.3888 - loss: 1.2173[32m [repeated 199x across cluster][0m
[36m(train_cnn_ray_tune pid=1127019)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.2643 - loss: 1.9391 
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.2823 - loss: 1.9063[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m 14/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 31ms/step - accuracy: 0.4280 - loss: 1.1779
[1m 16/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 31ms/step - accuracy: 0.4312 - loss: 1.1746
[1m 18/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 30ms/step - accuracy: 0.4339 - loss: 1.1723[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 27ms/step - accuracy: 0.3268 - loss: 1.7356  
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 27ms/step - accuracy: 0.3283 - loss: 1.7181
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 82ms/step - accuracy: 0.3750 - loss: 1.7377
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.3559 - loss: 1.7673 [32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 31ms/step - accuracy: 0.3785 - loss: 1.2434 
[36m(train_cnn_ray_tune pid=1127018)[0m Epoch 10/89[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 27ms/step - accuracy: 0.5330 - loss: 1.0774 - val_accuracy: 0.6138 - val_loss: 0.8505[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 3/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 35ms/step - accuracy: 0.3047 - loss: 1.8245 
[1m 6/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 26ms/step - accuracy: 0.3190 - loss: 1.8035
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m4s[0m 23ms/step - accuracy: 0.3413 - loss: 1.7620 - val_accuracy: 0.5105 - val_loss: 1.0767[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 30ms/step - accuracy: 0.2908 - loss: 1.6655 
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 80ms/step - accuracy: 0.6250 - loss: 0.9267[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m22/78[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 34ms/step - accuracy: 0.4841 - loss: 1.2277
[1m25/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 33ms/step - accuracy: 0.4842 - loss: 1.2281[32m [repeated 97x across cluster][0m
[36m(train_cnn_ray_tune pid=1127019)[0m 
[1m216/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m2s[0m 25ms/step - accuracy: 0.3320 - loss: 1.7894
[1m218/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m2s[0m 25ms/step - accuracy: 0.3320 - loss: 1.7893[32m [repeated 391x across cluster][0m
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m28/78[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 27ms/step - accuracy: 0.5636 - loss: 1.0232[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m199/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m2s[0m 24ms/step - accuracy: 0.3339 - loss: 1.6436[32m [repeated 265x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 29ms/step - accuracy: 0.3655 - loss: 1.6486 
[1m  5/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 29ms/step - accuracy: 0.3690 - loss: 1.6495[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m128/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 32ms/step - accuracy: 0.4642 - loss: 1.1390
[1m130/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 31ms/step - accuracy: 0.4644 - loss: 1.1386
[1m132/155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 31ms/step - accuracy: 0.4646 - loss: 1.1383[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 58ms/step - accuracy: 0.3750 - loss: 1.6409
[1m 4/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 21ms/step - accuracy: 0.3986 - loss: 1.6416[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m Epoch 8/131[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 43ms/step - accuracy: 0.6198 - loss: 1.0867
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 40ms/step - accuracy: 0.5956 - loss: 1.1074
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 38ms/step - accuracy: 0.4892 - loss: 1.2271 - val_accuracy: 0.5934 - val_loss: 0.8787[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 13/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.5751 - loss: 1.1026
[1m 15/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.5727 - loss: 1.0992
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 17/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.5722 - loss: 1.0943
[1m 19/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.5727 - loss: 1.0894
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 21/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 35ms/step - accuracy: 0.5735 - loss: 1.0853
[1m 23/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.5733 - loss: 1.0833 
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 71ms/step - accuracy: 0.3125 - loss: 1.7953
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 27ms/step - accuracy: 0.2934 - loss: 1.7737 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 27ms/step - accuracy: 0.2829 - loss: 1.8131
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 27ms/step - accuracy: 0.3375 - loss: 1.6357 - val_accuracy: 0.4940 - val_loss: 1.0851[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.4201 - loss: 1.4610 [32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 97ms/step - accuracy: 0.5625 - loss: 0.9708[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m30/78[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 31ms/step - accuracy: 0.3247 - loss: 1.7249
[1m32/78[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 31ms/step - accuracy: 0.3258 - loss: 1.7231[32m [repeated 91x across cluster][0m
[36m(train_cnn_ray_tune pid=1127019)[0m 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m6s[0m 25ms/step - accuracy: 0.3404 - loss: 1.7646
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m6s[0m 25ms/step - accuracy: 0.3405 - loss: 1.7642[32m [repeated 342x across cluster][0m
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m40/78[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 23ms/step - accuracy: 0.5652 - loss: 1.0218[32m [repeated 108x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m6s[0m 24ms/step - accuracy: 0.3602 - loss: 1.5636[32m [repeated 232x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  4/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 19ms/step - accuracy: 0.3662 - loss: 1.5192 
[1m  7/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step - accuracy: 0.3504 - loss: 1.5537[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 71/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m6s[0m 26ms/step - accuracy: 0.2579 - loss: 1.8934
[1m 73/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m6s[0m 26ms/step - accuracy: 0.2576 - loss: 1.8945
[1m 75/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m6s[0m 26ms/step - accuracy: 0.2574 - loss: 1.8955[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 82ms/step - accuracy: 0.3203 - loss: 1.8095
[1m 3/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 25ms/step - accuracy: 0.3142 - loss: 1.8520[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 45ms/step - accuracy: 0.4062 - loss: 1.5285  
[36m(train_cnn_ray_tune pid=1127026)[0m Epoch 5/93[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 3/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 37ms/step - accuracy: 0.3069 - loss: 1.7599 
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 37ms/step - accuracy: 0.3340 - loss: 1.7364
[1m  7/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 33ms/step - accuracy: 0.3353 - loss: 1.7443
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 38ms/step - accuracy: 0.3358 - loss: 1.7086 - val_accuracy: 0.4779 - val_loss: 1.0913[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m4s[0m 23ms/step - accuracy: 0.3489 - loss: 1.6438 - val_accuracy: 0.5316 - val_loss: 1.0181[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 86ms/step - accuracy: 0.5938 - loss: 1.0870[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m51/78[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 35ms/step - accuracy: 0.5149 - loss: 1.1621
[1m53/78[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 35ms/step - accuracy: 0.5150 - loss: 1.1616[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=1127019)[0m 
[1m254/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 26ms/step - accuracy: 0.3468 - loss: 1.7490
[1m256/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 26ms/step - accuracy: 0.3469 - loss: 1.7489[32m [repeated 371x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m56/78[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 38ms/step - accuracy: 0.4238 - loss: 1.4699[32m [repeated 132x across cluster][0m
[36m(train_cnn_ray_tune pid=1127030)[0m 
[1m262/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 25ms/step - accuracy: 0.3201 - loss: 1.9195[32m [repeated 283x across cluster][0m
[36m(train_cnn_ray_tune pid=1127021)[0m 
[1m  4/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 29ms/step - accuracy: 0.7598 - loss: 0.5881 
[1m  6/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 28ms/step - accuracy: 0.7505 - loss: 0.6042[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m282/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 24ms/step - accuracy: 0.2629 - loss: 1.8850
[1m285/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 24ms/step - accuracy: 0.2630 - loss: 1.8848
[1m288/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 24ms/step - accuracy: 0.2631 - loss: 1.8845[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 100ms/step - accuracy: 0.3750 - loss: 1.6709
[1m 3/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 38ms/step - accuracy: 0.3477 - loss: 1.7298 [32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 39ms/step - accuracy: 0.3602 - loss: 1.8176  
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.5295 - loss: 1.0573 
[36m(train_cnn_ray_tune pid=1127024)[0m Epoch 7/66[32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 30ms/step - accuracy: 0.2370 - loss: 1.9975  
[1m  5/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 29ms/step - accuracy: 0.2402 - loss: 1.9971
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m 3/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 37ms/step - accuracy: 0.5204 - loss: 1.1527 
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 29ms/step - accuracy: 0.3715 - loss: 1.7403 - val_accuracy: 0.4853 - val_loss: 1.0863[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 91ms/step - accuracy: 0.2578 - loss: 1.8607
[1m 3/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 27ms/step - accuracy: 0.3116 - loss: 1.7208
[1m 4/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 35ms/step - accuracy: 0.3236 - loss: 1.6945
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 44ms/step - accuracy: 0.3701 - loss: 1.5840 - val_accuracy: 0.4831 - val_loss: 1.1967[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 80ms/step - accuracy: 0.3906 - loss: 1.5833[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m 3/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 35ms/step - accuracy: 0.3915 - loss: 1.4608 
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m61/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 32ms/step - accuracy: 0.3544 - loss: 1.6073
[1m63/78[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 32ms/step - accuracy: 0.3545 - loss: 1.6075[32m [repeated 107x across cluster][0m
[36m(train_cnn_ray_tune pid=1127019)[0m 
[1m 50/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m6s[0m 26ms/step - accuracy: 0.3223 - loss: 1.7644
[1m 52/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m6s[0m 26ms/step - accuracy: 0.3230 - loss: 1.7636[32m [repeated 358x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m24/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 32ms/step - accuracy: 0.5152 - loss: 1.1228[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=1127019)[0m 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m6s[0m 26ms/step - accuracy: 0.3252 - loss: 1.7606[32m [repeated 210x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 53ms/step - accuracy: 0.6250 - loss: 0.8755
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 45ms/step - accuracy: 0.6197 - loss: 0.8883
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m  2/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 52ms/step - accuracy: 0.4414 - loss: 1.3282 
[1m  4/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 42ms/step - accuracy: 0.4225 - loss: 1.3572[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m 98/155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 29ms/step - accuracy: 0.2756 - loss: 1.9121
[1m100/155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 29ms/step - accuracy: 0.2759 - loss: 1.9115
[1m102/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m1s[0m 29ms/step - accuracy: 0.2762 - loss: 1.9109
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 12/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 44ms/step - accuracy: 0.6157 - loss: 0.8924
[1m 14/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 42ms/step - accuracy: 0.6177 - loss: 0.8890
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 78ms/step - accuracy: 0.4062 - loss: 1.5860
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.4036 - loss: 1.6597 [32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 22/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 39ms/step - accuracy: 0.6209 - loss: 0.8893
[1m 24/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 38ms/step - accuracy: 0.6214 - loss: 0.8889
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 26/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 39ms/step - accuracy: 0.6214 - loss: 0.8896
[1m 28/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 39ms/step - accuracy: 0.6210 - loss: 0.8902
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 36/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 37ms/step - accuracy: 0.6186 - loss: 0.8955[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 40/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 37ms/step - accuracy: 0.6173 - loss: 0.8980
[1m 42/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.6166 - loss: 0.8991 
[36m(train_cnn_ray_tune pid=1127029)[0m Epoch 12/131[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m  2/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 54ms/step - accuracy: 0.4727 - loss: 1.1631  
[1m  5/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 30ms/step - accuracy: 0.4866 - loss: 1.1054
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 36ms/step - accuracy: 0.5236 - loss: 1.1128 - val_accuracy: 0.6067 - val_loss: 0.8419[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127019)[0m 
[1m164/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m3s[0m 26ms/step - accuracy: 0.3395 - loss: 1.7393
[1m166/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m3s[0m 26ms/step - accuracy: 0.3397 - loss: 1.7389
[1m168/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m3s[0m 26ms/step - accuracy: 0.3400 - loss: 1.7386
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m 3/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 42ms/step - accuracy: 0.4314 - loss: 1.3047 
[36m(train_cnn_ray_tune pid=1127021)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m6s[0m 36ms/step - accuracy: 0.7321 - loss: 0.6149 - val_accuracy: 0.7356 - val_loss: 0.5820[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 62ms/step - accuracy: 0.5938 - loss: 1.0898[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m68/78[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 23ms/step - accuracy: 0.5927 - loss: 0.9356
[1m71/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 23ms/step - accuracy: 0.5924 - loss: 0.9363[32m [repeated 105x across cluster][0m
[36m(train_cnn_ray_tune pid=1127019)[0m 
[1m249/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 26ms/step - accuracy: 0.3466 - loss: 1.7273
[1m252/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 26ms/step - accuracy: 0.3468 - loss: 1.7270[32m [repeated 368x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m35/78[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 38ms/step - accuracy: 0.4406 - loss: 1.3482[32m [repeated 97x across cluster][0m
[36m(train_cnn_ray_tune pid=1127030)[0m 
[1m295/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 26ms/step - accuracy: 0.3402 - loss: 1.8161[32m [repeated 230x across cluster][0m
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 28ms/step - accuracy: 0.2665 - loss: 2.0152 
[1m  5/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 33ms/step - accuracy: 0.2743 - loss: 1.9844[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 77ms/step - accuracy: 0.3438 - loss: 1.8537
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 18ms/step - accuracy: 0.2858 - loss: 1.8252 [32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 29ms/step - accuracy: 0.5312 - loss: 1.0360 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m Epoch 20/115[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m 4/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 21ms/step - accuracy: 0.3652 - loss: 1.7041 
[1m 8/78[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 19ms/step - accuracy: 0.3687 - loss: 1.7018
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 45ms/step - accuracy: 0.4462 - loss: 1.2896  
[1m  4/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 48ms/step - accuracy: 0.4450 - loss: 1.2910
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m4s[0m 45ms/step - accuracy: 0.4417 - loss: 1.3535 - val_accuracy: 0.5565 - val_loss: 0.9444[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m134/155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 31ms/step - accuracy: 0.5124 - loss: 1.0459
[1m136/155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 31ms/step - accuracy: 0.5126 - loss: 1.0457
[1m138/155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 31ms/step - accuracy: 0.5128 - loss: 1.0454[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 35ms/step - accuracy: 0.4792 - loss: 1.3061  
[1m  5/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 39ms/step - accuracy: 0.4766 - loss: 1.3480
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 23ms/step - accuracy: 0.5994 - loss: 0.9151 - val_accuracy: 0.6440 - val_loss: 0.7054[32m [repeated 14x across cluster][0m
Trial status: 20 RUNNING
Current time: 2025-11-04 12:02:59. 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     tasa_aprendizaje     epochs │
├───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_af39f    RUNNING            2   rmsprop         tanh                                  128                 32                  5          0.000531671         89 │
│ trial_af39f    RUNNING            3   adam            relu                                   32                 32                  5          8.9631e-05          60 │
│ trial_af39f    RUNNING            2   adam            tanh                                  128                 32                  5          2.05278e-05        115 │
│ trial_af39f    RUNNING            2   adam            tanh                                  128                 64                  5          0.000263082         78 │
│ trial_af39f    RUNNING            3   rmsprop         tanh                                   32                 32                  3          0.00135267          51 │
│ trial_af39f    RUNNING            3   adam            relu                                  128                 64                  3          0.000113647        124 │
│ trial_af39f    RUNNING            3   adam            relu                                   32                 32                  5          0.000608101         70 │
│ trial_af39f    RUNNING            3   adam            relu                                   32                 32                  5          2.34078e-05        139 │
│ trial_af39f    RUNNING            3   adam            tanh                                   32                 64                  5          6.10182e-05         70 │
│ trial_af39f    RUNNING            3   rmsprop         tanh                                   32                 64                  3          4.80349e-05         99 │
│ trial_af39f    RUNNING            3   rmsprop         relu                                  128                 32                  5          4.00548e-05        132 │
│ trial_af39f    RUNNING            2   rmsprop         tanh                                   32                 64                  3          0.00160542         137 │
│ trial_af39f    RUNNING            4   adam            tanh                                   64                 64                  3          0.000170953         52 │
│ trial_af39f    RUNNING            3   rmsprop         relu                                   64                128                  5          5.18891e-05        146 │
│ trial_af39f    RUNNING            4   adam            tanh                                   64                 32                  3          2.56847e-05         93 │
│ trial_af39f    RUNNING            2   rmsprop         relu                                   64                128                  3          0.00143439          82 │
│ trial_af39f    RUNNING            3   rmsprop         relu                                   32                128                  5          0.000409376         53 │
│ trial_af39f    RUNNING            3   rmsprop         tanh                                   32                 64                  3          3.42484e-05        134 │
│ trial_af39f    RUNNING            2   rmsprop         relu                                   64                 32                  3          4.34693e-05        131 │
│ trial_af39f    RUNNING            4   adam            relu                                   64                 32                  3          0.0028724           66 │
╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 82ms/step - accuracy: 0.4297 - loss: 1.4272[32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m48/78[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 37ms/step - accuracy: 0.5496 - loss: 1.0612
[1m50/78[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 37ms/step - accuracy: 0.5497 - loss: 1.0614[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=1127019)[0m 
[1m 81/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m5s[0m 24ms/step - accuracy: 0.3828 - loss: 1.6671
[1m 83/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m5s[0m 24ms/step - accuracy: 0.3824 - loss: 1.6670[32m [repeated 351x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 9/78[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 36ms/step - accuracy: 0.3857 - loss: 1.4897[32m [repeated 112x across cluster][0m
[36m(train_cnn_ray_tune pid=1127021)[0m 
[1m 46/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m3s[0m 33ms/step - accuracy: 0.7538 - loss: 0.5785[32m [repeated 233x across cluster][0m
[36m(train_cnn_ray_tune pid=1127023)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.5938 - loss: 0.9442 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.5938 - loss: 0.9278[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 65ms/step - accuracy: 0.6250 - loss: 0.8350
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.6204 - loss: 0.8378 [32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m Epoch 17/78[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m 3/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 46ms/step - accuracy: 0.4375 - loss: 1.2966 
[1m 4/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 49ms/step - accuracy: 0.4385 - loss: 1.3018
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 41ms/step - accuracy: 0.5496 - loss: 1.0622 - val_accuracy: 0.6127 - val_loss: 0.8291[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m107/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m5s[0m 27ms/step - accuracy: 0.4209 - loss: 1.5376
[1m109/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m5s[0m 27ms/step - accuracy: 0.4208 - loss: 1.5377
[1m111/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m5s[0m 27ms/step - accuracy: 0.4207 - loss: 1.5379[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  4/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 19ms/step - accuracy: 0.3633 - loss: 1.6068 
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 43ms/step - accuracy: 0.7188 - loss: 0.6164
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 38ms/step - accuracy: 0.7231 - loss: 0.6314
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 41ms/step - accuracy: 0.7259 - loss: 0.6370
[1m  8/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 40ms/step - accuracy: 0.7246 - loss: 0.6476
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 10/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 40ms/step - accuracy: 0.7196 - loss: 0.6590
[1m 12/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 38ms/step - accuracy: 0.7141 - loss: 0.6726
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 14/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.7096 - loss: 0.6812
[1m 16/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 35ms/step - accuracy: 0.7056 - loss: 0.6873
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 18/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 35ms/step - accuracy: 0.7023 - loss: 0.6907
[1m 19/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.7007 - loss: 0.6926
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 20/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 37ms/step - accuracy: 0.6992 - loss: 0.6943
[1m 22/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 37ms/step - accuracy: 0.6954 - loss: 0.7003
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m8s[0m 27ms/step - accuracy: 0.2849 - loss: 1.7820 - val_accuracy: 0.4656 - val_loss: 1.1331[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=1127021)[0m 
[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 75ms/step - accuracy: 0.8125 - loss: 0.5105[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m16/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 36ms/step - accuracy: 0.5369 - loss: 1.0541
[1m18/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 35ms/step - accuracy: 0.5375 - loss: 1.0533[32m [repeated 113x across cluster][0m
[36m(train_cnn_ray_tune pid=1127019)[0m 
[1m279/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 25ms/step - accuracy: 0.3734 - loss: 1.6497
[1m281/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 25ms/step - accuracy: 0.3734 - loss: 1.6497[32m [repeated 395x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m10/78[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 48ms/step - accuracy: 0.4494 - loss: 1.2592[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m8s[0m 36ms/step - accuracy: 0.6725 - loss: 0.7442[32m [repeated 202x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 32/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.6842 - loss: 0.7228 
[1m 34/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.6830 - loss: 0.7253[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 112ms/step - accuracy: 0.4453 - loss: 1.2011
[1m 2/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 60ms/step - accuracy: 0.4531 - loss: 1.2252 [32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 61ms/step - accuracy: 0.4358 - loss: 1.3354  
[1m  4/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 59ms/step - accuracy: 0.4411 - loss: 1.3406
[36m(train_cnn_ray_tune pid=1127029)[0m Epoch 16/131[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 39ms/step - accuracy: 0.5518 - loss: 1.0509 - val_accuracy: 0.6162 - val_loss: 0.8189[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127019)[0m 
[1m 20/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.4075 - loss: 1.4875
[1m 22/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.4056 - loss: 1.4946
[1m 24/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.4041 - loss: 1.5005[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127021)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 37ms/step - accuracy: 0.7899 - loss: 0.5307 [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127030)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 37ms/step - accuracy: 0.3767 - loss: 1.9200
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 33ms/step - accuracy: 0.3954 - loss: 1.8445[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 44ms/step - accuracy: 0.3963 - loss: 1.4414 - val_accuracy: 0.4940 - val_loss: 1.1421[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127021)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 30ms/step - accuracy: 0.7795 - loss: 0.5970  
[36m(train_cnn_ray_tune pid=1127021)[0m 
[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 101ms/step - accuracy: 0.7812 - loss: 0.6186[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m76/78[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.5675 - loss: 1.0214
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 33ms/step - accuracy: 0.5674 - loss: 1.0215[32m [repeated 106x across cluster][0m
[36m(train_cnn_ray_tune pid=1127019)[0m 
[1m108/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m5s[0m 25ms/step - accuracy: 0.3849 - loss: 1.5576
[1m110/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m5s[0m 25ms/step - accuracy: 0.3848 - loss: 1.5582[32m [repeated 339x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m36/78[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 34ms/step - accuracy: 0.3791 - loss: 1.5308[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m 59/155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 29ms/step - accuracy: 0.5816 - loss: 0.9624[32m [repeated 277x across cluster][0m
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 30ms/step - accuracy: 0.3116 - loss: 1.8598 
[1m  5/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 29ms/step - accuracy: 0.3099 - loss: 1.8471[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 77ms/step - accuracy: 0.5156 - loss: 1.2037
[1m  4/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step - accuracy: 0.5062 - loss: 1.2494 [32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m Epoch 26/115[32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 3/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 34ms/step - accuracy: 0.3698 - loss: 1.5480 
[1m 5/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 33ms/step - accuracy: 0.3808 - loss: 1.5349
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 40ms/step - accuracy: 0.3811 - loss: 1.5284 - val_accuracy: 0.5042 - val_loss: 1.0175[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127023)[0m 
[1m158/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m3s[0m 24ms/step - accuracy: 0.5774 - loss: 0.9789
[1m160/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m3s[0m 24ms/step - accuracy: 0.5773 - loss: 0.9788
[1m162/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m3s[0m 24ms/step - accuracy: 0.5772 - loss: 0.9788[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 40ms/step - accuracy: 0.5877 - loss: 1.0258 
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m 3/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 30ms/step - accuracy: 0.6432 - loss: 0.8434 
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m6s[0m 35ms/step - accuracy: 0.2918 - loss: 1.8298 - val_accuracy: 0.4677 - val_loss: 1.1836[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.5399 - loss: 1.1166 
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.4225 - loss: 1.5002  
[1m  7/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.4191 - loss: 1.4788
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 54ms/step - accuracy: 0.4462 - loss: 1.6174  
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 72ms/step - accuracy: 0.5625 - loss: 1.0436[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m71/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 24ms/step - accuracy: 0.3837 - loss: 1.6292
[1m73/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 24ms/step - accuracy: 0.3837 - loss: 1.6297[32m [repeated 94x across cluster][0m
[36m(train_cnn_ray_tune pid=1127019)[0m 
[1m305/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 26ms/step - accuracy: 0.3837 - loss: 1.5879
[1m308/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 26ms/step - accuracy: 0.3837 - loss: 1.5881[32m [repeated 366x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 5/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 28ms/step - accuracy: 0.3996 - loss: 1.4772[32m [repeated 107x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m 40/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 24ms/step - accuracy: 0.4037 - loss: 1.4211[32m [repeated 245x across cluster][0m
[36m(train_cnn_ray_tune pid=1127030)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 254ms/step
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 34ms/step - accuracy: 0.3403 - loss: 1.5715 
[1m  5/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 33ms/step - accuracy: 0.3179 - loss: 1.6408[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127030)[0m 
[1m 6/43[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step  
[1m12/43[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1127030)[0m 
[1m19/43[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 9ms/step 
[36m(train_cnn_ray_tune pid=1127030)[0m 
[1m24/43[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1127030)[0m 
[1m30/43[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1127030)[0m 
[1m34/43[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 11ms/step
[1m40/43[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1127021)[0m 
[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 72ms/step - accuracy: 0.6875 - loss: 0.6712
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 33ms/step - accuracy: 0.7387 - loss: 0.5807 [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127030)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 15ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 41ms/step - accuracy: 0.4097 - loss: 1.3692  
[36m(train_cnn_ray_tune pid=1127030)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 37ms/step
[1m 8/89[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step 
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 11/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.6774 - loss: 0.6398
[1m 14/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 34ms/step - accuracy: 0.6745 - loss: 0.6488
[36m(train_cnn_ray_tune pid=1127030)[0m 
[1m13/89[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m17/89[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 16/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 34ms/step - accuracy: 0.6731 - loss: 0.6544
[1m 18/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.6716 - loss: 0.6601 
[36m(train_cnn_ray_tune pid=1127030)[0m 
[1m21/89[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1127030)[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=1127030)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1127030)[0m 2025-11-04 12:02:02.692439: 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=1127030)[0m 2025-11-04 12:02:02.711971: 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=1127031)[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=1127031)[0m E0000 00:00:1762254122.776952 1128321 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=1127031)[0m E0000 00:00:1762254122.785014 1128321 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=1127019)[0m W0000 00:00:1762254122.786999 1128319 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=1127019)[0m 2025-11-04 12:02:02.792251: 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=1127019)[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=1127030)[0m /home/simur/git/uniovi-simur-wearablepermed-ml/.venv/lib/python3.12/site-packages/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1127030)[0m   warnings.warn([32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1127030)[0m 2025-11-04 12:02:06.372157: 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=1127030)[0m 2025-11-04 12:02:06.372227: 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=1127030)[0m 2025-11-04 12:02:06.372237: 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=1127030)[0m 2025-11-04 12:02:06.372244: 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=1127030)[0m 2025-11-04 12:02:06.372250: 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=1127030)[0m 2025-11-04 12:02:06.372253: 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=1127030)[0m 2025-11-04 12:02:06.372658: 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=1127030)[0m 2025-11-04 12:02:06.372712: 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=1127030)[0m 2025-11-04 12:02:06.372716: 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=1127030)[0m 
[1m26/89[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m31/89[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1127030)[0m 
[1m35/89[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m40/89[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 22/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 35ms/step - accuracy: 0.6695 - loss: 0.6682
[1m 24/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.6681 - loss: 0.6719 
[36m(train_cnn_ray_tune pid=1127023)[0m Epoch 9/51[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=1127030)[0m 
[1m46/89[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m50/89[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1127030)[0m 
[1m54/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 11ms/step
[1m60/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1127019)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 246ms/step
[1m 6/43[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step  
[36m(train_cnn_ray_tune pid=1127030)[0m 
[1m65/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1127030)[0m 
[1m71/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 11ms/step
[1m76/89[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 11ms/step

Trial trial_af39f finished iteration 1 at 2025-11-04 12:03:17. Total running time: 1min 18s
╭──────────────────────────────────────╮
│ Trial trial_af39f result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             74.9586 │
│ time_total_s                 74.9586 │
│ training_iteration                 1 │
│ val_accuracy                 0.47472 │
╰──────────────────────────────────────╯

Trial trial_af39f completed after 1 iterations at 2025-11-04 12:03:17. Total running time: 1min 18s
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 40ms/step - accuracy: 0.5617 - loss: 1.0173 - val_accuracy: 0.6162 - val_loss: 0.8094[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=1127019)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 49ms/step
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m2s[0m 23ms/step - accuracy: 0.3143 - loss: 1.7223
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m2s[0m 23ms/step - accuracy: 0.3143 - loss: 1.7224
[1m210/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m2s[0m 23ms/step - accuracy: 0.3143 - loss: 1.7225[32m [repeated 3x across cluster][0m

Trial trial_af39f finished iteration 1 at 2025-11-04 12:03:18. Total running time: 1min 19s
╭──────────────────────────────────────╮
│ Trial trial_af39f result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             76.5749 │
│ time_total_s                 76.5749 │
│ training_iteration                 1 │
│ val_accuracy                  0.4856 │
╰──────────────────────────────────────╯

Trial trial_af39f completed after 1 iterations at 2025-11-04 12:03:18. Total running time: 1min 19s
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m4s[0m 25ms/step - accuracy: 0.4175 - loss: 1.4048 - val_accuracy: 0.5955 - val_loss: 0.9227[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 27ms/step - accuracy: 0.6163 - loss: 0.8290 
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 76ms/step - accuracy: 0.6406 - loss: 0.8453[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m68/78[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 25ms/step - accuracy: 0.3986 - loss: 1.6414
[1m71/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 25ms/step - accuracy: 0.3983 - loss: 1.6421[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m 20/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 29ms/step - accuracy: 0.6025 - loss: 0.8732
[1m 23/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 28ms/step - accuracy: 0.6023 - loss: 0.8763[32m [repeated 295x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m12/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 28ms/step - accuracy: 0.5624 - loss: 1.0187[32m [repeated 112x across cluster][0m
[36m(train_cnn_ray_tune pid=1127021)[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=1127021)[0m   _log_deprecation_warning([32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m100/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m5s[0m 26ms/step - accuracy: 0.4130 - loss: 1.5045[32m [repeated 233x across cluster][0m
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.4705 - loss: 0.8995 
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 23ms/step - accuracy: 0.4967 - loss: 0.9326[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127019)[0m 
[1m87/89[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 13ms/step[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m19/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 29ms/step - accuracy: 0.5662 - loss: 1.0177
[1m21/78[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 29ms/step - accuracy: 0.5668 - loss: 1.0171
[1m23/78[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 28ms/step - accuracy: 0.5675 - loss: 1.0166
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 65ms/step - accuracy: 0.4688 - loss: 1.5767
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.3385 - loss: 1.8057 [32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=1127021)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 195ms/step
[36m(train_cnn_ray_tune pid=1127021)[0m 
[1m 5/43[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 14ms/step 
[1m10/43[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1127029)[0m Epoch 20/131[32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=1127021)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 41ms/step
[36m(train_cnn_ray_tune pid=1127021)[0m 
[1m10/89[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step 
[1m17/89[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=1127021)[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=1127021)[0m 
[1m38/89[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1127021)[0m 
[1m44/89[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m51/89[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1127021)[0m 
[1m57/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 8ms/step
[1m65/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1127021)[0m 
[1m74/89[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=1127021)[0m 
[1m87/89[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 7ms/step

Trial trial_af39f finished iteration 1 at 2025-11-04 12:03:22. Total running time: 1min 23s
╭──────────────────────────────────────╮
│ Trial trial_af39f result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             80.4604 │
│ time_total_s                 80.4604 │
│ training_iteration                 1 │
│ val_accuracy                 0.73701 │
╰──────────────────────────────────────╯

Trial trial_af39f completed after 1 iterations at 2025-11-04 12:03:22. Total running time: 1min 23s
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m 3/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 29ms/step - accuracy: 0.5039 - loss: 1.1297 
[1m 5/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 33ms/step - accuracy: 0.5011 - loss: 1.1375
[36m(train_cnn_ray_tune pid=1127021)[0m 
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 34ms/step - accuracy: 0.5738 - loss: 1.0094 - val_accuracy: 0.6222 - val_loss: 0.8032[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m109/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m1s[0m 28ms/step - accuracy: 0.2950 - loss: 1.8127
[1m111/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m1s[0m 28ms/step - accuracy: 0.2951 - loss: 1.8122
[1m113/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m1s[0m 28ms/step - accuracy: 0.2952 - loss: 1.8117[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m5s[0m 31ms/step - accuracy: 0.6076 - loss: 0.9023 - val_accuracy: 0.6176 - val_loss: 0.7778[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127023)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 68ms/step - accuracy: 0.5938 - loss: 0.8945[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m24/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 21ms/step - accuracy: 0.6149 - loss: 0.8778
[1m27/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 21ms/step - accuracy: 0.6147 - loss: 0.8785[32m [repeated 113x across cluster][0m
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m 25/155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m3s[0m 26ms/step - accuracy: 0.3178 - loss: 1.7018
[1m 27/155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m3s[0m 26ms/step - accuracy: 0.3174 - loss: 1.7040[32m [repeated 306x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m28/78[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 21ms/step - accuracy: 0.3990 - loss: 1.6206[32m [repeated 82x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 15/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step - accuracy: 0.4250 - loss: 1.3591[32m [repeated 200x across cluster][0m
[36m(train_cnn_ray_tune pid=1127023)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 17ms/step - accuracy: 0.6328 - loss: 0.8748 
[1m  7/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 17ms/step - accuracy: 0.6445 - loss: 0.8374
[36m(train_cnn_ray_tune pid=1127021)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 14ms/step[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m70/78[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 29ms/step - accuracy: 0.3942 - loss: 1.4727
[1m72/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 29ms/step - accuracy: 0.3944 - loss: 1.4724
[1m74/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 29ms/step - accuracy: 0.3946 - loss: 1.4720
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 87ms/step - accuracy: 0.4688 - loss: 1.2704
[1m 4/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 25ms/step - accuracy: 0.4852 - loss: 1.2225[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 17ms/step - accuracy: 0.6017 - loss: 0.7665 
[36m(train_cnn_ray_tune pid=1127018)[0m Epoch 33/89[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 34ms/step - accuracy: 0.6378 - loss: 0.7644
[1m  7/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.6437 - loss: 0.7504 
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 32ms/step - accuracy: 0.5761 - loss: 0.9858 - val_accuracy: 0.6176 - val_loss: 0.7951[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 19ms/step - accuracy: 0.5820 - loss: 0.9570 
[1m  7/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 19ms/step - accuracy: 0.5855 - loss: 0.9466
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m 98/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m3s[0m 15ms/step - accuracy: 0.6185 - loss: 0.8148
[1m102/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m3s[0m 15ms/step - accuracy: 0.6191 - loss: 0.8145
[1m106/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m3s[0m 15ms/step - accuracy: 0.6199 - loss: 0.8143[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m5s[0m 30ms/step - accuracy: 0.3038 - loss: 1.7480 - val_accuracy: 0.4688 - val_loss: 1.1874[32m [repeated 12x across cluster][0m

Trial status: 17 RUNNING | 3 TERMINATED
Current time: 2025-11-04 12:03:29. Total running time: 1min 30s
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     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_af39f    RUNNING              2   rmsprop         tanh                                  128                 32                  5          0.000531671         89                                              │
│ trial_af39f    RUNNING              3   adam            relu                                   32                 32                  5          8.9631e-05          60                                              │
│ trial_af39f    RUNNING              2   adam            tanh                                  128                 32                  5          2.05278e-05        115                                              │
│ trial_af39f    RUNNING              2   adam            tanh                                  128                 64                  5          0.000263082         78                                              │
│ trial_af39f    RUNNING              3   rmsprop         tanh                                   32                 32                  3          0.00135267          51                                              │
│ trial_af39f    RUNNING              3   adam            relu                                  128                 64                  3          0.000113647        124                                              │
│ trial_af39f    RUNNING              3   adam            relu                                   32                 32                  5          0.000608101         70                                              │
│ trial_af39f    RUNNING              3   adam            relu                                   32                 32                  5          2.34078e-05        139                                              │
│ trial_af39f    RUNNING              3   adam            tanh                                   32                 64                  5          6.10182e-05         70                                              │
│ trial_af39f    RUNNING              3   rmsprop         relu                                  128                 32                  5          4.00548e-05        132                                              │
│ trial_af39f    RUNNING              2   rmsprop         tanh                                   32                 64                  3          0.00160542         137                                              │
│ trial_af39f    RUNNING              4   adam            tanh                                   64                 64                  3          0.000170953         52                                              │
│ trial_af39f    RUNNING              3   rmsprop         relu                                   64                128                  5          5.18891e-05        146                                              │
│ trial_af39f    RUNNING              4   adam            tanh                                   64                 32                  3          2.56847e-05         93                                              │
│ trial_af39f    RUNNING              3   rmsprop         relu                                   32                128                  5          0.000409376         53                                              │
│ trial_af39f    RUNNING              2   rmsprop         relu                                   64                 32                  3          4.34693e-05        131                                              │
│ trial_af39f    RUNNING              4   adam            relu                                   64                 32                  3          0.0028724           66                                              │
│ trial_af39f    TERMINATED           3   rmsprop         tanh                                   32                 64                  3          4.80349e-05         99        1            76.5749         0.485604 │
│ trial_af39f    TERMINATED           2   rmsprop         relu                                   64                128                  3          0.00143439          82        1            80.4604         0.737008 │
│ trial_af39f    TERMINATED           3   rmsprop         tanh                                   32                 64                  3          3.42484e-05        134        1            74.9586         0.474719 │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 92ms/step - accuracy: 0.3438 - loss: 1.7048[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m60/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 21ms/step - accuracy: 0.3960 - loss: 1.6346
[1m63/78[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 21ms/step - accuracy: 0.3965 - loss: 1.6330[32m [repeated 112x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m 54/155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m2s[0m 26ms/step - accuracy: 0.6260 - loss: 0.8133
[1m 56/155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 26ms/step - accuracy: 0.6257 - loss: 0.8142[32m [repeated 326x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m63/78[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 27ms/step - accuracy: 0.4166 - loss: 1.4219[32m [repeated 109x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m 61/155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m3s[0m 36ms/step - accuracy: 0.5000 - loss: 1.2942[32m [repeated 129x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 79ms/step - accuracy: 0.6484 - loss: 0.7246
[1m 4/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 18ms/step - accuracy: 0.6447 - loss: 0.8071[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.3194 - loss: 1.7503 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m Epoch 23/131[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 32ms/step - accuracy: 0.5933 - loss: 0.9511 - val_accuracy: 0.6229 - val_loss: 0.7843[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m 4/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 21ms/step - accuracy: 0.3709 - loss: 1.7506 
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 16ms/step - accuracy: 0.5743 - loss: 0.8654 
[1m  8/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 17ms/step - accuracy: 0.5913 - loss: 0.8354[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m200/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m2s[0m 20ms/step - accuracy: 0.3163 - loss: 1.6873
[1m203/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m2s[0m 20ms/step - accuracy: 0.3162 - loss: 1.6871
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m2s[0m 20ms/step - accuracy: 0.3162 - loss: 1.6870[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 295ms/step
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m 9/43[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step   
[1m16/43[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m21/43[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m27/43[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m33/43[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step
[1m38/43[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m8s[0m 26ms/step - accuracy: 0.4303 - loss: 1.4453 - val_accuracy: 0.5021 - val_loss: 1.0543[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=1127026)[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=1127026)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 44ms/step
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m 7/89[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m11/89[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m15/89[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[1m21/89[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 66ms/step - accuracy: 0.3828 - loss: 1.5703[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m26/89[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m33/89[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m38/89[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m10/78[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 20ms/step - accuracy: 0.4001 - loss: 1.6236
[1m12/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 22ms/step - accuracy: 0.3995 - loss: 1.6207[32m [repeated 110x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m 59/155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 25ms/step - accuracy: 0.6510 - loss: 0.8314
[1m 61/155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 25ms/step - accuracy: 0.6509 - loss: 0.8313[32m [repeated 311x across cluster][0m
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m43/89[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m47/89[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1127026)[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=1127026)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m52/89[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m56/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m26/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 21ms/step - accuracy: 0.3979 - loss: 1.6180[32m [repeated 83x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 36/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 21ms/step - accuracy: 0.3036 - loss: 1.7372[32m [repeated 157x across cluster][0m
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m61/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 11ms/step
[1m67/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 11ms/step
[1m72/89[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m77/89[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 11ms/step
[1m81/89[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1127026)[0m 
[1m86/89[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 11ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 11ms/step

Trial trial_af39f finished iteration 1 at 2025-11-04 12:03:35. Total running time: 1min 36s
╭──────────────────────────────────────╮
│ Trial trial_af39f result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s              93.886 │
│ time_total_s                  93.886 │
│ training_iteration                 1 │
│ val_accuracy                 0.47402 │
╰──────────────────────────────────────╯

Trial trial_af39f completed after 1 iterations at 2025-11-04 12:03:35. Total running time: 1min 36s
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 99ms/step - accuracy: 0.2188 - loss: 2.0262
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.2734 - loss: 1.8649 [32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 38ms/step - accuracy: 0.4436 - loss: 1.4146 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127018)[0m Epoch 38/89[32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 30ms/step - accuracy: 0.5913 - loss: 0.9550 - val_accuracy: 0.6246 - val_loss: 0.7768[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.6910 - loss: 0.7143 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.7008 - loss: 0.6890[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m163/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m2s[0m 20ms/step - accuracy: 0.3202 - loss: 1.6695
[1m165/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m2s[0m 20ms/step - accuracy: 0.3203 - loss: 1.6693
[1m168/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m2s[0m 20ms/step - accuracy: 0.3203 - loss: 1.6689[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m5s[0m 30ms/step - accuracy: 0.6457 - loss: 0.8335 - val_accuracy: 0.6829 - val_loss: 0.6635[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 73ms/step - accuracy: 0.6016 - loss: 0.9824[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m10/78[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 22ms/step - accuracy: 0.6163 - loss: 0.9506
[1m12/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 23ms/step - accuracy: 0.6146 - loss: 0.9509[32m [repeated 123x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m 84/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 22ms/step - accuracy: 0.6294 - loss: 0.8563
[1m 87/155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 22ms/step - accuracy: 0.6293 - loss: 0.8565[32m [repeated 310x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m11/78[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 30ms/step - accuracy: 0.5321 - loss: 1.1041[32m [repeated 84x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 98/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m5s[0m 28ms/step - accuracy: 0.7229 - loss: 0.6209[32m [repeated 129x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 61ms/step - accuracy: 0.3828 - loss: 1.5254
[1m 4/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 24ms/step - accuracy: 0.3818 - loss: 1.4588[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 29ms/step - accuracy: 0.4531 - loss: 1.1396 
[36m(train_cnn_ray_tune pid=1127028)[0m Epoch 11/70[32m [repeated 23x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 34ms/step - accuracy: 0.5339 - loss: 1.0897 - val_accuracy: 0.6215 - val_loss: 0.8131[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 28ms/step - accuracy: 0.6528 - loss: 0.8985 
[1m  6/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 24ms/step - accuracy: 0.6319 - loss: 0.8973[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 43/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 18ms/step - accuracy: 0.3289 - loss: 1.6413
[1m 46/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 17ms/step - accuracy: 0.3294 - loss: 1.6407
[1m 49/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m4s[0m 18ms/step - accuracy: 0.3297 - loss: 1.6401[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127023)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 18ms/step - accuracy: 0.5736 - loss: 1.0982 
[36m(train_cnn_ray_tune pid=1127023)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m6s[0m 20ms/step - accuracy: 0.5878 - loss: 0.9145 - val_accuracy: 0.6647 - val_loss: 0.7254[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 71ms/step - accuracy: 0.4453 - loss: 1.5565[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m42/78[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 19ms/step - accuracy: 0.4160 - loss: 1.5400
[1m45/78[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 19ms/step - accuracy: 0.4161 - loss: 1.5391[32m [repeated 122x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 24ms/step - accuracy: 0.6327 - loss: 0.8440
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 24ms/step - accuracy: 0.6328 - loss: 0.8436[32m [repeated 300x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m23/78[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 25ms/step - accuracy: 0.6307 - loss: 0.9133[32m [repeated 80x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m186/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m2s[0m 20ms/step - accuracy: 0.4420 - loss: 1.3768[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 80ms/step - accuracy: 0.5000 - loss: 1.1052
[1m 3/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 25ms/step - accuracy: 0.5122 - loss: 1.0711[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m Epoch 19/66[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 26ms/step - accuracy: 0.4260 - loss: 1.3659 - val_accuracy: 0.5513 - val_loss: 0.9308[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 22ms/step - accuracy: 0.6738 - loss: 0.8594 
[1m  7/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 23ms/step - accuracy: 0.6919 - loss: 0.7869[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 95/155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 14ms/step - accuracy: 0.4594 - loss: 1.2610
[1m 99/155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 14ms/step - accuracy: 0.4594 - loss: 1.2612
[1m104/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 14ms/step - accuracy: 0.4593 - loss: 1.2615[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.3340 - loss: 1.5841 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 23ms/step - accuracy: 0.4421 - loss: 1.3791 - val_accuracy: 0.5091 - val_loss: 1.0380[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127023)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 61ms/step - accuracy: 0.6562 - loss: 0.7818[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m48/78[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 25ms/step - accuracy: 0.6173 - loss: 0.9140
[1m51/78[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 25ms/step - accuracy: 0.6171 - loss: 0.9137[32m [repeated 129x across cluster][0m
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m173/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 14ms/step - accuracy: 0.6719 - loss: 0.7561
[1m176/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 14ms/step - accuracy: 0.6718 - loss: 0.7564[32m [repeated 283x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m73/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 29ms/step - accuracy: 0.5342 - loss: 1.0698[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m141/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m2s[0m 18ms/step - accuracy: 0.6329 - loss: 0.8572[32m [repeated 106x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 65ms/step - accuracy: 0.3984 - loss: 1.6907
[1m 4/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 18ms/step - accuracy: 0.4002 - loss: 1.6488[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m Epoch 15/146[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 30ms/step - accuracy: 0.4289 - loss: 1.3482 - val_accuracy: 0.5527 - val_loss: 0.9240[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  5/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 18ms/step - accuracy: 0.4669 - loss: 1.2613 
[1m  8/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 18ms/step - accuracy: 0.4555 - loss: 1.2694[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m238/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m1s[0m 18ms/step - accuracy: 0.3312 - loss: 1.5998
[1m242/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m1s[0m 18ms/step - accuracy: 0.3312 - loss: 1.5997
[1m245/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m1s[0m 18ms/step - accuracy: 0.3311 - loss: 1.5997[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 36ms/step - accuracy: 0.4123 - loss: 1.3283 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m34/78[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 18ms/step - accuracy: 0.4140 - loss: 1.5198
[1m37/78[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 18ms/step - accuracy: 0.4142 - loss: 1.5194
[1m40/78[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 18ms/step - accuracy: 0.4144 - loss: 1.5188
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m6s[0m 18ms/step - accuracy: 0.6697 - loss: 0.7656 - val_accuracy: 0.6928 - val_loss: 0.6208[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 66ms/step - accuracy: 0.2188 - loss: 1.5015[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m62/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 25ms/step - accuracy: 0.6208 - loss: 0.9128
[1m64/78[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 25ms/step - accuracy: 0.6208 - loss: 0.9127[32m [repeated 120x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m 12/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 24ms/step - accuracy: 0.6618 - loss: 0.7490
[1m 14/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 24ms/step - accuracy: 0.6610 - loss: 0.7509[32m [repeated 311x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m60/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 25ms/step - accuracy: 0.6207 - loss: 0.9131[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 20ms/step - accuracy: 0.3037 - loss: 1.5915[32m [repeated 152x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 82ms/step - accuracy: 0.4688 - loss: 1.3746
[1m 4/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 22ms/step - accuracy: 0.4541 - loss: 1.4063[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m Epoch 32/124[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 23ms/step - accuracy: 0.4265 - loss: 1.4980 - val_accuracy: 0.5379 - val_loss: 1.0011[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 40ms/step - accuracy: 0.5330 - loss: 1.1537 
[1m  5/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 36ms/step - accuracy: 0.5431 - loss: 1.1177[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m154/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m2s[0m 15ms/step - accuracy: 0.6598 - loss: 0.7689
[1m158/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m2s[0m 15ms/step - accuracy: 0.6598 - loss: 0.7688
[1m162/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m2s[0m 15ms/step - accuracy: 0.6599 - loss: 0.7687[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.8014 - loss: 0.5093 

Trial status: 16 RUNNING | 4 TERMINATED
Current time: 2025-11-04 12:03:59. Total running time: 2min 0s
Logical resource usage: 16.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status         N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_af39f    RUNNING              2   rmsprop         tanh                                  128                 32                  5          0.000531671         89                                              │
│ trial_af39f    RUNNING              3   adam            relu                                   32                 32                  5          8.9631e-05          60                                              │
│ trial_af39f    RUNNING              2   adam            tanh                                  128                 32                  5          2.05278e-05        115                                              │
│ trial_af39f    RUNNING              2   adam            tanh                                  128                 64                  5          0.000263082         78                                              │
│ trial_af39f    RUNNING              3   rmsprop         tanh                                   32                 32                  3          0.00135267          51                                              │
│ trial_af39f    RUNNING              3   adam            relu                                  128                 64                  3          0.000113647        124                                              │
│ trial_af39f    RUNNING              3   adam            relu                                   32                 32                  5          0.000608101         70                                              │
│ trial_af39f    RUNNING              3   adam            relu                                   32                 32                  5          2.34078e-05        139                                              │
│ trial_af39f    RUNNING              3   adam            tanh                                   32                 64                  5          6.10182e-05         70                                              │
│ trial_af39f    RUNNING              3   rmsprop         relu                                  128                 32                  5          4.00548e-05        132                                              │
│ trial_af39f    RUNNING              2   rmsprop         tanh                                   32                 64                  3          0.00160542         137                                              │
│ trial_af39f    RUNNING              4   adam            tanh                                   64                 64                  3          0.000170953         52                                              │
│ trial_af39f    RUNNING              3   rmsprop         relu                                   64                128                  5          5.18891e-05        146                                              │
│ trial_af39f    RUNNING              3   rmsprop         relu                                   32                128                  5          0.000409376         53                                              │
│ trial_af39f    RUNNING              2   rmsprop         relu                                   64                 32                  3          4.34693e-05        131                                              │
│ trial_af39f    RUNNING              4   adam            relu                                   64                 32                  3          0.0028724           66                                              │
│ trial_af39f    TERMINATED           3   rmsprop         tanh                                   32                 64                  3          4.80349e-05         99        1            76.5749         0.485604 │
│ trial_af39f    TERMINATED           4   adam            tanh                                   64                 32                  3          2.56847e-05         93        1            93.8861         0.474017 │
│ trial_af39f    TERMINATED           2   rmsprop         relu                                   64                128                  3          0.00143439          82        1            80.4604         0.737008 │
│ trial_af39f    TERMINATED           3   rmsprop         tanh                                   32                 64                  3          3.42484e-05        134        1            74.9586         0.474719 │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m  4/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6663 - loss: 0.7886 
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m4s[0m 27ms/step - accuracy: 0.6516 - loss: 0.7905 - val_accuracy: 0.6970 - val_loss: 0.6393[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 96ms/step - accuracy: 0.5391 - loss: 1.0641[32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m74/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 25ms/step - accuracy: 0.6154 - loss: 0.9003
[1m76/78[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 25ms/step - accuracy: 0.6155 - loss: 0.9000[32m [repeated 119x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m 44/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m2s[0m 24ms/step - accuracy: 0.6481 - loss: 0.7810
[1m 47/155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m2s[0m 23ms/step - accuracy: 0.6482 - loss: 0.7809[32m [repeated 310x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m51/78[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 20ms/step - accuracy: 0.4108 - loss: 1.5164[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 18ms/step - accuracy: 0.3309 - loss: 1.5932[32m [repeated 143x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 89ms/step - accuracy: 0.6484 - loss: 0.8659
[1m 4/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 22ms/step - accuracy: 0.6460 - loss: 0.8710[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m Epoch 41/132[32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 37ms/step - accuracy: 0.5658 - loss: 0.9812 - val_accuracy: 0.6338 - val_loss: 0.7786[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 17ms/step - accuracy: 0.7474 - loss: 0.6992 
[1m  8/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 17ms/step - accuracy: 0.7390 - loss: 0.6947
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m 97/155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 23ms/step - accuracy: 0.6474 - loss: 0.7856
[1m 99/155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 23ms/step - accuracy: 0.6474 - loss: 0.7857
[1m101/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m1s[0m 23ms/step - accuracy: 0.6475 - loss: 0.7859[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 17ms/step - accuracy: 0.4913 - loss: 1.1042 
[1m  8/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 18ms/step - accuracy: 0.4821 - loss: 1.1300
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m12/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 26ms/step - accuracy: 0.4351 - loss: 1.3125
[1m14/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 26ms/step - accuracy: 0.4369 - loss: 1.3090
[1m16/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 26ms/step - accuracy: 0.4379 - loss: 1.3064
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 35ms/step - accuracy: 0.5616 - loss: 1.0738 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m6s[0m 18ms/step - accuracy: 0.6845 - loss: 0.7475 - val_accuracy: 0.6949 - val_loss: 0.6207[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 64ms/step - accuracy: 0.7188 - loss: 0.5345[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m52/78[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 19ms/step - accuracy: 0.6297 - loss: 0.8223
[1m55/78[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 19ms/step - accuracy: 0.6297 - loss: 0.8222[32m [repeated 123x across cluster][0m
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m 53/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m4s[0m 17ms/step - accuracy: 0.6836 - loss: 0.7152
[1m 57/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m4s[0m 16ms/step - accuracy: 0.6837 - loss: 0.7159[32m [repeated 308x across cluster][0m
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m58/78[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 19ms/step - accuracy: 0.6297 - loss: 0.8222[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m127/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 16ms/step - accuracy: 0.4887 - loss: 1.1769[32m [repeated 137x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m73/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 25ms/step - accuracy: 0.4428 - loss: 1.2914
[1m75/78[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 25ms/step - accuracy: 0.4428 - loss: 1.2914
[1m77/78[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 25ms/step - accuracy: 0.4428 - loss: 1.2913
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 87ms/step - accuracy: 0.6641 - loss: 0.8140
[1m 3/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 28ms/step - accuracy: 0.6445 - loss: 0.8327[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m  3/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 33ms/step - accuracy: 0.6684 - loss: 0.7609
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 34ms/step - accuracy: 0.6898 - loss: 0.7047
[36m(train_cnn_ray_tune pid=1127004)[0m Epoch 54/115[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 24ms/step - accuracy: 0.4103 - loss: 1.4998 - val_accuracy: 0.5428 - val_loss: 0.9926[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m180/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m2s[0m 16ms/step - accuracy: 0.6777 - loss: 0.7337
[1m183/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m2s[0m 16ms/step - accuracy: 0.6776 - loss: 0.7341
[1m186/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 16ms/step - accuracy: 0.6776 - loss: 0.7345[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m  4/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 23ms/step - accuracy: 0.6755 - loss: 0.7408 
[1m  7/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.6769 - loss: 0.7710[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m69/78[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 29ms/step - accuracy: 0.5770 - loss: 0.9685
[1m71/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 29ms/step - accuracy: 0.5769 - loss: 0.9687
[1m73/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 29ms/step - accuracy: 0.5767 - loss: 0.9689
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m  7/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.7075 - loss: 0.6639 
[36m(train_cnn_ray_tune pid=1127023)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 21ms/step - accuracy: 0.6121 - loss: 0.8649 - val_accuracy: 0.6840 - val_loss: 0.6603[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 37ms/step - accuracy: 0.5460 - loss: 1.0577 
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 66ms/step - accuracy: 0.5312 - loss: 1.0542[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m13/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 21ms/step - accuracy: 0.6264 - loss: 0.8208
[1m16/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 20ms/step - accuracy: 0.6276 - loss: 0.8227[32m [repeated 103x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m108/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m1s[0m 23ms/step - accuracy: 0.6522 - loss: 0.7975
[1m111/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m1s[0m 23ms/step - accuracy: 0.6522 - loss: 0.7975[32m [repeated 295x across cluster][0m
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m22/78[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 21ms/step - accuracy: 0.6298 - loss: 0.8241[32m [repeated 111x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m140/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m4s[0m 28ms/step - accuracy: 0.7419 - loss: 0.5991[32m [repeated 141x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 81ms/step - accuracy: 0.5312 - loss: 1.1131
[1m 4/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 22ms/step - accuracy: 0.4945 - loss: 1.1871[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m Epoch 15/70[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 25ms/step - accuracy: 0.4142 - loss: 1.4944 - val_accuracy: 0.5449 - val_loss: 0.9893[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m 75/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m3s[0m 15ms/step - accuracy: 0.6665 - loss: 0.7361
[1m 79/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m3s[0m 15ms/step - accuracy: 0.6671 - loss: 0.7364
[1m 83/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m3s[0m 15ms/step - accuracy: 0.6677 - loss: 0.7368[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.4844 - loss: 1.1401 
[1m  7/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 19ms/step - accuracy: 0.4889 - loss: 1.1393[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m 3/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 31ms/step - accuracy: 0.5803 - loss: 1.0063 
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 19ms/step - accuracy: 0.4759 - loss: 1.2032 - val_accuracy: 0.6197 - val_loss: 0.8506[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 18ms/step - accuracy: 0.5358 - loss: 1.1353 
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.2878 - loss: 1.5170 
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 60ms/step - accuracy: 0.5781 - loss: 0.9185[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m39/78[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 19ms/step - accuracy: 0.4203 - loss: 1.4690
[1m42/78[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 19ms/step - accuracy: 0.4210 - loss: 1.4686[32m [repeated 117x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m136/155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 23ms/step - accuracy: 0.6525 - loss: 0.7997
[1m138/155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 24ms/step - accuracy: 0.6524 - loss: 0.7996[32m [repeated 279x across cluster][0m
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m77/78[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 19ms/step - accuracy: 0.6379 - loss: 0.8236[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 25/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 17ms/step - accuracy: 0.3270 - loss: 1.5344[32m [repeated 201x across cluster][0m
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 70ms/step - accuracy: 0.6406 - loss: 0.8362
[1m 4/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 22ms/step - accuracy: 0.6393 - loss: 0.7935[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m Epoch 17/60[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 24ms/step - accuracy: 0.6443 - loss: 0.8089 - val_accuracy: 0.6527 - val_loss: 0.6883[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 14ms/step - accuracy: 0.4764 - loss: 1.1880
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 15ms/step - accuracy: 0.4765 - loss: 1.1877
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 15ms/step - accuracy: 0.4766 - loss: 1.1873[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127023)[0m 
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 13ms/step - accuracy: 0.6259 - loss: 0.7754 
[1m  9/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 15ms/step - accuracy: 0.6167 - loss: 0.7885[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 19ms/step - accuracy: 0.4323 - loss: 1.2898 
[1m  7/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 19ms/step - accuracy: 0.4678 - loss: 1.2670
[1m 10/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 18ms/step - accuracy: 0.4828 - loss: 1.2566
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m57/78[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 26ms/step - accuracy: 0.4702 - loss: 1.2275
[1m59/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 26ms/step - accuracy: 0.4700 - loss: 1.2275
[1m61/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 26ms/step - accuracy: 0.4698 - loss: 1.2276
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 24ms/step - accuracy: 0.4615 - loss: 1.3088 - val_accuracy: 0.5530 - val_loss: 0.9763[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 74ms/step - accuracy: 0.4766 - loss: 1.2867[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m18/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 28ms/step - accuracy: 0.6270 - loss: 0.8680
[1m20/78[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 28ms/step - accuracy: 0.6274 - loss: 0.8663[32m [repeated 113x across cluster][0m
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m302/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 15ms/step - accuracy: 0.6749 - loss: 0.7429
[1m305/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 15ms/step - accuracy: 0.6750 - loss: 0.7429[32m [repeated 325x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m15/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 19ms/step - accuracy: 0.4293 - loss: 1.4514[32m [repeated 74x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m145/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m4s[0m 28ms/step - accuracy: 0.7590 - loss: 0.5570[32m [repeated 123x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 66ms/step - accuracy: 0.4062 - loss: 1.3275
[1m  5/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step - accuracy: 0.4289 - loss: 1.2870 [32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 296ms/step
[1m 8/43[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step   
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m15/43[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m20/43[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m26/43[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=1127012)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 38ms/step - accuracy: 0.5321 - loss: 1.1001 
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m36/43[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 10ms/step
[1m42/43[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=1127033)[0m Epoch 21/52[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 48ms/step
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m 7/89[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step 
[1m12/89[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m17/89[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m23/89[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m27/89[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m31/89[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m36/89[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m42/89[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m47/89[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m52/89[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m58/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m65/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m73/89[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=1127025)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 40ms/step - accuracy: 0.5945 - loss: 0.9323 - val_accuracy: 0.6506 - val_loss: 0.7386[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127024)[0m 
[1m87/89[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 10ms/step

Trial trial_af39f finished iteration 1 at 2025-11-04 12:04:23. Total running time: 2min 24s
[36m(train_cnn_ray_tune pid=1127024)[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=1127024)[0m   _log_deprecation_warning(
╭──────────────────────────────────────╮
│ Trial trial_af39f result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s              141.32 │
│ time_total_s                  141.32 │
│ training_iteration                 1 │
│ val_accuracy                 0.68645 │
╰──────────────────────────────────────╯

Trial trial_af39f completed after 1 iterations at 2025-11-04 12:04:23. Total running time: 2min 24s
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 14ms/step - accuracy: 0.6666 - loss: 0.7534
[1m117/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 14ms/step - accuracy: 0.6668 - loss: 0.7529
[1m120/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 14ms/step - accuracy: 0.6670 - loss: 0.7525[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127023)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.6426 - loss: 0.7665 
[1m  7/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 20ms/step - accuracy: 0.6301 - loss: 0.7920[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m66/78[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 18ms/step - accuracy: 0.4197 - loss: 1.4658
[1m69/78[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 18ms/step - accuracy: 0.4197 - loss: 1.4656
[1m71/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 18ms/step - accuracy: 0.4197 - loss: 1.4654[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 18ms/step - accuracy: 0.4854 - loss: 1.1713 - val_accuracy: 0.6194 - val_loss: 0.8448[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 60ms/step - accuracy: 0.6562 - loss: 0.8567[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m18/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 21ms/step - accuracy: 0.4581 - loss: 1.2529
[1m21/78[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 21ms/step - accuracy: 0.4598 - loss: 1.2488[32m [repeated 116x across cluster][0m
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m277/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 15ms/step - accuracy: 0.6753 - loss: 0.7447
[1m282/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 14ms/step - accuracy: 0.6754 - loss: 0.7446[32m [repeated 281x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m44/78[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 23ms/step - accuracy: 0.6395 - loss: 0.8415[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 69/155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 15ms/step - accuracy: 0.4858 - loss: 1.1578[32m [repeated 122x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 83ms/step - accuracy: 0.4531 - loss: 1.3709
[1m 4/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step - accuracy: 0.4412 - loss: 1.3178[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 18ms/step - accuracy: 0.5098 - loss: 1.0488 
[36m(train_cnn_ray_tune pid=1127011)[0m Epoch 52/132[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 30ms/step - accuracy: 0.5182 - loss: 1.1573 
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 32ms/step - accuracy: 0.5944 - loss: 0.9354 - val_accuracy: 0.6559 - val_loss: 0.7242[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m 82/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m2s[0m 13ms/step - accuracy: 0.6750 - loss: 0.7382
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m2s[0m 13ms/step - accuracy: 0.6752 - loss: 0.7378
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m2s[0m 13ms/step - accuracy: 0.6755 - loss: 0.7372[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 18ms/step - accuracy: 0.4023 - loss: 1.4291 
[1m  8/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 16ms/step - accuracy: 0.4070 - loss: 1.4382[32m [repeated 5x across cluster][0m

Trial status: 15 RUNNING | 5 TERMINATED
Current time: 2025-11-04 12:04:29. Total running time: 2min 30s
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     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_af39f    RUNNING              2   rmsprop         tanh                                  128                 32                  5          0.000531671         89                                              │
│ trial_af39f    RUNNING              3   adam            relu                                   32                 32                  5          8.9631e-05          60                                              │
│ trial_af39f    RUNNING              2   adam            tanh                                  128                 32                  5          2.05278e-05        115                                              │
│ trial_af39f    RUNNING              2   adam            tanh                                  128                 64                  5          0.000263082         78                                              │
│ trial_af39f    RUNNING              3   rmsprop         tanh                                   32                 32                  3          0.00135267          51                                              │
│ trial_af39f    RUNNING              3   adam            relu                                  128                 64                  3          0.000113647        124                                              │
│ trial_af39f    RUNNING              3   adam            relu                                   32                 32                  5          0.000608101         70                                              │
│ trial_af39f    RUNNING              3   adam            relu                                   32                 32                  5          2.34078e-05        139                                              │
│ trial_af39f    RUNNING              3   adam            tanh                                   32                 64                  5          6.10182e-05         70                                              │
│ trial_af39f    RUNNING              3   rmsprop         relu                                  128                 32                  5          4.00548e-05        132                                              │
│ trial_af39f    RUNNING              2   rmsprop         tanh                                   32                 64                  3          0.00160542         137                                              │
│ trial_af39f    RUNNING              4   adam            tanh                                   64                 64                  3          0.000170953         52                                              │
│ trial_af39f    RUNNING              3   rmsprop         relu                                   64                128                  5          5.18891e-05        146                                              │
│ trial_af39f    RUNNING              3   rmsprop         relu                                   32                128                  5          0.000409376         53                                              │
│ trial_af39f    RUNNING              2   rmsprop         relu                                   64                 32                  3          4.34693e-05        131                                              │
│ trial_af39f    TERMINATED           3   rmsprop         tanh                                   32                 64                  3          4.80349e-05         99        1            76.5749         0.485604 │
│ trial_af39f    TERMINATED           4   adam            tanh                                   64                 32                  3          2.56847e-05         93        1            93.8861         0.474017 │
│ trial_af39f    TERMINATED           2   rmsprop         relu                                   64                128                  3          0.00143439          82        1            80.4604         0.737008 │
│ trial_af39f    TERMINATED           3   rmsprop         tanh                                   32                 64                  3          3.42484e-05        134        1            74.9586         0.474719 │
│ trial_af39f    TERMINATED           4   adam            relu                                   64                 32                  3          0.0028724           66        1           141.32           0.686447 │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1127023)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m6s[0m 20ms/step - accuracy: 0.6219 - loss: 0.8514 - val_accuracy: 0.6629 - val_loss: 0.6821[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 61ms/step - accuracy: 0.4375 - loss: 1.2405[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m69/78[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 20ms/step - accuracy: 0.4232 - loss: 1.4576
[1m72/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 20ms/step - accuracy: 0.4235 - loss: 1.4571[32m [repeated 136x across cluster][0m
[36m(train_cnn_ray_tune pid=1127018)[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=1127018)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 14ms/step - accuracy: 0.6776 - loss: 0.7370
[1m272/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 14ms/step - accuracy: 0.6776 - loss: 0.7370[32m [repeated 289x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m66/78[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 24ms/step - accuracy: 0.6431 - loss: 0.8312[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=1127023)[0m 
[1m118/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m3s[0m 17ms/step - accuracy: 0.6309 - loss: 0.8371[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 177ms/step
[1m 9/43[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step  
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m18/43[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m24/43[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m34/43[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m41/43[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 80ms/step - accuracy: 0.5312 - loss: 1.0199
[1m 3/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 25ms/step - accuracy: 0.5703 - loss: 0.9711[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 36ms/step
[1m11/89[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step 
[36m(train_cnn_ray_tune pid=1127018)[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=1127018)[0m 
[1m32/89[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m39/89[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m46/89[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=1127018)[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=1127018)[0m 
[1m67/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 7ms/step
[1m76/89[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=1127018)[0m 
[1m85/89[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 7ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

Trial trial_af39f finished iteration 1 at 2025-11-04 12:04:32. Total running time: 2min 33s
╭──────────────────────────────────────╮
│ Trial trial_af39f result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             150.309 │
│ time_total_s                 150.309 │
│ training_iteration                 1 │
│ val_accuracy                 0.65871 │
╰──────────────────────────────────────╯

Trial trial_af39f completed after 1 iterations at 2025-11-04 12:04:32. Total running time: 2min 33s
[36m(train_cnn_ray_tune pid=1127033)[0m Epoch 23/52[32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=1127023)[0m 
[1m  4/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 18ms/step - accuracy: 0.5391 - loss: 1.1164 
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 22ms/step - accuracy: 0.4469 - loss: 1.4169 - val_accuracy: 0.5523 - val_loss: 0.9751[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m133/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m2s[0m 14ms/step - accuracy: 0.6773 - loss: 0.7345
[1m136/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m2s[0m 14ms/step - accuracy: 0.6773 - loss: 0.7344
[1m141/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m2s[0m 14ms/step - accuracy: 0.6773 - loss: 0.7343
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m106/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m2s[0m 13ms/step - accuracy: 0.6815 - loss: 0.7647
[1m110/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 13ms/step - accuracy: 0.6817 - loss: 0.7642
[1m114/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 13ms/step - accuracy: 0.6819 - loss: 0.7637
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.5365 - loss: 1.0472 
[1m  5/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 35ms/step - accuracy: 0.5489 - loss: 1.0417
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 17ms/step - accuracy: 0.7029 - loss: 0.5699 
[1m  8/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 17ms/step - accuracy: 0.6784 - loss: 0.6244
[36m(train_cnn_ray_tune pid=1127023)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m6s[0m 19ms/step - accuracy: 0.6329 - loss: 0.8328 - val_accuracy: 0.6447 - val_loss: 0.6844[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127023)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 53ms/step - accuracy: 0.6562 - loss: 0.8914[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 231ms/step
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m61/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 16ms/step - accuracy: 0.4310 - loss: 1.4428
[1m66/78[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 16ms/step - accuracy: 0.4312 - loss: 1.4423[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 13ms/step - accuracy: 0.6860 - loss: 0.7478
[1m273/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 13ms/step - accuracy: 0.6860 - loss: 0.7475[32m [repeated 282x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m 7/43[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step 
[1m13/43[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step 
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m10/78[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 20ms/step - accuracy: 0.6354 - loss: 0.8629[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=1127023)[0m 
[1m 75/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m3s[0m 15ms/step - accuracy: 0.6208 - loss: 0.8208[32m [repeated 120x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m19/43[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m27/43[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m34/43[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 8ms/step
[1m42/43[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 55ms/step - accuracy: 0.6406 - loss: 0.9237
[1m 4/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step - accuracy: 0.6291 - loss: 0.8854[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=1127031)[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=1127031)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 38ms/step
[1m 7/89[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step 
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m14/89[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m21/89[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m27/89[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m33/89[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m39/89[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m45/89[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m52/89[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m58/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 8ms/step
[1m65/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m71/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 8ms/step
[1m77/89[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1127031)[0m 
[1m83/89[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/step

Trial trial_af39f finished iteration 1 at 2025-11-04 12:04:37. Total running time: 2min 38s
[36m(train_cnn_ray_tune pid=1127031)[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=1127031)[0m   _log_deprecation_warning(
╭──────────────────────────────────────╮
│ Trial trial_af39f result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s              155.27 │
│ time_total_s                  155.27 │
│ training_iteration                 1 │
│ val_accuracy                 0.73139 │
╰──────────────────────────────────────╯

Trial trial_af39f completed after 1 iterations at 2025-11-04 12:04:37. Total running time: 2min 38s
[36m(train_cnn_ray_tune pid=1127032)[0m Epoch 24/137[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 26ms/step - accuracy: 0.6085 - loss: 0.8749 - val_accuracy: 0.6615 - val_loss: 0.7045[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m 26/155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m3s[0m 24ms/step - accuracy: 0.5718 - loss: 1.0187
[1m 28/155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m3s[0m 25ms/step - accuracy: 0.5712 - loss: 1.0204
[1m 30/155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m3s[0m 25ms/step - accuracy: 0.5709 - loss: 1.0216[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m  3/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 31ms/step - accuracy: 0.5477 - loss: 1.1556 
[1m  5/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 28ms/step - accuracy: 0.5447 - loss: 1.1283[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127023)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m5s[0m 16ms/step - accuracy: 0.6271 - loss: 0.8340 - val_accuracy: 0.7012 - val_loss: 0.6841[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127023)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 267ms/step
[36m(train_cnn_ray_tune pid=1127023)[0m 
[1m 9/43[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step   
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  7/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5113 - loss: 1.1210 
[1m 12/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step - accuracy: 0.5161 - loss: 1.1139
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 47ms/step - accuracy: 0.4844 - loss: 1.1885[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127023)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 37ms/step
[1m 9/89[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step 
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m61/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 19ms/step - accuracy: 0.4740 - loss: 1.1828
[1m64/78[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 19ms/step - accuracy: 0.4742 - loss: 1.1827
[1m67/78[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 19ms/step - accuracy: 0.4744 - loss: 1.1826
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m71/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 18ms/step - accuracy: 0.6485 - loss: 0.8041
[1m74/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 18ms/step - accuracy: 0.6484 - loss: 0.8042[32m [repeated 108x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 83/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m3s[0m 15ms/step - accuracy: 0.3859 - loss: 1.4570
[1m 87/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m3s[0m 15ms/step - accuracy: 0.3857 - loss: 1.4570[32m [repeated 246x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m17/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 15ms/step - accuracy: 0.4285 - loss: 1.3725[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 54/155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step - accuracy: 0.5069 - loss: 1.1217[32m [repeated 83x across cluster][0m
[36m(train_cnn_ray_tune pid=1127023)[0m 
[1m43/89[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[1m51/89[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 7ms/step[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 13ms/step - accuracy: 0.7415 - loss: 0.6622 

Trial trial_af39f finished iteration 1 at 2025-11-04 12:04:41. Total running time: 2min 42s
╭──────────────────────────────────────╮
│ Trial trial_af39f result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             159.585 │
│ time_total_s                 159.585 │
│ training_iteration                 1 │
│ val_accuracy                 0.70119 │
╰──────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1127032)[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=1127032)[0m   _log_deprecation_warning([32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 68ms/step - accuracy: 0.5703 - loss: 0.8907
[1m 4/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 21ms/step - accuracy: 0.5866 - loss: 0.8693[32m [repeated 10x across cluster][0m

Trial trial_af39f completed after 1 iterations at 2025-11-04 12:04:41. Total running time: 2min 42s
[36m(train_cnn_ray_tune pid=1127025)[0m Epoch 49/124[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 21ms/step - accuracy: 0.4806 - loss: 1.1555 - val_accuracy: 0.5945 - val_loss: 0.8464[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 11ms/step - accuracy: 0.7016 - loss: 0.7161
[1m 66/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 11ms/step - accuracy: 0.7012 - loss: 0.7157
[1m 71/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 11ms/step - accuracy: 0.7008 - loss: 0.7159[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 16ms/step - accuracy: 0.4707 - loss: 1.1408 
[1m  9/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 15ms/step - accuracy: 0.4587 - loss: 1.1553
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.6835 - loss: 0.6882 
[1m 11/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.6657 - loss: 0.7139
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m6s[0m 18ms/step - accuracy: 0.4955 - loss: 1.2055 - val_accuracy: 0.5699 - val_loss: 0.9385[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 12/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step - accuracy: 0.5168 - loss: 1.0946
[1m 17/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step - accuracy: 0.5198 - loss: 1.0886
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 190ms/step
[1m11/43[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step  
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 57ms/step - accuracy: 0.4688 - loss: 1.2149[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m61/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 17ms/step - accuracy: 0.4845 - loss: 1.1742
[1m65/78[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 17ms/step - accuracy: 0.4845 - loss: 1.1736[32m [repeated 97x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m100/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m2s[0m 13ms/step - accuracy: 0.3668 - loss: 1.4887
[1m104/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m2s[0m 13ms/step - accuracy: 0.3674 - loss: 1.4875[32m [repeated 230x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 17ms/step - accuracy: 0.6477 - loss: 0.7942[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m110/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 11ms/step - accuracy: 0.5155 - loss: 1.0948[32m [repeated 87x across cluster][0m
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/step[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 32ms/step
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m12/89[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step 
[1m26/89[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 61ms/step - accuracy: 0.4297 - loss: 1.3919
[1m 6/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step - accuracy: 0.4140 - loss: 1.3868[32m [repeated 10x across cluster][0m

Trial trial_af39f finished iteration 1 at 2025-11-04 12:04:46. Total running time: 2min 47s
╭──────────────────────────────────────╮
│ Trial trial_af39f result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             164.664 │
│ time_total_s                 164.664 │
│ training_iteration                 1 │
│ val_accuracy                 0.69206 │
╰──────────────────────────────────────╯

Trial trial_af39f completed after 1 iterations at 2025-11-04 12:04:46. Total running time: 2min 47s
[36m(train_cnn_ray_tune pid=1127029)[0m Epoch 49/131[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 24ms/step - accuracy: 0.6217 - loss: 0.8481 - val_accuracy: 0.6749 - val_loss: 0.6727[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m279/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step - accuracy: 0.3806 - loss: 1.4611
[1m284/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step - accuracy: 0.3807 - loss: 1.4608
[1m289/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step - accuracy: 0.3809 - loss: 1.4605[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  7/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5313 - loss: 1.0639 
[1m 12/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step - accuracy: 0.5246 - loss: 1.0838
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 13ms/step - accuracy: 0.5468 - loss: 0.8281 
[1m 10/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.6003 - loss: 0.8103[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 13ms/step - accuracy: 0.4704 - loss: 1.2852 
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m4s[0m 24ms/step - accuracy: 0.5739 - loss: 1.0066 - val_accuracy: 0.6454 - val_loss: 0.7381[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 63ms/step - accuracy: 0.6875 - loss: 0.6959[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  7/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5087 - loss: 1.0773 
[1m 13/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step - accuracy: 0.5074 - loss: 1.0805
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m 5/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step - accuracy: 0.6729 - loss: 0.7323
[1m 9/78[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step - accuracy: 0.6676 - loss: 0.7455[32m [repeated 108x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m156/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 12ms/step - accuracy: 0.4003 - loss: 1.4142
[1m161/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 12ms/step - accuracy: 0.4002 - loss: 1.4144[32m [repeated 218x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m55/78[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 20ms/step - accuracy: 0.6352 - loss: 0.8380[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 28/155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step - accuracy: 0.5056 - loss: 1.0872[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=1127032)[0m 
[1m82/89[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 5ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 6ms/step[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 59ms/step - accuracy: 0.4922 - loss: 1.1552
[1m 5/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step - accuracy: 0.4917 - loss: 1.1421[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m Epoch 65/78[32m [repeated 23x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 19ms/step - accuracy: 0.4853 - loss: 1.1426 - val_accuracy: 0.5983 - val_loss: 0.8366[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.2677 - loss: 1.6245 
[1m 11/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.3082 - loss: 1.5616[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m4s[0m 14ms/step - accuracy: 0.5261 - loss: 1.0452 - val_accuracy: 0.6138 - val_loss: 0.8296[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 57ms/step - accuracy: 0.6172 - loss: 0.9526[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 9/78[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step - accuracy: 0.5116 - loss: 1.0928
[1m12/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step - accuracy: 0.5138 - loss: 1.0961[32m [repeated 106x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m3s[0m 14ms/step - accuracy: 0.4950 - loss: 1.1781
[1m 88/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m3s[0m 14ms/step - accuracy: 0.4956 - loss: 1.1778[32m [repeated 228x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m35/78[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 17ms/step - accuracy: 0.6629 - loss: 0.7877[32m [repeated 42x across cluster][0m
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m245/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 12ms/step - accuracy: 0.6732 - loss: 0.7469[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 60ms/step - accuracy: 0.4609 - loss: 1.1704
[1m 5/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step - accuracy: 0.5014 - loss: 1.0965[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m284/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step - accuracy: 0.3913 - loss: 1.4187
[1m288/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step - accuracy: 0.3914 - loss: 1.4185
[1m292/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step - accuracy: 0.3915 - loss: 1.4183
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  7/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.4834 - loss: 1.0483 
[1m 13/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5000 - loss: 1.0431
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 19/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5018 - loss: 1.0469
[1m 26/155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5022 - loss: 1.0492
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 32/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5037 - loss: 1.0535
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5043 - loss: 1.0576
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 44/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5046 - loss: 1.0613
[1m 51/155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5052 - loss: 1.0642
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 58/155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5064 - loss: 1.0657
[1m 63/155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5070 - loss: 1.0664
[36m(train_cnn_ray_tune pid=1127011)[0m Epoch 69/132[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 69/155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5077 - loss: 1.0671
[1m 74/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5083 - loss: 1.0676
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5087 - loss: 1.0681
[1m 85/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5091 - loss: 1.0684
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 91/155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5095 - loss: 1.0687
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.6852 - loss: 0.9510 
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 97/155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5099 - loss: 1.0691
[1m102/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5102 - loss: 1.0693
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m107/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5105 - loss: 1.0693
[1m112/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5108 - loss: 1.0694
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5110 - loss: 1.0696
[1m122/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5112 - loss: 1.0698
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m128/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5115 - loss: 1.0698
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m133/155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5117 - loss: 1.0697
[1m138/155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5119 - loss: 1.0698
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 15ms/step - accuracy: 0.4475 - loss: 1.3410 - val_accuracy: 0.5653 - val_loss: 0.9548[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 19/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5371 - loss: 1.0801
[1m 25/155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5326 - loss: 1.0775
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 31/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5308 - loss: 1.0756
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5292 - loss: 1.0751
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 44/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5284 - loss: 1.0740
[1m 50/155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5282 - loss: 1.0735
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 55/155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5282 - loss: 1.0730
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 60/155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5285 - loss: 1.0722
[1m 66/155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5286 - loss: 1.0714

Trial status: 9 TERMINATED | 11 RUNNING
Current time: 2025-11-04 12:04:59. Total running time: 3min 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     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_af39f    RUNNING              3   adam            relu                                   32                 32                  5          8.9631e-05          60                                              │
│ trial_af39f    RUNNING              2   adam            tanh                                  128                 32                  5          2.05278e-05        115                                              │
│ trial_af39f    RUNNING              2   adam            tanh                                  128                 64                  5          0.000263082         78                                              │
│ trial_af39f    RUNNING              3   adam            relu                                  128                 64                  3          0.000113647        124                                              │
│ trial_af39f    RUNNING              3   adam            relu                                   32                 32                  5          0.000608101         70                                              │
│ trial_af39f    RUNNING              3   adam            relu                                   32                 32                  5          2.34078e-05        139                                              │
│ trial_af39f    RUNNING              3   adam            tanh                                   32                 64                  5          6.10182e-05         70                                              │
│ trial_af39f    RUNNING              3   rmsprop         relu                                  128                 32                  5          4.00548e-05        132                                              │
│ trial_af39f    RUNNING              4   adam            tanh                                   64                 64                  3          0.000170953         52                                              │
│ trial_af39f    RUNNING              3   rmsprop         relu                                   64                128                  5          5.18891e-05        146                                              │
│ trial_af39f    RUNNING              2   rmsprop         relu                                   64                 32                  3          4.34693e-05        131                                              │
│ trial_af39f    TERMINATED           2   rmsprop         tanh                                  128                 32                  5          0.000531671         89        1           150.309          0.658708 │
│ trial_af39f    TERMINATED           3   rmsprop         tanh                                   32                 32                  3          0.00135267          51        1           159.585          0.701194 │
│ trial_af39f    TERMINATED           3   rmsprop         tanh                                   32                 64                  3          4.80349e-05         99        1            76.5749         0.485604 │
│ trial_af39f    TERMINATED           2   rmsprop         tanh                                   32                 64                  3          0.00160542         137        1           164.664          0.692065 │
│ trial_af39f    TERMINATED           4   adam            tanh                                   64                 32                  3          2.56847e-05         93        1            93.8861         0.474017 │
│ trial_af39f    TERMINATED           2   rmsprop         relu                                   64                128                  3          0.00143439          82        1            80.4604         0.737008 │
│ trial_af39f    TERMINATED           3   rmsprop         relu                                   32                128                  5          0.000409376         53        1           155.27           0.73139  │
│ trial_af39f    TERMINATED           3   rmsprop         tanh                                   32                 64                  3          3.42484e-05        134        1            74.9586         0.474719 │
│ trial_af39f    TERMINATED           4   adam            relu                                   64                 32                  3          0.0028724           66        1           141.32           0.686447 │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 71/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5284 - loss: 1.0710
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5283 - loss: 1.0709
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5281 - loss: 1.0710
[1m 87/155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5279 - loss: 1.0711
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.4123 - loss: 1.1815 
[1m 10/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.4405 - loss: 1.1292
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m48/78[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 16ms/step - accuracy: 0.4918 - loss: 1.1147
[1m51/78[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 16ms/step - accuracy: 0.4921 - loss: 1.1147
[1m54/78[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 16ms/step - accuracy: 0.4923 - loss: 1.1148
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m5s[0m 16ms/step - accuracy: 0.5021 - loss: 1.1674 - val_accuracy: 0.5832 - val_loss: 0.9200[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 61ms/step - accuracy: 0.4922 - loss: 1.0549[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 25/155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5124 - loss: 1.0990
[1m 31/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5120 - loss: 1.0973
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m49/78[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 12ms/step - accuracy: 0.4424 - loss: 1.3678
[1m53/78[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 12ms/step - accuracy: 0.4422 - loss: 1.3683[32m [repeated 109x across cluster][0m
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m294/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step - accuracy: 0.6681 - loss: 0.7511
[1m298/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step - accuracy: 0.6681 - loss: 0.7509[32m [repeated 190x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 36/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5124 - loss: 1.0951
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step - accuracy: 0.5131 - loss: 1.0932
[1m 46/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step - accuracy: 0.5137 - loss: 1.0915
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m62/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 16ms/step - accuracy: 0.6656 - loss: 0.7610[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m156/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 12ms/step - accuracy: 0.5239 - loss: 1.0536[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m  4/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 24ms/step - accuracy: 0.6071 - loss: 0.9626 
[1m  7/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 23ms/step - accuracy: 0.5891 - loss: 0.9714
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 49ms/step - accuracy: 0.5000 - loss: 1.0064
[1m  7/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step - accuracy: 0.5042 - loss: 1.1070[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m 17/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 14ms/step - accuracy: 0.5549 - loss: 1.0555
[1m 21/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 14ms/step - accuracy: 0.5493 - loss: 1.0657
[1m 25/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 14ms/step - accuracy: 0.5452 - loss: 1.0729[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m Epoch 26/139[32m [repeated 23x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 20ms/step - accuracy: 0.6625 - loss: 0.7756 - val_accuracy: 0.6545 - val_loss: 0.6889[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m4s[0m 24ms/step - accuracy: 0.5935 - loss: 0.9367 - val_accuracy: 0.6587 - val_loss: 0.7092[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 64ms/step - accuracy: 0.3672 - loss: 1.3982[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m55/78[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 16ms/step - accuracy: 0.5094 - loss: 1.0827
[1m59/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 16ms/step - accuracy: 0.5092 - loss: 1.0839[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m108/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m2s[0m 13ms/step - accuracy: 0.5238 - loss: 1.1209
[1m112/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 13ms/step - accuracy: 0.5233 - loss: 1.1219[32m [repeated 211x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m76/78[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 16ms/step - accuracy: 0.6679 - loss: 0.7576[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m2s[0m 19ms/step - accuracy: 0.5472 - loss: 1.0550[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 13ms/step - accuracy: 0.5868 - loss: 0.9989 
[1m 10/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 13ms/step - accuracy: 0.5806 - loss: 1.0176[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 53ms/step - accuracy: 0.4375 - loss: 1.2627
[1m  7/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step - accuracy: 0.5016 - loss: 1.1330[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 8/78[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step - accuracy: 0.5035 - loss: 1.0743
[1m11/78[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step - accuracy: 0.5046 - loss: 1.0745
[1m14/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step - accuracy: 0.5051 - loss: 1.0754
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5228 - loss: 1.0610
[1m126/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5230 - loss: 1.0609
[1m131/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5232 - loss: 1.0608
[36m(train_cnn_ray_tune pid=1127004)[0m Epoch 93/115[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m 13/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.5606 - loss: 1.0120
[1m 19/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.5650 - loss: 1.0105
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m 24/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 10ms/step - accuracy: 0.5680 - loss: 1.0062
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 9/78[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step - accuracy: 0.4856 - loss: 1.1571
[1m13/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 14ms/step - accuracy: 0.4875 - loss: 1.1500
[1m17/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 14ms/step - accuracy: 0.4891 - loss: 1.1435
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 19ms/step - accuracy: 0.5020 - loss: 1.0911 - val_accuracy: 0.6053 - val_loss: 0.8335[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  7/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5035 - loss: 1.1520 
[1m 13/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step - accuracy: 0.5130 - loss: 1.1222
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 31/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5231 - loss: 1.0847 
[1m 36/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step - accuracy: 0.5243 - loss: 1.0798
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m5s[0m 16ms/step - accuracy: 0.5171 - loss: 1.1368 - val_accuracy: 0.5899 - val_loss: 0.9047[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.7103 - loss: 0.6741 
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 60ms/step - accuracy: 0.7188 - loss: 0.7594[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m30/78[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step - accuracy: 0.4580 - loss: 1.3331
[1m34/78[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 13ms/step - accuracy: 0.4581 - loss: 1.3316[32m [repeated 98x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 11/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.3916 - loss: 1.4358
[1m 16/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.3989 - loss: 1.4184[32m [repeated 214x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m53/78[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 19ms/step - accuracy: 0.6631 - loss: 0.7867[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m127/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 21ms/step - accuracy: 0.6158 - loss: 0.8875[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[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=1127020)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m  4/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.5771 - loss: 0.9433 
[1m  7/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.6012 - loss: 0.9064[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 63ms/step - accuracy: 0.6094 - loss: 0.8830
[1m 5/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step - accuracy: 0.5544 - loss: 0.9927[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m Epoch 78/78[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m239/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 13ms/step - accuracy: 0.5261 - loss: 1.1132
[1m243/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 13ms/step - accuracy: 0.5261 - loss: 1.1133
[1m247/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 13ms/step - accuracy: 0.5261 - loss: 1.1134
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 16ms/step - accuracy: 0.4512 - loss: 1.3374 - val_accuracy: 0.5639 - val_loss: 0.9464[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 171ms/step
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  7/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5437 - loss: 1.0190 
[1m 12/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5424 - loss: 1.0223
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m12/43[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step  
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m22/43[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 5ms/step
[1m34/43[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 17/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step - accuracy: 0.5399 - loss: 1.0249
[1m 22/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step - accuracy: 0.5399 - loss: 1.0256
[36m(train_cnn_ray_tune pid=1127020)[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=1127020)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 36ms/step
[1m12/89[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step 
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m4s[0m 14ms/step - accuracy: 0.6672 - loss: 0.7337 - val_accuracy: 0.6928 - val_loss: 0.6234[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m  5/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 15ms/step - accuracy: 0.7044 - loss: 0.7636 
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 69/155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5389 - loss: 1.0367
[1m 74/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5391 - loss: 1.0372
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m24/89[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m34/89[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step
[1m45/89[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m57/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 5ms/step
[1m70/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 98/155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5401 - loss: 1.0374 
[1m104/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5403 - loss: 1.0374

Trial trial_af39f finished iteration 1 at 2025-11-04 12:05:15. Total running time: 3min 16s
╭──────────────────────────────────────╮
│ Trial trial_af39f result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             193.726 │
│ time_total_s                 193.726 │
│ training_iteration                 1 │
│ val_accuracy                 0.65414 │
╰──────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1127020)[0m 
[1m86/89[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 4ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 5ms/step

Trial trial_af39f completed after 1 iterations at 2025-11-04 12:05:15. Total running time: 3min 16s
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m110/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5404 - loss: 1.0375
[1m116/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5405 - loss: 1.0375
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5406 - loss: 1.0375
[1m130/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5407 - loss: 1.0375
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m137/155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5407 - loss: 1.0375
[1m144/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.5407 - loss: 1.0374
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m12/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.4524 - loss: 1.3506
[1m17/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.4523 - loss: 1.3518
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m151/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.5406 - loss: 1.0373
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 56ms/step - accuracy: 0.7969 - loss: 0.5508[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m18/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step - accuracy: 0.5081 - loss: 1.0861
[1m22/78[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step - accuracy: 0.5078 - loss: 1.0873[32m [repeated 105x across cluster][0m
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m107/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m2s[0m 10ms/step - accuracy: 0.6831 - loss: 0.7092
[1m113/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 10ms/step - accuracy: 0.6819 - loss: 0.7105[32m [repeated 212x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 11ms/step - accuracy: 0.5406 - loss: 1.0373 - val_accuracy: 0.6338 - val_loss: 0.7937
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m 9/78[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step - accuracy: 0.6536 - loss: 0.8097[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m 23/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step - accuracy: 0.5333 - loss: 1.0430[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 10ms/step - accuracy: 0.3806 - loss: 1.3667 
[1m 11/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.3965 - loss: 1.3631[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 14/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5505 - loss: 1.0505
[1m 20/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5466 - loss: 1.0554
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 27/155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step - accuracy: 0.5445 - loss: 1.0547
[1m 33/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5432 - loss: 1.0556
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5417 - loss: 1.0571
[1m 45/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5411 - loss: 1.0579
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 51/155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5403 - loss: 1.0579
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 57/155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5399 - loss: 1.0568
[1m 63/155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5396 - loss: 1.0554
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 54ms/step - accuracy: 0.5938 - loss: 1.0366
[1m  8/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step - accuracy: 0.5609 - loss: 1.0352 [32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 69/155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5394 - loss: 1.0546
[1m 75/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5395 - loss: 1.0537
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5396 - loss: 1.0529
[1m 87/155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5399 - loss: 1.0520
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 94/155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5401 - loss: 1.0511
[1m100/155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5404 - loss: 1.0503
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m106/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5406 - loss: 1.0497
[1m112/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5408 - loss: 1.0490
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5409 - loss: 1.0483
[1m124/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5409 - loss: 1.0478
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m130/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5410 - loss: 1.0474
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m135/155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5410 - loss: 1.0470
[1m141/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.5412 - loss: 1.0465
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m147/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.5413 - loss: 1.0460
[1m153/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.5414 - loss: 1.0456
[36m(train_cnn_ray_tune pid=1127011)[0m Epoch 82/132[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m 33/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step - accuracy: 0.5374 - loss: 1.0383
[1m 36/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step - accuracy: 0.5383 - loss: 1.0383
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step - accuracy: 0.5391 - loss: 1.0382[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 11ms/step - accuracy: 0.5415 - loss: 1.0453 - val_accuracy: 0.6341 - val_loss: 0.7892
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 13/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5412 - loss: 1.0463
[1m 19/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5365 - loss: 1.0489
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 24/155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5347 - loss: 1.0505
[1m 30/155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5335 - loss: 1.0503
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5337 - loss: 1.0496
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 44/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5343 - loss: 1.0478
[1m 51/155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5350 - loss: 1.0463
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 59/155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5358 - loss: 1.0448
[1m 65/155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5366 - loss: 1.0432
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 20ms/step - accuracy: 0.6631 - loss: 0.7635 - val_accuracy: 0.6928 - val_loss: 0.6124[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 73/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5375 - loss: 1.0409
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5380 - loss: 1.0393
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 87/155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5382 - loss: 1.0381
[1m 94/155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5383 - loss: 1.0371
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m101/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5385 - loss: 1.0362
[1m108/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5387 - loss: 1.0353
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m  7/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.6638 - loss: 0.7884  
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m152/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 8ms/step - accuracy: 0.5402 - loss: 1.0323
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m140/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 8ms/step - accuracy: 0.5398 - loss: 1.0329
[1m146/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 8ms/step - accuracy: 0.5400 - loss: 1.0326[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 11ms/step - accuracy: 0.5403 - loss: 1.0322 - val_accuracy: 0.6345 - val_loss: 0.7845
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  7/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step - accuracy: 0.5382 - loss: 1.0456 
[1m 14/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step - accuracy: 0.5409 - loss: 1.0334
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 33/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5429 - loss: 1.0264
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 21ms/step - accuracy: 0.6366 - loss: 0.8339 - val_accuracy: 0.6675 - val_loss: 0.6765[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 99/155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5535 - loss: 1.0206
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 59ms/step - accuracy: 0.5312 - loss: 1.0444[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m150/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.5542 - loss: 1.0213
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m47/78[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 18ms/step - accuracy: 0.6694 - loss: 0.7673
[1m50/78[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 18ms/step - accuracy: 0.6693 - loss: 0.7671[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m223/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 11ms/step - accuracy: 0.6638 - loss: 0.7571
[1m228/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 11ms/step - accuracy: 0.6639 - loss: 0.7567[32m [repeated 189x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step - accuracy: 0.4695 - loss: 1.3060[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m 97/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m2s[0m 11ms/step - accuracy: 0.5225 - loss: 1.0585[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.5076 - loss: 1.0719 
[1m 11/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.5034 - loss: 1.0852[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 11ms/step - accuracy: 0.5542 - loss: 1.0212 - val_accuracy: 0.6373 - val_loss: 0.7810
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  7/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5783 - loss: 0.9719 
[1m 13/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5610 - loss: 0.9927
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 57ms/step - accuracy: 0.5781 - loss: 0.9948
[1m 5/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step - accuracy: 0.5455 - loss: 1.0404[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5356 - loss: 1.0235
[36m(train_cnn_ray_tune pid=1127011)[0m Epoch 86/132[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m264/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 10ms/step - accuracy: 0.4203 - loss: 1.3401
[1m269/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 10ms/step - accuracy: 0.4204 - loss: 1.3400
[1m274/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 10ms/step - accuracy: 0.4204 - loss: 1.3398[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step - accuracy: 0.5413 - loss: 1.0210
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 11ms/step - accuracy: 0.5414 - loss: 1.0210 - val_accuracy: 0.6359 - val_loss: 0.7845
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 19/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5662 - loss: 1.0279
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 19ms/step - accuracy: 0.6705 - loss: 0.7541 - val_accuracy: 0.6907 - val_loss: 0.6118[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m124/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5549 - loss: 1.0165
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m143/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.5544 - loss: 1.0168
[1m150/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.5543 - loss: 1.0169[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 11ms/step - accuracy: 0.5541 - loss: 1.0171 - val_accuracy: 0.6359 - val_loss: 0.7788
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 19ms/step - accuracy: 0.5534 - loss: 1.0350 - val_accuracy: 0.5871 - val_loss: 0.8668[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 69/155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5489 - loss: 1.0074
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m137/155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5507 - loss: 1.0108
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 66ms/step - accuracy: 0.7188 - loss: 0.7408[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m53/78[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 14ms/step - accuracy: 0.5290 - loss: 1.0616
[1m57/78[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 14ms/step - accuracy: 0.5287 - loss: 1.0612[32m [repeated 91x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m 22/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 18ms/step - accuracy: 0.6583 - loss: 0.8337
[1m 25/155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 18ms/step - accuracy: 0.6576 - loss: 0.8314[32m [repeated 195x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.5508 - loss: 1.0115
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m75/78[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 16ms/step - accuracy: 0.6720 - loss: 0.7504[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 16ms/step - accuracy: 0.5536 - loss: 1.0239[32m [repeated 42x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.6046 - loss: 0.9386 
[1m 11/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.5898 - loss: 0.9547
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 11ms/step - accuracy: 0.5508 - loss: 1.0115 - val_accuracy: 0.6401 - val_loss: 0.7819
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  7/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5828 - loss: 1.0152 
[1m 14/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step - accuracy: 0.5648 - loss: 1.0242
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 20/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step - accuracy: 0.5590 - loss: 1.0217
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 238ms/step
[36m(train_cnn_ray_tune pid=1127022)[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=1127022)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 49ms/step - accuracy: 0.5625 - loss: 1.0387
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 10ms/step - accuracy: 0.4445 - loss: 1.2547 [32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m12/43[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step  
[1m25/43[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m35/43[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m22/78[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 14ms/step - accuracy: 0.5325 - loss: 1.0358
[1m26/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step - accuracy: 0.5313 - loss: 1.0376
[1m30/78[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step - accuracy: 0.5308 - loss: 1.0388
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5534 - loss: 1.0174
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.5693 - loss: 1.1032 
[1m 11/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.5569 - loss: 1.1183
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 38ms/step
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m12/89[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step 
[1m24/89[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m36/89[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 4ms/step
[1m47/89[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 4ms/step
[1m59/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m133/155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5548 - loss: 1.0146
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m71/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 4ms/step
[1m83/89[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=1127033)[0m Epoch 39/52[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 11/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.4292 - loss: 1.2767
[1m 17/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 10ms/step - accuracy: 0.4217 - loss: 1.2873
[1m 22/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 10ms/step - accuracy: 0.4211 - loss: 1.2900[32m [repeated 5x across cluster][0m

Trial trial_af39f finished iteration 1 at 2025-11-04 12:05:28. Total running time: 3min 29s
╭──────────────────────────────────────╮
│ Trial trial_af39f result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             205.984 │
│ time_total_s                 205.984 │
│ training_iteration                 1 │
│ val_accuracy                  0.6868 │
╰──────────────────────────────────────╯

Trial trial_af39f completed after 1 iterations at 2025-11-04 12:05:28. Total running time: 3min 29s
[36m(train_cnn_ray_tune pid=1127022)[0m 
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m152/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 8ms/step - accuracy: 0.5552 - loss: 1.0142
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 11ms/step - accuracy: 0.5552 - loss: 1.0141 - val_accuracy: 0.6373 - val_loss: 0.7812
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  8/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5521 - loss: 1.0212 
[1m 15/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step - accuracy: 0.5495 - loss: 1.0240
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 16ms/step - accuracy: 0.5284 - loss: 1.0471 - val_accuracy: 0.6152 - val_loss: 0.8088[32m [repeated 12x across cluster][0m

Trial status: 11 TERMINATED | 9 RUNNING
Current time: 2025-11-04 12:05:29. Total running time: 3min 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     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_af39f    RUNNING              3   adam            relu                                   32                 32                  5          8.9631e-05          60                                              │
│ trial_af39f    RUNNING              2   adam            tanh                                  128                 32                  5          2.05278e-05        115                                              │
│ trial_af39f    RUNNING              3   adam            relu                                  128                 64                  3          0.000113647        124                                              │
│ trial_af39f    RUNNING              3   adam            relu                                   32                 32                  5          2.34078e-05        139                                              │
│ trial_af39f    RUNNING              3   adam            tanh                                   32                 64                  5          6.10182e-05         70                                              │
│ trial_af39f    RUNNING              3   rmsprop         relu                                  128                 32                  5          4.00548e-05        132                                              │
│ trial_af39f    RUNNING              4   adam            tanh                                   64                 64                  3          0.000170953         52                                              │
│ trial_af39f    RUNNING              3   rmsprop         relu                                   64                128                  5          5.18891e-05        146                                              │
│ trial_af39f    RUNNING              2   rmsprop         relu                                   64                 32                  3          4.34693e-05        131                                              │
│ trial_af39f    TERMINATED           2   rmsprop         tanh                                  128                 32                  5          0.000531671         89        1           150.309          0.658708 │
│ trial_af39f    TERMINATED           2   adam            tanh                                  128                 64                  5          0.000263082         78        1           193.726          0.654143 │
│ trial_af39f    TERMINATED           3   rmsprop         tanh                                   32                 32                  3          0.00135267          51        1           159.585          0.701194 │
│ trial_af39f    TERMINATED           3   adam            relu                                   32                 32                  5          0.000608101         70        1           205.984          0.686798 │
│ trial_af39f    TERMINATED           3   rmsprop         tanh                                   32                 64                  3          4.80349e-05         99        1            76.5749         0.485604 │
│ trial_af39f    TERMINATED           2   rmsprop         tanh                                   32                 64                  3          0.00160542         137        1           164.664          0.692065 │
│ trial_af39f    TERMINATED           4   adam            tanh                                   64                 32                  3          2.56847e-05         93        1            93.8861         0.474017 │
│ trial_af39f    TERMINATED           2   rmsprop         relu                                   64                128                  3          0.00143439          82        1            80.4604         0.737008 │
│ trial_af39f    TERMINATED           3   rmsprop         relu                                   32                128                  5          0.000409376         53        1           155.27           0.73139  │
│ trial_af39f    TERMINATED           3   rmsprop         tanh                                   32                 64                  3          3.42484e-05        134        1            74.9586         0.474719 │
│ trial_af39f    TERMINATED           4   adam            relu                                   64                 32                  3          0.0028724           66        1           141.32           0.686447 │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m195/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5764 - loss: 0.9847
[1m201/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.5766 - loss: 0.9846[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 10ms/step - accuracy: 0.5532 - loss: 1.0125 - val_accuracy: 0.6383 - val_loss: 0.7780
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m4s[0m 11ms/step - accuracy: 0.4238 - loss: 1.3177 - val_accuracy: 0.5576 - val_loss: 0.9184[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 50ms/step - accuracy: 0.5000 - loss: 0.8702[32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m21/78[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 14ms/step - accuracy: 0.6740 - loss: 0.7448
[1m25/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 14ms/step - accuracy: 0.6746 - loss: 0.7440[32m [repeated 78x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m151/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 16ms/step - accuracy: 0.6431 - loss: 0.8041
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.6431 - loss: 0.8041[32m [repeated 124x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m154/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 8ms/step - accuracy: 0.5576 - loss: 1.0010[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m13/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.4653 - loss: 1.3098 
[1m19/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.4648 - loss: 1.3094
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m28/78[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step - accuracy: 0.6557 - loss: 0.7768[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 10ms/step - accuracy: 0.5224 - loss: 1.0290[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m25/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.4648 - loss: 1.3094
[1m31/78[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.4652 - loss: 1.3082
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m37/78[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.4653 - loss: 1.3074
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m42/78[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.4652 - loss: 1.3069
[1m48/78[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.4649 - loss: 1.3062
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 10ms/step - accuracy: 0.5575 - loss: 1.0011 - val_accuracy: 0.6401 - val_loss: 0.7731[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m54/78[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.4644 - loss: 1.3057
[1m60/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.4641 - loss: 1.3050
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 71/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.4469 - loss: 1.2891 
[1m 78/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.4461 - loss: 1.2893[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m65/78[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.4639 - loss: 1.3042
[1m70/78[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step - accuracy: 0.4637 - loss: 1.3035
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 65ms/step - accuracy: 0.4844 - loss: 0.9617
[1m 5/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 14ms/step - accuracy: 0.5025 - loss: 1.0365[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m75/78[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step - accuracy: 0.4636 - loss: 1.3028
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m18/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step - accuracy: 0.5147 - loss: 1.0454
[1m22/78[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step - accuracy: 0.5157 - loss: 1.0478
[1m26/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step - accuracy: 0.5175 - loss: 1.0487
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m  6/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.5134 - loss: 0.9654 
[1m 11/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.5223 - loss: 0.9959[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m Epoch 78/124[32m [repeated 23x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 184ms/step
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m15/43[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step  
[1m29/43[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=1127004)[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=1127004)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 13ms/step - accuracy: 0.4702 - loss: 1.2784 - val_accuracy: 0.5758 - val_loss: 0.9327[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 32ms/step
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m16/89[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step 
[1m33/89[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m48/89[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 3ms/step
[1m66/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1127004)[0m 
[1m85/89[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 3ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step

Trial trial_af39f finished iteration 1 at 2025-11-04 12:05:34. Total running time: 3min 35s
╭──────────────────────────────────────╮
│ Trial trial_af39f result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             212.308 │
│ time_total_s                 212.308 │
│ training_iteration                 1 │
│ val_accuracy                 0.57584 │
╰──────────────────────────────────────╯

Trial trial_af39f completed after 1 iterations at 2025-11-04 12:05:34. Total running time: 3min 35s
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m140/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 8ms/step - accuracy: 0.4372 - loss: 1.3042
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 8ms/step - accuracy: 0.4368 - loss: 1.3042[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m4s[0m 12ms/step - accuracy: 0.5318 - loss: 1.0820 - val_accuracy: 0.6046 - val_loss: 0.8724[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m122/310[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step - accuracy: 0.5900 - loss: 0.9477
[1m128/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 8ms/step - accuracy: 0.5897 - loss: 0.9478
[1m134/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 8ms/step - accuracy: 0.5895 - loss: 0.9478
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 51ms/step - accuracy: 0.5469 - loss: 0.9722[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m72/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 11ms/step - accuracy: 0.5407 - loss: 1.0360
[1m77/78[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 11ms/step - accuracy: 0.5404 - loss: 1.0360[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m122/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 14ms/step - accuracy: 0.6503 - loss: 0.7766
[1m126/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 14ms/step - accuracy: 0.6503 - loss: 0.7770[32m [repeated 84x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step - accuracy: 0.4326 - loss: 1.2978[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m34/78[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 13ms/step - accuracy: 0.6784 - loss: 0.7395[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m 29/155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 13ms/step - accuracy: 0.5867 - loss: 0.9758[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  8/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 8ms/step - accuracy: 0.3773 - loss: 1.2363  
[1m 14/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.3920 - loss: 1.2366
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 10ms/step - accuracy: 0.4326 - loss: 1.2977 - val_accuracy: 0.5629 - val_loss: 0.9119[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  8/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step - accuracy: 0.5702 - loss: 0.9655 
[1m 16/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 7ms/step - accuracy: 0.5810 - loss: 0.9619[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[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=1127025)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 49ms/step - accuracy: 0.5078 - loss: 0.9834
[1m 6/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step - accuracy: 0.5099 - loss: 1.0386[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m Epoch 82/124[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 14ms/step - accuracy: 0.5297 - loss: 1.0415 - val_accuracy: 0.6197 - val_loss: 0.7905[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 220ms/step
[1m17/43[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step  
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m34/43[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 32ms/step
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m14/89[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step 
[1m30/89[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 47/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 7ms/step - accuracy: 0.4297 - loss: 1.2985
[1m 54/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 7ms/step - accuracy: 0.4309 - loss: 1.2939[32m [repeated 137x across cluster][0m
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m45/89[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 4ms/step
[1m61/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1127025)[0m 
[1m76/89[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 3ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step

Trial trial_af39f finished iteration 1 at 2025-11-04 12:05:40. Total running time: 3min 41s
╭──────────────────────────────────────╮
│ Trial trial_af39f result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             218.387 │
│ time_total_s                 218.387 │
│ training_iteration                 1 │
│ val_accuracy                 0.69558 │
╰──────────────────────────────────────╯

Trial trial_af39f completed after 1 iterations at 2025-11-04 12:05:40. Total running time: 3min 41s
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step - accuracy: 0.5746 - loss: 0.9963 - val_accuracy: 0.6057 - val_loss: 0.8289[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m12/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5448 - loss: 1.0215
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m36/78[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5439 - loss: 1.0224 
[1m42/78[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5440 - loss: 1.0218
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m48/78[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5440 - loss: 1.0212
[1m54/78[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5441 - loss: 1.0204
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m60/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5448 - loss: 1.0191
[1m66/78[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5453 - loss: 1.0185
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 51ms/step - accuracy: 0.5234 - loss: 1.0380[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m72/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.5455 - loss: 1.0180
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.5454 - loss: 1.0177
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m24/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5439 - loss: 1.0238
[1m30/78[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5443 - loss: 1.0223[32m [repeated 42x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m147/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step - accuracy: 0.6529 - loss: 0.7776
[1m152/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step - accuracy: 0.6528 - loss: 0.7777[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m108/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 7ms/step - accuracy: 0.5974 - loss: 0.9294[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m18/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5441 - loss: 1.0239[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m153/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step - accuracy: 0.5745 - loss: 0.9964[32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step - accuracy: 0.5454 - loss: 1.0177 - val_accuracy: 0.6257 - val_loss: 0.7845
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  9/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 7ms/step - accuracy: 0.4528 - loss: 1.2661  
[1m 18/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 6ms/step - accuracy: 0.4334 - loss: 1.3071[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 10ms/step - accuracy: 0.5420 - loss: 1.0622 - val_accuracy: 0.6088 - val_loss: 0.8597[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m15/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5506 - loss: 0.9904
[1m21/78[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5478 - loss: 0.9929
[1m27/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5469 - loss: 0.9940
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  9/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step - accuracy: 0.5492 - loss: 0.9815 
[1m 18/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step - accuracy: 0.5573 - loss: 0.9786
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m33/78[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5453 - loss: 0.9964
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m40/78[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5439 - loss: 0.9994
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 52ms/step - accuracy: 0.7656 - loss: 0.6220
[1m  6/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step - accuracy: 0.6804 - loss: 0.6925[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m46/78[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5432 - loss: 1.0011
[1m52/78[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5422 - loss: 1.0030
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m58/78[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5414 - loss: 1.0046
[1m64/78[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5408 - loss: 1.0058
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m71/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.5405 - loss: 1.0070
[1m77/78[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.5402 - loss: 1.0080
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 11ms/step - accuracy: 0.5402 - loss: 1.0083 - val_accuracy: 0.6268 - val_loss: 0.7812
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 10/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step - accuracy: 0.5656 - loss: 1.0241 
[1m 18/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step - accuracy: 0.5724 - loss: 1.0075
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 77/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 6ms/step - accuracy: 0.4291 - loss: 1.2813
[1m 84/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 7ms/step - accuracy: 0.4297 - loss: 1.2804
[1m 91/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 7ms/step - accuracy: 0.4303 - loss: 1.2794
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m13/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5487 - loss: 1.0093 
[1m19/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5463 - loss: 1.0136
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m25/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5452 - loss: 1.0149
[1m31/78[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5447 - loss: 1.0159
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m37/78[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5436 - loss: 1.0174
[1m43/78[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5425 - loss: 1.0193
[36m(train_cnn_ray_tune pid=1127005)[0m Epoch 37/60[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m49/78[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5416 - loss: 1.0200
[1m55/78[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5414 - loss: 1.0202
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m61/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5413 - loss: 1.0203
[1m67/78[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5413 - loss: 1.0202
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m73/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.5412 - loss: 1.0202
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step - accuracy: 0.5411 - loss: 1.0202 - val_accuracy: 0.6261 - val_loss: 0.7842
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 7/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5695 - loss: 0.9808 
[1m14/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5593 - loss: 0.9911
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m20/78[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5556 - loss: 0.9956
[1m26/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5521 - loss: 0.9980
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m32/78[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5505 - loss: 1.0001
[1m39/78[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5499 - loss: 1.0016
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step - accuracy: 0.5437 - loss: 1.0311 - val_accuracy: 0.6239 - val_loss: 0.7911[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m46/78[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5493 - loss: 1.0035
[1m53/78[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5488 - loss: 1.0048
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m59/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5484 - loss: 1.0061
[1m65/78[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5481 - loss: 1.0074
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m72/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 8ms/step - accuracy: 0.5478 - loss: 1.0085
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 11ms/step - accuracy: 0.5475 - loss: 1.0093 - val_accuracy: 0.6250 - val_loss: 0.7894
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 7/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5422 - loss: 0.9979 
[1m13/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5434 - loss: 1.0051
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m19/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5433 - loss: 1.0080
[1m25/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5419 - loss: 1.0105
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m31/78[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5404 - loss: 1.0129
[1m37/78[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5396 - loss: 1.0140
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m43/78[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5391 - loss: 1.0151
[1m49/78[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5389 - loss: 1.0162
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m267/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 7ms/step - accuracy: 0.6030 - loss: 0.9235
[1m274/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 7ms/step - accuracy: 0.6029 - loss: 0.9237[32m [repeated 130x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  9/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step - accuracy: 0.5741 - loss: 0.9659 
[1m 18/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step - accuracy: 0.5655 - loss: 0.9739
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m54/78[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5388 - loss: 1.0170
[1m60/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5389 - loss: 1.0176
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m66/78[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5389 - loss: 1.0181
[1m72/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.5389 - loss: 1.0186
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.5390 - loss: 1.0190
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 13ms/step - accuracy: 0.5741 - loss: 0.9915 - val_accuracy: 0.6081 - val_loss: 0.8126[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step - accuracy: 0.5390 - loss: 1.0190 - val_accuracy: 0.6250 - val_loss: 0.7899
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m13/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5559 - loss: 1.0139
[1m19/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5535 - loss: 1.0149
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m24/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5525 - loss: 1.0149
[1m30/78[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5510 - loss: 1.0145
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m35/78[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5499 - loss: 1.0137
[1m41/78[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5490 - loss: 1.0132 
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m47/78[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5485 - loss: 1.0128
[1m53/78[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5482 - loss: 1.0125
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m59/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5481 - loss: 1.0123
[1m66/78[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5478 - loss: 1.0122
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m73/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.5476 - loss: 1.0122
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 10/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step - accuracy: 0.5886 - loss: 0.9180 
[1m 19/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step - accuracy: 0.5898 - loss: 0.9318
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 11ms/step - accuracy: 0.5474 - loss: 1.0121 - val_accuracy: 0.6278 - val_loss: 0.7873
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 46ms/step - accuracy: 0.6328 - loss: 0.8668[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 7/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5767 - loss: 0.9454
[1m13/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5671 - loss: 0.9644 
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m 25/155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step - accuracy: 0.6884 - loss: 0.7225
[1m 30/155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step - accuracy: 0.6869 - loss: 0.7242[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 63/155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 6ms/step - accuracy: 0.5875 - loss: 0.9474[32m [repeated 23x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m19/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5625 - loss: 0.9720
[1m25/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5577 - loss: 0.9788
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 7/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5557 - loss: 1.0162 
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m152/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 11ms/step - accuracy: 0.5830 - loss: 0.9758[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m31/78[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5550 - loss: 0.9827
[1m37/78[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5529 - loss: 0.9861
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m  8/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 8ms/step - accuracy: 0.5285 - loss: 0.9835  
[1m 16/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 7ms/step - accuracy: 0.5503 - loss: 0.9546[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m43/78[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5513 - loss: 0.9888 
[1m49/78[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5499 - loss: 0.9914
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step - accuracy: 0.5678 - loss: 0.9771 - val_accuracy: 0.6517 - val_loss: 0.7506[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m55/78[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5491 - loss: 0.9929
[1m61/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5486 - loss: 0.9942
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m67/78[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5483 - loss: 0.9953
[1m73/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.5480 - loss: 0.9961
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 43ms/step - accuracy: 0.4688 - loss: 1.0874
[1m  8/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 8ms/step - accuracy: 0.5184 - loss: 1.0310  [32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 11ms/step - accuracy: 0.5478 - loss: 0.9968 - val_accuracy: 0.6285 - val_loss: 0.7762
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m13/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5575 - loss: 0.9898
[1m19/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5563 - loss: 0.9960
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m25/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5536 - loss: 1.0014
[1m31/78[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5523 - loss: 1.0053
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m37/78[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5515 - loss: 1.0073
[1m43/78[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5503 - loss: 1.0094
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 67/155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 6ms/step - accuracy: 0.5826 - loss: 0.9635
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 6ms/step - accuracy: 0.5823 - loss: 0.9629
[1m 84/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 6ms/step - accuracy: 0.5822 - loss: 0.9628
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m49/78[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5496 - loss: 1.0104
[1m55/78[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5492 - loss: 1.0108 
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m61/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5489 - loss: 1.0114
[1m67/78[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5485 - loss: 1.0122
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m74/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.5482 - loss: 1.0127
[36m(train_cnn_ray_tune pid=1127029)[0m Epoch 85/131[32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 11ms/step - accuracy: 0.5480 - loss: 1.0128 - val_accuracy: 0.6275 - val_loss: 0.7777
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 7/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5889 - loss: 0.9665 
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m13/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5772 - loss: 0.9834
[1m19/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5721 - loss: 0.9906
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m25/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5685 - loss: 0.9941
[1m31/78[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5656 - loss: 0.9974
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  9/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 7ms/step - accuracy: 0.5669 - loss: 0.9730 
[1m 18/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step - accuracy: 0.5648 - loss: 0.9806
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m37/78[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5633 - loss: 0.9997
[1m43/78[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5619 - loss: 1.0006
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m49/78[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5607 - loss: 1.0012
[1m55/78[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5595 - loss: 1.0018
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m61/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5586 - loss: 1.0021
[1m67/78[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5580 - loss: 1.0021
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m73/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.5574 - loss: 1.0019
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step - accuracy: 0.5569 - loss: 1.0020 - val_accuracy: 0.6296 - val_loss: 0.7820
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m13/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5251 - loss: 1.0191 
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m19/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5314 - loss: 1.0191
[1m25/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5354 - loss: 1.0186
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m31/78[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5381 - loss: 1.0180
[1m37/78[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5401 - loss: 1.0170
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m43/78[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5412 - loss: 1.0162
[1m49/78[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5421 - loss: 1.0153
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m56/78[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5428 - loss: 1.0141
[1m63/78[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5436 - loss: 1.0127
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  9/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step - accuracy: 0.6065 - loss: 0.9439 
[1m 18/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step - accuracy: 0.5940 - loss: 0.9567
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m69/78[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5443 - loss: 1.0117
[1m75/78[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.5450 - loss: 1.0106
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m258/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 7ms/step - accuracy: 0.5997 - loss: 0.9180
[1m268/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 7ms/step - accuracy: 0.5997 - loss: 0.9178[32m [repeated 131x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 11ms/step - accuracy: 0.5454 - loss: 1.0101 - val_accuracy: 0.6313 - val_loss: 0.7729
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m15/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5570 - loss: 1.0074
[1m22/78[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5561 - loss: 1.0041
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m29/78[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5530 - loss: 1.0061
[1m36/78[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5518 - loss: 1.0075
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 13ms/step - accuracy: 0.6831 - loss: 0.7392 - val_accuracy: 0.7047 - val_loss: 0.6093[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m42/78[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5507 - loss: 1.0092
[1m48/78[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5494 - loss: 1.0107
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m54/78[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5487 - loss: 1.0112
[1m60/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5485 - loss: 1.0113
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m66/78[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5484 - loss: 1.0113
[1m72/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 8ms/step - accuracy: 0.5487 - loss: 1.0108
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.5489 - loss: 1.0104
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 11ms/step - accuracy: 0.5490 - loss: 1.0103 - val_accuracy: 0.6299 - val_loss: 0.7589
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m13/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5225 - loss: 1.0116
[1m19/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5255 - loss: 1.0134
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m25/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5271 - loss: 1.0142
[1m31/78[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5270 - loss: 1.0151 
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m37/78[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5273 - loss: 1.0158
[1m43/78[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5278 - loss: 1.0166
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 45ms/step - accuracy: 0.6875 - loss: 0.8761[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m49/78[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5286 - loss: 1.0169
[1m55/78[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5297 - loss: 1.0161 
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m 91/155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 12ms/step - accuracy: 0.6691 - loss: 0.7433
[1m 96/155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 12ms/step - accuracy: 0.6691 - loss: 0.7431[32m [repeated 65x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m101/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 6ms/step - accuracy: 0.5763 - loss: 0.9623[32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m61/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5309 - loss: 1.0155
[1m67/78[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5319 - loss: 1.0150
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m154/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step - accuracy: 0.6831 - loss: 0.7391[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m73/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.5327 - loss: 1.0146
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m  8/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 7ms/step - accuracy: 0.6118 - loss: 1.0811  
[1m 15/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 7ms/step - accuracy: 0.5845 - loss: 1.0841[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step - accuracy: 0.5811 - loss: 0.9714 - val_accuracy: 0.6531 - val_loss: 0.7429[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step - accuracy: 0.5334 - loss: 1.0142 - val_accuracy: 0.6268 - val_loss: 0.7773
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 1/78[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 48ms/step - accuracy: 0.5703 - loss: 0.9843
[1m 7/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5527 - loss: 1.0033 [32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m14/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5558 - loss: 1.0074
[1m20/78[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5548 - loss: 1.0115
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 12/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step - accuracy: 0.5818 - loss: 0.9671 
[1m 22/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step - accuracy: 0.5818 - loss: 0.9634
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m27/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5529 - loss: 1.0146
[1m34/78[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5515 - loss: 1.0146
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m41/78[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5506 - loss: 1.0136
[1m48/78[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5498 - loss: 1.0125
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m54/78[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5492 - loss: 1.0113
[1m61/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5488 - loss: 1.0101
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m67/78[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5487 - loss: 1.0091
[1m73/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 8ms/step - accuracy: 0.5486 - loss: 1.0084
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m177/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 8ms/step - accuracy: 0.5663 - loss: 1.0379
[1m183/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5661 - loss: 1.0377
[1m190/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 8ms/step - accuracy: 0.5659 - loss: 1.0375
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 11ms/step - accuracy: 0.5487 - loss: 1.0078 - val_accuracy: 0.6331 - val_loss: 0.7731
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m13/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5505 - loss: 1.0015
[1m19/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5528 - loss: 1.0017
[36m(train_cnn_ray_tune pid=1127011)[0m Epoch 114/132[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m25/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5537 - loss: 1.0023
[1m31/78[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5540 - loss: 1.0035
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m134/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 6ms/step - accuracy: 0.4513 - loss: 1.2641
[1m141/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 6ms/step - accuracy: 0.4517 - loss: 1.2628
[1m149/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 6ms/step - accuracy: 0.4521 - loss: 1.2614
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m37/78[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5542 - loss: 1.0043
[1m43/78[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5541 - loss: 1.0048
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m49/78[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5538 - loss: 1.0053
[1m54/78[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5539 - loss: 1.0053
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m60/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5541 - loss: 1.0052
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m66/78[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5544 - loss: 1.0048
[1m72/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.5546 - loss: 1.0043
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.5548 - loss: 1.0038
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step - accuracy: 0.5549 - loss: 1.0037 - val_accuracy: 0.6331 - val_loss: 0.7710
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 7/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5880 - loss: 1.0186 
[1m13/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5765 - loss: 1.0204
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m19/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.5723 - loss: 1.0182
[1m25/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5707 - loss: 1.0163 
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m31/78[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5683 - loss: 1.0155
[1m37/78[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5669 - loss: 1.0131
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m43/78[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5657 - loss: 1.0113
[1m49/78[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5647 - loss: 1.0101
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m56/78[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5641 - loss: 1.0086
[1m63/78[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5636 - loss: 1.0069
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m70/78[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5633 - loss: 1.0053
[1m77/78[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.5631 - loss: 1.0039
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 12/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step - accuracy: 0.5738 - loss: 0.9609 
[1m 23/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step - accuracy: 0.5735 - loss: 0.9742
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 11ms/step - accuracy: 0.5630 - loss: 1.0035 - val_accuracy: 0.6352 - val_loss: 0.7658
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 7/78[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5378 - loss: 1.0003 
[1m13/78[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5408 - loss: 0.9920
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m19/78[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5430 - loss: 0.9894
[1m25/78[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5442 - loss: 0.9864
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m31/78[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5442 - loss: 0.9867
[1m37/78[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5445 - loss: 0.9885
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m264/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 7ms/step - accuracy: 0.6186 - loss: 0.8756
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 7ms/step - accuracy: 0.6184 - loss: 0.8761[32m [repeated 138x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m43/78[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5451 - loss: 0.9898
[1m49/78[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5456 - loss: 0.9908
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m55/78[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5459 - loss: 0.9917
[1m61/78[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5461 - loss: 0.9926
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m67/78[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step - accuracy: 0.5462 - loss: 0.9931
[1m73/78[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.5462 - loss: 0.9936
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 13ms/step - accuracy: 0.6757 - loss: 0.7185 - val_accuracy: 0.7107 - val_loss: 0.5983[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m78/78[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step - accuracy: 0.5462 - loss: 0.9942 - val_accuracy: 0.6313 - val_loss: 0.7648
[36m(train_cnn_ray_tune pid=1127011)[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=1127011)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 11/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step - accuracy: 0.6125 - loss: 0.9054 
[1m 21/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step - accuracy: 0.6006 - loss: 0.9313
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 210ms/step
[1m16/43[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step  
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m33/43[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 25ms/step
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m20/89[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step 
[1m39/89[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 43ms/step - accuracy: 0.6250 - loss: 0.9149[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m58/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 3ms/step
[1m79/89[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 3ms/step

Trial trial_af39f finished iteration 1 at 2025-11-04 12:05:56. Total running time: 3min 57s
╭──────────────────────────────────────╮
│ Trial trial_af39f result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             234.641 │
│ time_total_s                 234.641 │
│ training_iteration                 1 │
│ val_accuracy                 0.63132 │
╰──────────────────────────────────────╯

Trial trial_af39f completed after 1 iterations at 2025-11-04 12:05:56. Total running time: 3min 57s
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m 13/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step - accuracy: 0.6018 - loss: 0.9346
[1m 19/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step - accuracy: 0.6051 - loss: 0.9330[32m [repeated 60x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m 90/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 7ms/step - accuracy: 0.5686 - loss: 1.0231[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=1127011)[0m 
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m152/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 11ms/step - accuracy: 0.6840 - loss: 0.7184[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step - accuracy: 0.5886 - loss: 0.9421 - val_accuracy: 0.6591 - val_loss: 0.7297[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 44ms/step - accuracy: 0.3750 - loss: 1.3178
[1m  9/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 6ms/step - accuracy: 0.4154 - loss: 1.3097  [32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m 11/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 5ms/step - accuracy: 0.5805 - loss: 0.9478  
[1m 22/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 5ms/step - accuracy: 0.5906 - loss: 0.9212
[36m(train_cnn_ray_tune pid=1127005)[0m Epoch 43/60[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 35/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 6ms/step - accuracy: 0.4356 - loss: 1.2743
[1m 44/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 6ms/step - accuracy: 0.4353 - loss: 1.2695
[1m 52/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 6ms/step - accuracy: 0.4340 - loss: 1.2688[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 239ms/step
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m19/43[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 3ms/step   
[1m40/43[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 27ms/step
[1m18/89[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step 

Trial trial_af39f finished iteration 1 at 2025-11-04 12:05:59. Total running time: 4min 0s
[36m(train_cnn_ray_tune pid=1127033)[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=1127033)[0m   _log_deprecation_warning(
╭──────────────────────────────────────╮
│ Trial trial_af39f result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             237.334 │
│ time_total_s                 237.334 │
│ training_iteration                 1 │
│ val_accuracy                 0.62008 │
╰──────────────────────────────────────╯

Trial trial_af39f completed after 1 iterations at 2025-11-04 12:05:59. Total running time: 4min 0s

Trial status: 15 TERMINATED | 5 RUNNING
Current time: 2025-11-04 12:05:59. Total running time: 4min 0s
Logical resource usage: 5.0/20 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     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_af39f    RUNNING              3   adam            relu                                   32                 32                  5          8.9631e-05          60                                              │
│ trial_af39f    RUNNING              3   adam            relu                                   32                 32                  5          2.34078e-05        139                                              │
│ trial_af39f    RUNNING              3   adam            tanh                                   32                 64                  5          6.10182e-05         70                                              │
│ trial_af39f    RUNNING              3   rmsprop         relu                                   64                128                  5          5.18891e-05        146                                              │
│ trial_af39f    RUNNING              2   rmsprop         relu                                   64                 32                  3          4.34693e-05        131                                              │
│ trial_af39f    TERMINATED           2   rmsprop         tanh                                  128                 32                  5          0.000531671         89        1           150.309          0.658708 │
│ trial_af39f    TERMINATED           2   adam            tanh                                  128                 32                  5          2.05278e-05        115        1           212.308          0.575843 │
│ trial_af39f    TERMINATED           2   adam            tanh                                  128                 64                  5          0.000263082         78        1           193.726          0.654143 │
│ trial_af39f    TERMINATED           3   rmsprop         tanh                                   32                 32                  3          0.00135267          51        1           159.585          0.701194 │
│ trial_af39f    TERMINATED           3   adam            relu                                  128                 64                  3          0.000113647        124        1           218.387          0.695576 │
│ trial_af39f    TERMINATED           3   adam            relu                                   32                 32                  5          0.000608101         70        1           205.984          0.686798 │
│ trial_af39f    TERMINATED           3   rmsprop         tanh                                   32                 64                  3          4.80349e-05         99        1            76.5749         0.485604 │
│ trial_af39f    TERMINATED           3   rmsprop         relu                                  128                 32                  5          4.00548e-05        132        1           234.641          0.63132  │
│ trial_af39f    TERMINATED           2   rmsprop         tanh                                   32                 64                  3          0.00160542         137        1           164.664          0.692065 │
│ trial_af39f    TERMINATED           4   adam            tanh                                   64                 64                  3          0.000170953         52        1           237.334          0.620084 │
│ trial_af39f    TERMINATED           4   adam            tanh                                   64                 32                  3          2.56847e-05         93        1            93.8861         0.474017 │
│ trial_af39f    TERMINATED           2   rmsprop         relu                                   64                128                  3          0.00143439          82        1            80.4604         0.737008 │
│ trial_af39f    TERMINATED           3   rmsprop         relu                                   32                128                  5          0.000409376         53        1           155.27           0.73139  │
│ trial_af39f    TERMINATED           3   rmsprop         tanh                                   32                 64                  3          3.42484e-05        134        1            74.9586         0.474719 │
│ trial_af39f    TERMINATED           4   adam            relu                                   64                 32                  3          0.0028724           66        1           141.32           0.686447 │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 12/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step - accuracy: 0.5722 - loss: 0.9885 
[1m 23/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step - accuracy: 0.5829 - loss: 0.9716[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m 23/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 5ms/step - accuracy: 0.6160 - loss: 0.8635
[1m 34/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 5ms/step - accuracy: 0.6168 - loss: 0.8715[32m [repeated 147x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 11ms/step - accuracy: 0.6758 - loss: 0.7210 - val_accuracy: 0.7072 - val_loss: 0.6040[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127033)[0m 
[1m87/89[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 3ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 39ms/step - accuracy: 0.6562 - loss: 0.8277[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m145/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 10ms/step - accuracy: 0.6759 - loss: 0.7212
[1m151/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step - accuracy: 0.6758 - loss: 0.7211[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m309/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 5ms/step - accuracy: 0.6197 - loss: 0.8848[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m104/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 10ms/step - accuracy: 0.6762 - loss: 0.7209[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 6ms/step - accuracy: 0.6197 - loss: 0.8849 - val_accuracy: 0.6594 - val_loss: 0.7225[32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 37ms/step - accuracy: 0.6562 - loss: 0.8741
[1m 14/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step - accuracy: 0.6139 - loss: 0.9130 [32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 11/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 5ms/step - accuracy: 0.4925 - loss: 1.1102  
[1m 21/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 5ms/step - accuracy: 0.4937 - loss: 1.1264[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m Epoch 53/146[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 56/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 5ms/step - accuracy: 0.4934 - loss: 1.1445
[1m 67/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 5ms/step - accuracy: 0.4907 - loss: 1.1511
[1m 79/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 5ms/step - accuracy: 0.4886 - loss: 1.1564[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 12/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step - accuracy: 0.6165 - loss: 0.9195 
[1m 23/155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step - accuracy: 0.6020 - loss: 0.9405[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m287/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 5ms/step - accuracy: 0.6274 - loss: 0.8765
[1m297/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 5ms/step - accuracy: 0.6273 - loss: 0.8768[32m [repeated 163x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m 11/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 5ms/step - accuracy: 0.5917 - loss: 0.9590  
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 39ms/step - accuracy: 0.3750 - loss: 1.1970[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step - accuracy: 0.6910 - loss: 0.7025[32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 7ms/step - accuracy: 0.5750 - loss: 0.9968 - val_accuracy: 0.6117 - val_loss: 0.8271[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 39ms/step - accuracy: 0.5000 - loss: 1.2285
[1m 10/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 6ms/step - accuracy: 0.5377 - loss: 1.1649  [32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m 11/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 5ms/step - accuracy: 0.5798 - loss: 0.8861  
[1m 22/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 5ms/step - accuracy: 0.5887 - loss: 0.8839[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m Epoch 56/146[32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[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=1127012)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 79/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 5ms/step - accuracy: 0.4726 - loss: 1.2031
[1m 89/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 5ms/step - accuracy: 0.4720 - loss: 1.2010
[1m 99/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 5ms/step - accuracy: 0.4717 - loss: 1.1992
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m  7/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.7222 - loss: 0.6700 
[1m 13/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.7194 - loss: 0.6574[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m178/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 5ms/step - accuracy: 0.6095 - loss: 0.8790
[1m189/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 5ms/step - accuracy: 0.6101 - loss: 0.8775[32m [repeated 175x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m  8/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step - accuracy: 0.6695 - loss: 0.6824 
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 36ms/step - accuracy: 0.7031 - loss: 0.5702[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m147/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 4ms/step - accuracy: 0.6121 - loss: 0.8894[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 6ms/step - accuracy: 0.4761 - loss: 1.1728 - val_accuracy: 0.5913 - val_loss: 0.8506[32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 38ms/step - accuracy: 0.3750 - loss: 1.2846
[1m 11/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 5ms/step - accuracy: 0.3980 - loss: 1.2658  [32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m130/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 5ms/step - accuracy: 0.4600 - loss: 1.1799
[1m142/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 5ms/step - accuracy: 0.4612 - loss: 1.1791
[1m155/310[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 5ms/step - accuracy: 0.4624 - loss: 1.1785
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 172ms/step
[1m23/43[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step  
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 24ms/step
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m 10/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 6ms/step - accuracy: 0.6046 - loss: 0.9049  
[1m 19/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 6ms/step - accuracy: 0.6040 - loss: 0.9305[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m Epoch 46/70[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m21/89[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step 
[1m42/89[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m62/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1127012)[0m 
[1m85/89[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step

Trial trial_af39f finished iteration 1 at 2025-11-04 12:06:13. Total running time: 4min 14s
╭──────────────────────────────────────╮
│ Trial trial_af39f result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             251.697 │
│ time_total_s                 251.697 │
│ training_iteration                 1 │
│ val_accuracy                 0.72437 │
╰──────────────────────────────────────╯

Trial trial_af39f completed after 1 iterations at 2025-11-04 12:06:13. Total running time: 4min 14s
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 15/155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step - accuracy: 0.6407 - loss: 0.9364 
[1m 30/155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step - accuracy: 0.6278 - loss: 0.9295[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[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=1127029)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m195/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 4ms/step - accuracy: 0.6478 - loss: 0.8387
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 4ms/step - accuracy: 0.6480 - loss: 0.8384[32m [repeated 146x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.3750 - loss: 1.2737[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m300/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 4ms/step - accuracy: 0.6469 - loss: 0.8399[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step - accuracy: 0.6127 - loss: 0.8806 - val_accuracy: 0.6713 - val_loss: 0.6906[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.6250 - loss: 0.7499
[1m 12/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 5ms/step - accuracy: 0.5899 - loss: 0.9109 [32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m 14/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 4ms/step - accuracy: 0.6429 - loss: 0.8603 
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m181/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 5ms/step - accuracy: 0.5797 - loss: 0.9801
[1m192/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 5ms/step - accuracy: 0.5802 - loss: 0.9795
[1m203/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 5ms/step - accuracy: 0.5806 - loss: 0.9789
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m 14/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 4ms/step - accuracy: 0.6759 - loss: 0.8214  
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 4ms/step - accuracy: 0.6686 - loss: 0.8239
[36m(train_cnn_ray_tune pid=1127028)[0m Epoch 49/70[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 14/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 4ms/step - accuracy: 0.4810 - loss: 1.1534 
[1m 27/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 4ms/step - accuracy: 0.4977 - loss: 1.1261[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m194/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 4ms/step - accuracy: 0.5043 - loss: 1.1238
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 4ms/step - accuracy: 0.5039 - loss: 1.1245[32m [repeated 130x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.6250 - loss: 0.8716[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m306/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 5ms/step - accuracy: 0.5806 - loss: 0.9670[32m [repeated 23x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 118ms/step
[1m40/43[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step  
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 5ms/step - accuracy: 0.5807 - loss: 0.9670 - val_accuracy: 0.6131 - val_loss: 0.7935[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 22ms/step
[1m39/89[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 

Trial trial_af39f finished iteration 1 at 2025-11-04 12:06:22. Total running time: 4min 23s
╭──────────────────────────────────────╮
│ Trial trial_af39f result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             260.493 │
│ time_total_s                 260.493 │
│ training_iteration                 1 │
│ val_accuracy                 0.66713 │
╰──────────────────────────────────────╯

Trial trial_af39f completed after 1 iterations at 2025-11-04 12:06:22. Total running time: 4min 23s
[36m(train_cnn_ray_tune pid=1127029)[0m 
[1m80/89[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.7188 - loss: 0.6494
[1m 14/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 4ms/step - accuracy: 0.6811 - loss: 0.7688 [32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m Epoch 52/70[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[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=1127005)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 16/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 3ms/step - accuracy: 0.5157 - loss: 1.1198 
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5025 - loss: 1.1324[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m277/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 3ms/step - accuracy: 0.6543 - loss: 0.7830
[1m292/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 3ms/step - accuracy: 0.6544 - loss: 0.7841[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.5938 - loss: 0.9794[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m307/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 4ms/step - accuracy: 0.5907 - loss: 0.9463[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 155ms/step
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step - accuracy: 0.6579 - loss: 0.7885 - val_accuracy: 0.6777 - val_loss: 0.6615[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m36/43[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step  
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.4688 - loss: 1.1252
[1m 16/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.4609 - loss: 1.1663 [32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 21ms/step
[36m(train_cnn_ray_tune pid=1127005)[0m 
[1m36/89[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m72/89[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step

Trial trial_af39f finished iteration 1 at 2025-11-04 12:06:27. Total running time: 4min 28s
╭──────────────────────────────────────╮
│ Trial trial_af39f result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s              265.77 │
│ time_total_s                  265.77 │
│ training_iteration                 1 │
│ val_accuracy                 0.67767 │
╰──────────────────────────────────────╯

Trial trial_af39f completed after 1 iterations at 2025-11-04 12:06:27. Total running time: 4min 28s
[36m(train_cnn_ray_tune pid=1127028)[0m Epoch 55/70[32m [repeated 9x across cluster][0m

Trial status: 18 TERMINATED | 2 RUNNING
Current time: 2025-11-04 12:06:29. Total running time: 4min 30s
Logical resource usage: 2.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status         N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_af39f    RUNNING              3   adam            relu                                   32                 32                  5          2.34078e-05        139                                              │
│ trial_af39f    RUNNING              3   adam            tanh                                   32                 64                  5          6.10182e-05         70                                              │
│ trial_af39f    TERMINATED           2   rmsprop         tanh                                  128                 32                  5          0.000531671         89        1           150.309          0.658708 │
│ trial_af39f    TERMINATED           3   adam            relu                                   32                 32                  5          8.9631e-05          60        1           265.77           0.677669 │
│ trial_af39f    TERMINATED           2   adam            tanh                                  128                 32                  5          2.05278e-05        115        1           212.308          0.575843 │
│ trial_af39f    TERMINATED           2   adam            tanh                                  128                 64                  5          0.000263082         78        1           193.726          0.654143 │
│ trial_af39f    TERMINATED           3   rmsprop         tanh                                   32                 32                  3          0.00135267          51        1           159.585          0.701194 │
│ trial_af39f    TERMINATED           3   adam            relu                                  128                 64                  3          0.000113647        124        1           218.387          0.695576 │
│ trial_af39f    TERMINATED           3   adam            relu                                   32                 32                  5          0.000608101         70        1           205.984          0.686798 │
│ trial_af39f    TERMINATED           3   rmsprop         tanh                                   32                 64                  3          4.80349e-05         99        1            76.5749         0.485604 │
│ trial_af39f    TERMINATED           3   rmsprop         relu                                  128                 32                  5          4.00548e-05        132        1           234.641          0.63132  │
│ trial_af39f    TERMINATED           2   rmsprop         tanh                                   32                 64                  3          0.00160542         137        1           164.664          0.692065 │
│ trial_af39f    TERMINATED           4   adam            tanh                                   64                 64                  3          0.000170953         52        1           237.334          0.620084 │
│ trial_af39f    TERMINATED           3   rmsprop         relu                                   64                128                  5          5.18891e-05        146        1           251.697          0.724368 │
│ trial_af39f    TERMINATED           4   adam            tanh                                   64                 32                  3          2.56847e-05         93        1            93.8861         0.474017 │
│ trial_af39f    TERMINATED           2   rmsprop         relu                                   64                128                  3          0.00143439          82        1            80.4604         0.737008 │
│ trial_af39f    TERMINATED           3   rmsprop         relu                                   32                128                  5          0.000409376         53        1           155.27           0.73139  │
│ trial_af39f    TERMINATED           3   rmsprop         tanh                                   32                 64                  3          3.42484e-05        134        1            74.9586         0.474719 │
│ trial_af39f    TERMINATED           2   rmsprop         relu                                   64                 32                  3          4.34693e-05        131        1           260.493          0.667135 │
│ trial_af39f    TERMINATED           4   adam            relu                                   64                 32                  3          0.0028724           66        1           141.32           0.686447 │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m 15/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 4ms/step - accuracy: 0.6081 - loss: 0.8942 
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 4ms/step - accuracy: 0.6048 - loss: 0.9066[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5061 - loss: 1.1093
[1m224/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5058 - loss: 1.1088[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 27ms/step - accuracy: 0.6250 - loss: 1.0312[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m300/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 4ms/step - accuracy: 0.5925 - loss: 0.9396[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step - accuracy: 0.4917 - loss: 1.1126 - val_accuracy: 0.6096 - val_loss: 0.8151[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 26ms/step - accuracy: 0.5938 - loss: 0.8506
[1m 18/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5041 - loss: 1.0665 [32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m Epoch 67/139[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m 15/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 4ms/step - accuracy: 0.6325 - loss: 0.9180 
[1m 30/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step - accuracy: 0.6310 - loss: 0.9189[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m228/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 4ms/step - accuracy: 0.6026 - loss: 0.9247
[1m243/310[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 4ms/step - accuracy: 0.6026 - loss: 0.9244[32m [repeated 70x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.6250 - loss: 0.9878
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m258/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 4ms/step - accuracy: 0.5936 - loss: 0.9185[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step - accuracy: 0.5956 - loss: 0.9180 - val_accuracy: 0.6204 - val_loss: 0.7744[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 27ms/step - accuracy: 0.6562 - loss: 0.8669
[1m 15/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 4ms/step - accuracy: 0.6270 - loss: 0.9631 [32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m Epoch 71/139[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.6562 - loss: 0.8482
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 69/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5108 - loss: 1.0728
[1m 86/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5119 - loss: 1.0715
[1m103/310[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5121 - loss: 1.0708
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.5938 - loss: 1.1037
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m 15/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 4ms/step - accuracy: 0.6155 - loss: 0.8877 
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 4ms/step - accuracy: 0.6123 - loss: 0.9092
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m 16/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 4ms/step - accuracy: 0.6074 - loss: 0.9612 
[1m 31/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.6080 - loss: 0.9526
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m130/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 4ms/step - accuracy: 0.6176 - loss: 0.9112
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 4ms/step - accuracy: 0.6179 - loss: 0.9101[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m 71/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step - accuracy: 0.6162 - loss: 0.8548[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step - accuracy: 0.6175 - loss: 0.9049 - val_accuracy: 0.6187 - val_loss: 0.7676[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 26ms/step - accuracy: 0.6250 - loss: 0.9653
[1m 18/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5212 - loss: 1.0678 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m Epoch 66/70[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.4062 - loss: 1.1743[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 18/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.6048 - loss: 1.0335 
[1m 35/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5857 - loss: 1.0368[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[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=1127028)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m 29/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 4ms/step - accuracy: 0.5668 - loss: 0.9352
[1m 43/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step - accuracy: 0.5830 - loss: 0.9264[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m296/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 3ms/step - accuracy: 0.5439 - loss: 1.0471[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step - accuracy: 0.5317 - loss: 1.0433 - val_accuracy: 0.6303 - val_loss: 0.7890[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 27ms/step - accuracy: 0.5938 - loss: 0.8712
[1m 15/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 4ms/step - accuracy: 0.6496 - loss: 0.8110 [32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m Epoch 80/139[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 26ms/step - accuracy: 0.5000 - loss: 1.0106[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 136ms/step
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m35/43[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step  
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 18ms/step
[1m35/89[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[36m(train_cnn_ray_tune pid=1127028)[0m 
[1m70/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step

Trial trial_af39f finished iteration 1 at 2025-11-04 12:06:50. Total running time: 4min 51s
╭──────────────────────────────────────╮
│ Trial trial_af39f result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s               288.4 │
│ time_total_s                   288.4 │
│ training_iteration                 1 │
│ val_accuracy                 0.62886 │
╰──────────────────────────────────────╯

Trial trial_af39f completed after 1 iterations at 2025-11-04 12:06:50. Total running time: 4min 51s
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 18/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5496 - loss: 1.0069 
[1m 36/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5471 - loss: 1.0283[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5408 - loss: 1.0087
[1m 81/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5394 - loss: 1.0108[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 81/310[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5253 - loss: 1.0540[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 3ms/step - accuracy: 0.5309 - loss: 1.0449 - val_accuracy: 0.6352 - val_loss: 0.7809[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 19ms/step - accuracy: 0.6250 - loss: 1.0341
[1m 21/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5772 - loss: 1.0538 [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m Epoch 85/139[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 19ms/step - accuracy: 0.5938 - loss: 1.0887[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 21/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5310 - loss: 0.9910 
[1m 42/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5336 - loss: 1.0064[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m185/310[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5391 - loss: 1.0197
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5403 - loss: 1.0193[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m307/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 3ms/step - accuracy: 0.5452 - loss: 1.0168[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 3ms/step - accuracy: 0.5550 - loss: 1.0040 - val_accuracy: 0.6366 - val_loss: 0.7684[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 19ms/step - accuracy: 0.5625 - loss: 1.0863
[1m 21/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5203 - loss: 1.0915 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m Epoch 90/139[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 19ms/step - accuracy: 0.5625 - loss: 1.0460[32m [repeated 3x across cluster][0m

Trial status: 19 TERMINATED | 1 RUNNING
Current time: 2025-11-04 12:06:59. Total running time: 5min 0s
Logical resource usage: 1.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status         N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_af39f    RUNNING              3   adam            relu                                   32                 32                  5          2.34078e-05        139                                              │
│ trial_af39f    TERMINATED           2   rmsprop         tanh                                  128                 32                  5          0.000531671         89        1           150.309          0.658708 │
│ trial_af39f    TERMINATED           3   adam            relu                                   32                 32                  5          8.9631e-05          60        1           265.77           0.677669 │
│ trial_af39f    TERMINATED           2   adam            tanh                                  128                 32                  5          2.05278e-05        115        1           212.308          0.575843 │
│ trial_af39f    TERMINATED           2   adam            tanh                                  128                 64                  5          0.000263082         78        1           193.726          0.654143 │
│ trial_af39f    TERMINATED           3   rmsprop         tanh                                   32                 32                  3          0.00135267          51        1           159.585          0.701194 │
│ trial_af39f    TERMINATED           3   adam            relu                                  128                 64                  3          0.000113647        124        1           218.387          0.695576 │
│ trial_af39f    TERMINATED           3   adam            relu                                   32                 32                  5          0.000608101         70        1           205.984          0.686798 │
│ trial_af39f    TERMINATED           3   adam            tanh                                   32                 64                  5          6.10182e-05         70        1           288.4            0.628862 │
│ trial_af39f    TERMINATED           3   rmsprop         tanh                                   32                 64                  3          4.80349e-05         99        1            76.5749         0.485604 │
│ trial_af39f    TERMINATED           3   rmsprop         relu                                  128                 32                  5          4.00548e-05        132        1           234.641          0.63132  │
│ trial_af39f    TERMINATED           2   rmsprop         tanh                                   32                 64                  3          0.00160542         137        1           164.664          0.692065 │
│ trial_af39f    TERMINATED           4   adam            tanh                                   64                 64                  3          0.000170953         52        1           237.334          0.620084 │
│ trial_af39f    TERMINATED           3   rmsprop         relu                                   64                128                  5          5.18891e-05        146        1           251.697          0.724368 │
│ trial_af39f    TERMINATED           4   adam            tanh                                   64                 32                  3          2.56847e-05         93        1            93.8861         0.474017 │
│ trial_af39f    TERMINATED           2   rmsprop         relu                                   64                128                  3          0.00143439          82        1            80.4604         0.737008 │
│ trial_af39f    TERMINATED           3   rmsprop         relu                                   32                128                  5          0.000409376         53        1           155.27           0.73139  │
│ trial_af39f    TERMINATED           3   rmsprop         tanh                                   32                 64                  3          3.42484e-05        134        1            74.9586         0.474719 │
│ trial_af39f    TERMINATED           2   rmsprop         relu                                   64                 32                  3          4.34693e-05        131        1           260.493          0.667135 │
│ trial_af39f    TERMINATED           4   adam            relu                                   64                 32                  3          0.0028724           66        1           141.32           0.686447 │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
2025-11-04 12:07:08,378	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_ESANN_acc_gyr_superclasses_CPA_METs/ESANN_hyperparameters_tuning' in 0.0068s.
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 21/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5503 - loss: 0.9881 
[1m 42/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5494 - loss: 0.9945[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m265/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5529 - loss: 1.0096
[1m286/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 3ms/step - accuracy: 0.5533 - loss: 1.0091[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 60/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5756 - loss: 1.0155[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 3ms/step - accuracy: 0.5557 - loss: 0.9925 - val_accuracy: 0.6387 - val_loss: 0.7636[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.6875 - loss: 0.7965
[1m 21/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5755 - loss: 0.9422 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m Epoch 96/139[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.5625 - loss: 1.0347[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 21/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5776 - loss: 0.9977 
[1m 42/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5768 - loss: 0.9882[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 41/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5589 - loss: 0.9792
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5652 - loss: 0.9755[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m303/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 3ms/step - accuracy: 0.5667 - loss: 0.9898[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 3ms/step - accuracy: 0.5794 - loss: 0.9666 - val_accuracy: 0.6433 - val_loss: 0.7522[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 99ms/step
[1m42/43[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step 
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 19ms/step - accuracy: 0.5938 - loss: 0.8121
[1m 21/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5513 - loss: 0.9723 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[1m42/89[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step 

Trial trial_af39f finished iteration 1 at 2025-11-04 12:07:08. Total running time: 5min 9s
╭──────────────────────────────────────╮
│ Trial trial_af39f result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             306.335 │
│ time_total_s                 306.335 │
│ training_iteration                 1 │
│ val_accuracy                 0.64326 │
╰──────────────────────────────────────╯

Trial trial_af39f completed after 1 iterations at 2025-11-04 12:07:08. Total running time: 5min 9s

Trial status: 20 TERMINATED
Current time: 2025-11-04 12:07:08. Total running time: 5min 9s
Logical resource usage: 1.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
/home/simur/git/uniovi-simur-wearablepermed-ml/.venv/lib/python3.12/site-packages/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762254428.521421 1125391 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
[36m(train_cnn_ray_tune pid=1127027)[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=1127027)[0m   _log_deprecation_warning(
╭──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status         N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_af39f    TERMINATED           2   rmsprop         tanh                                  128                 32                  5          0.000531671         89        1           150.309          0.658708 │
│ trial_af39f    TERMINATED           3   adam            relu                                   32                 32                  5          8.9631e-05          60        1           265.77           0.677669 │
│ trial_af39f    TERMINATED           2   adam            tanh                                  128                 32                  5          2.05278e-05        115        1           212.308          0.575843 │
│ trial_af39f    TERMINATED           2   adam            tanh                                  128                 64                  5          0.000263082         78        1           193.726          0.654143 │
│ trial_af39f    TERMINATED           3   rmsprop         tanh                                   32                 32                  3          0.00135267          51        1           159.585          0.701194 │
│ trial_af39f    TERMINATED           3   adam            relu                                  128                 64                  3          0.000113647        124        1           218.387          0.695576 │
│ trial_af39f    TERMINATED           3   adam            relu                                   32                 32                  5          0.000608101         70        1           205.984          0.686798 │
│ trial_af39f    TERMINATED           3   adam            relu                                   32                 32                  5          2.34078e-05        139        1           306.335          0.643258 │
│ trial_af39f    TERMINATED           3   adam            tanh                                   32                 64                  5          6.10182e-05         70        1           288.4            0.628862 │
│ trial_af39f    TERMINATED           3   rmsprop         tanh                                   32                 64                  3          4.80349e-05         99        1            76.5749         0.485604 │
│ trial_af39f    TERMINATED           3   rmsprop         relu                                  128                 32                  5          4.00548e-05        132        1           234.641          0.63132  │
│ trial_af39f    TERMINATED           2   rmsprop         tanh                                   32                 64                  3          0.00160542         137        1           164.664          0.692065 │
│ trial_af39f    TERMINATED           4   adam            tanh                                   64                 64                  3          0.000170953         52        1           237.334          0.620084 │
│ trial_af39f    TERMINATED           3   rmsprop         relu                                   64                128                  5          5.18891e-05        146        1           251.697          0.724368 │
│ trial_af39f    TERMINATED           4   adam            tanh                                   64                 32                  3          2.56847e-05         93        1            93.8861         0.474017 │
│ trial_af39f    TERMINATED           2   rmsprop         relu                                   64                128                  3          0.00143439          82        1            80.4604         0.737008 │
│ trial_af39f    TERMINATED           3   rmsprop         relu                                   32                128                  5          0.000409376         53        1           155.27           0.73139  │
│ trial_af39f    TERMINATED           3   rmsprop         tanh                                   32                 64                  3          3.42484e-05        134        1            74.9586         0.474719 │
│ trial_af39f    TERMINATED           2   rmsprop         relu                                   64                 32                  3          4.34693e-05        131        1           260.493          0.667135 │
│ trial_af39f    TERMINATED           4   adam            relu                                   64                 32                  3          0.0028724           66        1           141.32           0.686447 │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯

Mejores hiperparámetros: {'N_capas': 2, 'optimizador': 'rmsprop', 'funcion_activacion': 'relu', 'tamanho_minilote': 64, 'numero_filtros': 128, 'tamanho_filtro': 3, 'tasa_aprendizaje': 0.001434388064590175, 'epochs': 82}
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m87/89[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762254430.160074 1229165 service.cc:152] XLA service 0x76c77000a910 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762254430.160117 1229165 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:07:10.196678: 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 00:00:1762254430.315214 1229165 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762254432.614730 1229165 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:43[0m 3s/step - accuracy: 0.2344 - loss: 2.1253
[1m 32/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3497 - loss: 1.7591 
[1m 67/155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3755 - loss: 1.6455
[1m103/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3990 - loss: 1.5624
[1m144/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.4196 - loss: 1.4920
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4244 - loss: 1.4757
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m8s[0m 28ms/step - accuracy: 0.4248 - loss: 1.4743 - val_accuracy: 0.6773 - val_loss: 0.6841
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6562 - loss: 0.9007
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6000 - loss: 0.9308 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6075 - loss: 0.9090
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6140 - loss: 0.8959
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6181 - loss: 0.8869 - val_accuracy: 0.6907 - val_loss: 0.6434
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7500 - loss: 0.6282
[1m 36/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6671 - loss: 0.7638 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6645 - loss: 0.7692
[1m114/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6663 - loss: 0.7661
[1m151/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6679 - loss: 0.7619
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6680 - loss: 0.7614 - val_accuracy: 0.6959 - val_loss: 0.6092
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7969 - loss: 0.6485
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7052 - loss: 0.7097 
[1m 74/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7008 - loss: 0.7085
[1m114/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6975 - loss: 0.7067
[1m146/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.6964 - loss: 0.7048
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6961 - loss: 0.7044 - val_accuracy: 0.7149 - val_loss: 0.5955
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6719 - loss: 0.7311
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6967 - loss: 0.6774 
[1m 74/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6968 - loss: 0.6743
[1m116/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6982 - loss: 0.6721
[1m154/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6996 - loss: 0.6703
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6996 - loss: 0.6702 - val_accuracy: 0.7089 - val_loss: 0.6094
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7344 - loss: 0.6273
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7246 - loss: 0.6195 
[1m 72/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7229 - loss: 0.6210
[1m107/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7209 - loss: 0.6251
[1m148/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7190 - loss: 0.6290
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7187 - loss: 0.6296 - val_accuracy: 0.7198 - val_loss: 0.5954
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.6875 - loss: 0.8001
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7138 - loss: 0.6160 
[1m 73/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7151 - loss: 0.6172
[1m114/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7187 - loss: 0.6160
[1m151/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7198 - loss: 0.6169
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7199 - loss: 0.6170 - val_accuracy: 0.7166 - val_loss: 0.6065
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7344 - loss: 0.4814
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7607 - loss: 0.5915 
[1m 68/155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7477 - loss: 0.6001
[1m109/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7415 - loss: 0.6016
[1m148/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7376 - loss: 0.6044
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7371 - loss: 0.6047 - val_accuracy: 0.7226 - val_loss: 0.5970
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.8438 - loss: 0.4073
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7483 - loss: 0.5823 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7441 - loss: 0.5802
[1m115/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7419 - loss: 0.5823
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7410 - loss: 0.5840 - val_accuracy: 0.7191 - val_loss: 0.6098
Epoch 10/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7812 - loss: 0.6525
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7515 - loss: 0.6252 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7486 - loss: 0.6126
[1m113/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7471 - loss: 0.6088
[1m151/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7463 - loss: 0.6040
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7462 - loss: 0.6035 - val_accuracy: 0.7212 - val_loss: 0.6241
Epoch 11/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6406 - loss: 0.7997
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7487 - loss: 0.5709 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7540 - loss: 0.5650
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7557 - loss: 0.5640
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7563 - loss: 0.5639 - val_accuracy: 0.7247 - val_loss: 0.6190

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 357ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 13ms/step
Saved model to disk.
[36m(train_cnn_ray_tune pid=1127027)[0m Epoch 99/139[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.5938 - loss: 0.8581
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m 21/310[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5649 - loss: 0.9383 
[1m 41/310[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5659 - loss: 0.9605
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m263/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 3ms/step - accuracy: 0.5804 - loss: 0.9657
[1m283/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 3ms/step - accuracy: 0.5800 - loss: 0.9661[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1127027)[0m 
[1m303/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 3ms/step - accuracy: 0.5796 - loss: 0.9664

=== 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:50[0m 940ms/step
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 841us/step  
[1m132/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 771us/step
[1m201/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 757us/step
[1m273/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 742us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m65/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 789us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 901us/step
Global accuracy score (validation) = 72.86 [%]
Global F1 score (validation) = 73.46 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[7.3068917e-01 1.8777309e-01 6.6522695e-02 1.5015003e-02]
 [6.4245450e-01 1.6864455e-01 1.5511924e-01 3.3781730e-02]
 [7.0372319e-01 2.9481655e-01 9.7824144e-04 4.8196141e-04]
 ...
 [2.3567387e-05 1.1868019e-04 3.9781383e-04 9.9945992e-01]
 [1.7951174e-05 9.4062358e-05 3.1573349e-04 9.9957234e-01]
 [3.4972490e-03 1.7725715e-03 9.7309381e-01 2.1636404e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 79.62 [%]
Global accuracy score (test) = 73.09 [%]
Global F1 score (train) = 79.82 [%]
Global F1 score (test) = 73.97 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.53      0.58      0.55       350
MODERATE-INTENSITY       0.55      0.53      0.54       350
         SEDENTARY       0.94      0.97      0.95       350
VIGOROUS-INTENSITY       0.96      0.87      0.91       299

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

2025-11-04 12:07:33.337180: 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`.
2025-11-04 12:07:33.348440: 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 00:00:1762254453.361384 1231056 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762254453.365457 1231056 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762254453.375129 1231056 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254453.375146 1231056 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254453.375147 1231056 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254453.375149 1231056 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:07:33.378438: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762254455.698402 1231056 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762254457.099842 1231165 service.cc:152] XLA service 0x7c6ba400a620 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762254457.099873 1231165 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:07:37.133643: 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 00:00:1762254457.257628 1231165 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762254459.560584 1231165 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:12[0m 3s/step - accuracy: 0.2969 - loss: 2.0054
[1m 35/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3796 - loss: 1.7704 
[1m 74/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4048 - loss: 1.6527
[1m114/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4257 - loss: 1.5674
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4426 - loss: 1.5001
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 28ms/step - accuracy: 0.4429 - loss: 1.4986 - val_accuracy: 0.6879 - val_loss: 0.6866
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.5625 - loss: 0.9930
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.5919 - loss: 0.9719 
[1m 78/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6024 - loss: 0.9473
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6093 - loss: 0.9288
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6149 - loss: 0.9135 - val_accuracy: 0.6942 - val_loss: 0.6497
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6406 - loss: 1.0514
[1m 43/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6551 - loss: 0.7694 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6622 - loss: 0.7580
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6653 - loss: 0.7541
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6669 - loss: 0.7516 - val_accuracy: 0.7096 - val_loss: 0.6113
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.6875 - loss: 0.6463
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6889 - loss: 0.7009 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6836 - loss: 0.7088
[1m116/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6845 - loss: 0.7058
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6865 - loss: 0.7021 - val_accuracy: 0.7058 - val_loss: 0.6108
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7031 - loss: 0.7189
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7064 - loss: 0.6703 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7081 - loss: 0.6696
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7104 - loss: 0.6632
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7112 - loss: 0.6614 - val_accuracy: 0.7156 - val_loss: 0.6018
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6875 - loss: 0.5466
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7196 - loss: 0.6214 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7200 - loss: 0.6254
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7189 - loss: 0.6284
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7182 - loss: 0.6305 - val_accuracy: 0.7096 - val_loss: 0.6296
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7500 - loss: 0.5489
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7161 - loss: 0.6096 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7202 - loss: 0.6081
[1m111/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7211 - loss: 0.6120
[1m147/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.7218 - loss: 0.6150
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7222 - loss: 0.6152 - val_accuracy: 0.7244 - val_loss: 0.6018
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7344 - loss: 0.5837
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7268 - loss: 0.6094 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7333 - loss: 0.6007
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7342 - loss: 0.6017
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7354 - loss: 0.6010 - val_accuracy: 0.7110 - val_loss: 0.6314
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.8906 - loss: 0.3784
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7456 - loss: 0.5765 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7442 - loss: 0.5832
[1m116/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7443 - loss: 0.5846
[1m153/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7446 - loss: 0.5851
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7447 - loss: 0.5850 - val_accuracy: 0.7212 - val_loss: 0.6209
Epoch 10/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7188 - loss: 0.5123
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7552 - loss: 0.5519 
[1m 78/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7565 - loss: 0.5553
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7586 - loss: 0.5580
[1m154/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7593 - loss: 0.5599
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7594 - loss: 0.5600 - val_accuracy: 0.7314 - val_loss: 0.6149
Epoch 11/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 19ms/step - accuracy: 0.8438 - loss: 0.4397
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7722 - loss: 0.5520 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7701 - loss: 0.5583
[1m115/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7702 - loss: 0.5572
[1m153/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7691 - loss: 0.5582
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7690 - loss: 0.5583 - val_accuracy: 0.7247 - val_loss: 0.6367
Epoch 12/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.8750 - loss: 0.3983
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7800 - loss: 0.5446 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7779 - loss: 0.5405
[1m125/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7778 - loss: 0.5394
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7778 - loss: 0.5390 - val_accuracy: 0.7370 - val_loss: 0.6422

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 355ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 1: 73.09 [%]
F1-score capturado en la ejecución 1: 73.97 [%]

=== EJECUCIÓN 2 ===

--- TRAIN (ejecución 2) ---

--- TEST (ejecución 2) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:47[0m 932ms/step
[1m 66/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 769us/step  
[1m143/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 704us/step
[1m210/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 719us/step
[1m277/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 728us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m69/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 740us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 867us/step
Global accuracy score (validation) = 73.95 [%]
Global F1 score (validation) = 75.07 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[6.9990999e-01 2.0506686e-01 7.5962104e-02 1.9061066e-02]
 [6.7860752e-01 2.1355557e-01 8.6619958e-02 2.1216923e-02]
 [3.3021462e-01 6.6925526e-01 7.6072836e-05 4.5400843e-04]
 ...
 [1.7805143e-05 1.7460837e-04 1.9800784e-04 9.9960959e-01]
 [1.4059609e-05 8.8368404e-05 1.7548447e-04 9.9972218e-01]
 [1.0764031e-02 1.7583398e-02 7.0971435e-01 2.6193815e-01]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 80.98 [%]
Global accuracy score (test) = 73.02 [%]
Global F1 score (train) = 81.34 [%]
Global F1 score (test) = 74.26 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.53      0.54      0.53       350
MODERATE-INTENSITY       0.55      0.60      0.57       350
         SEDENTARY       0.98      0.91      0.94       350
VIGOROUS-INTENSITY       0.95      0.89      0.92       299

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

2025-11-04 12:07:57.712147: 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`.
2025-11-04 12:07:57.723302: 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 00:00:1762254477.736418 1233102 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762254477.740497 1233102 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762254477.750624 1233102 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254477.750643 1233102 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254477.750644 1233102 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254477.750646 1233102 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:07:57.753962: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762254480.092479 1233102 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762254481.522003 1233240 service.cc:152] XLA service 0x71c15800a9c0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762254481.522057 1233240 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:08:01.561405: 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 00:00:1762254481.683557 1233240 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762254483.986944 1233240 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:18[0m 3s/step - accuracy: 0.2500 - loss: 2.1621
[1m 35/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3837 - loss: 1.7226 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4134 - loss: 1.5992
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4344 - loss: 1.5183
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4499 - loss: 1.4606
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m8s[0m 28ms/step - accuracy: 0.4502 - loss: 1.4593 - val_accuracy: 0.7082 - val_loss: 0.6796
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 23ms/step - accuracy: 0.5156 - loss: 1.2014
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.5783 - loss: 1.0017 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.5956 - loss: 0.9535
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6056 - loss: 0.9277
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6116 - loss: 0.9121 - val_accuracy: 0.7082 - val_loss: 0.6179
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6250 - loss: 0.8875
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6527 - loss: 0.7748 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6581 - loss: 0.7646
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6619 - loss: 0.7595
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6631 - loss: 0.7568 - val_accuracy: 0.7138 - val_loss: 0.5850
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6719 - loss: 0.7560
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6955 - loss: 0.6866 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6927 - loss: 0.6896
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6933 - loss: 0.6886
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6936 - loss: 0.6875 - val_accuracy: 0.7107 - val_loss: 0.6129
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7344 - loss: 0.5859
[1m 43/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6960 - loss: 0.6432 
[1m 84/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7001 - loss: 0.6468
[1m124/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7009 - loss: 0.6512
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7016 - loss: 0.6531 - val_accuracy: 0.7156 - val_loss: 0.5877
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6094 - loss: 0.6473
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6929 - loss: 0.6628 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6979 - loss: 0.6611
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7018 - loss: 0.6570
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7040 - loss: 0.6548 - val_accuracy: 0.7191 - val_loss: 0.5951
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7656 - loss: 0.5517
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7414 - loss: 0.5927 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7319 - loss: 0.6075
[1m114/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7258 - loss: 0.6164
[1m154/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7227 - loss: 0.6208
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7227 - loss: 0.6209 - val_accuracy: 0.7114 - val_loss: 0.6142
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7812 - loss: 0.4710
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7431 - loss: 0.5679 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7391 - loss: 0.5824
[1m125/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7362 - loss: 0.5902
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7349 - loss: 0.5936 - val_accuracy: 0.7353 - val_loss: 0.5893

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 352ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 2: 73.02 [%]
F1-score capturado en la ejecución 2: 74.26 [%]

=== EJECUCIÓN 3 ===

--- TRAIN (ejecución 3) ---

--- TEST (ejecución 3) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:38[0m 901ms/step
[1m 71/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 720us/step  
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 705us/step
[1m219/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 694us/step
[1m290/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 697us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 19ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m66/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 770us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 904us/step
Global accuracy score (validation) = 73.56 [%]
Global F1 score (validation) = 74.43 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[5.9576124e-01 3.9873263e-01 1.3675940e-03 4.1385130e-03]
 [4.6831751e-01 5.3021657e-01 3.8303831e-04 1.0829457e-03]
 [6.9819325e-01 2.1825024e-01 7.1793854e-02 1.1762583e-02]
 ...
 [6.3111715e-05 2.2705454e-04 5.0049496e-04 9.9920928e-01]
 [7.0656781e-05 2.2896205e-04 2.3048861e-04 9.9946976e-01]
 [2.2150427e-02 1.2115162e-02 9.1978687e-01 4.5947522e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 78.13 [%]
Global accuracy score (test) = 75.09 [%]
Global F1 score (train) = 78.52 [%]
Global F1 score (test) = 76.01 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.54      0.68      0.60       350
MODERATE-INTENSITY       0.60      0.49      0.54       350
         SEDENTARY       0.97      0.95      0.96       350
VIGOROUS-INTENSITY       0.98      0.91      0.94       299

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

2025-11-04 12:08:20.729457: 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`.
2025-11-04 12:08:20.740768: 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 00:00:1762254500.754005 1234809 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762254500.758186 1234809 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762254500.768111 1234809 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254500.768129 1234809 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254500.768130 1234809 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254500.768131 1234809 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:08:20.771237: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762254503.079424 1234809 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762254504.497862 1234948 service.cc:152] XLA service 0x76a8b4005840 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762254504.497892 1234948 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:08:24.533259: 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 00:00:1762254504.650145 1234948 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762254506.950372 1234948 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:13[0m 3s/step - accuracy: 0.2344 - loss: 2.2029
[1m 34/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3547 - loss: 1.7699 
[1m 70/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3882 - loss: 1.6356
[1m107/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4117 - loss: 1.5463
[1m146/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.4306 - loss: 1.4780
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4346 - loss: 1.4642
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 28ms/step - accuracy: 0.4351 - loss: 1.4627 - val_accuracy: 0.6822 - val_loss: 0.6541
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.5000 - loss: 1.0077
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6132 - loss: 0.8999 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6190 - loss: 0.8848
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6214 - loss: 0.8752
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6229 - loss: 0.8671 - val_accuracy: 0.6984 - val_loss: 0.6244
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.5469 - loss: 0.9933
[1m 36/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6703 - loss: 0.7597 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6763 - loss: 0.7458
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6773 - loss: 0.7408
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6785 - loss: 0.7367 - val_accuracy: 0.7040 - val_loss: 0.6201
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7031 - loss: 0.7613
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6924 - loss: 0.7167 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6899 - loss: 0.7116
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6895 - loss: 0.7068
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6898 - loss: 0.7028 - val_accuracy: 0.7124 - val_loss: 0.5928
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7031 - loss: 0.6810
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7105 - loss: 0.6527 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7109 - loss: 0.6608
[1m124/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7127 - loss: 0.6568
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7129 - loss: 0.6553 - val_accuracy: 0.7198 - val_loss: 0.5894
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.5469 - loss: 0.9241
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7058 - loss: 0.6650 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7096 - loss: 0.6524
[1m125/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7105 - loss: 0.6483
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7110 - loss: 0.6464 - val_accuracy: 0.7086 - val_loss: 0.6127
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.8594 - loss: 0.4488
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7453 - loss: 0.6339 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7411 - loss: 0.6240
[1m122/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7382 - loss: 0.6217
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7365 - loss: 0.6207 - val_accuracy: 0.7317 - val_loss: 0.5874
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7188 - loss: 0.6181
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7438 - loss: 0.6150 
[1m 78/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7431 - loss: 0.6080
[1m115/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7428 - loss: 0.6047
[1m153/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7440 - loss: 0.6020
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7441 - loss: 0.6018 - val_accuracy: 0.7342 - val_loss: 0.5913
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7656 - loss: 0.5194
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7605 - loss: 0.5666 
[1m 75/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7614 - loss: 0.5649
[1m108/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7610 - loss: 0.5667
[1m144/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.7604 - loss: 0.5684
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7601 - loss: 0.5692 - val_accuracy: 0.7296 - val_loss: 0.5954
Epoch 10/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7031 - loss: 0.6308
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7409 - loss: 0.5866 
[1m 84/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7450 - loss: 0.5775
[1m128/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7483 - loss: 0.5733
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7496 - loss: 0.5721 - val_accuracy: 0.7391 - val_loss: 0.5870
Epoch 11/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7344 - loss: 0.5268
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7710 - loss: 0.5175 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7732 - loss: 0.5293
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7727 - loss: 0.5344
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7714 - loss: 0.5395 - val_accuracy: 0.7335 - val_loss: 0.6123
Epoch 12/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.8281 - loss: 0.4097
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7956 - loss: 0.5061 
[1m 78/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7862 - loss: 0.5223
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7818 - loss: 0.5291
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7804 - loss: 0.5317 - val_accuracy: 0.7346 - val_loss: 0.6125
Epoch 13/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 24ms/step - accuracy: 0.8750 - loss: 0.4379
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.8026 - loss: 0.5135 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7965 - loss: 0.5153
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7946 - loss: 0.5164
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7930 - loss: 0.5188 - val_accuracy: 0.7226 - val_loss: 0.6220
Epoch 14/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7500 - loss: 0.4918
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7759 - loss: 0.5327 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7819 - loss: 0.5256
[1m125/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7843 - loss: 0.5236
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7849 - loss: 0.5236 - val_accuracy: 0.7381 - val_loss: 0.6261
Epoch 15/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7344 - loss: 0.5385
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7941 - loss: 0.5087 
[1m 85/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7975 - loss: 0.5049
[1m126/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7976 - loss: 0.5071
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7975 - loss: 0.5083 - val_accuracy: 0.7367 - val_loss: 0.6250

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 365ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 3: 75.09 [%]
F1-score capturado en la ejecución 3: 76.01 [%]

=== EJECUCIÓN 4 ===

--- TRAIN (ejecución 4) ---

--- TEST (ejecución 4) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:51[0m 943ms/step
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 825us/step  
[1m136/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 748us/step
[1m207/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 735us/step
[1m281/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 721us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m68/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 750us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 877us/step
Global accuracy score (validation) = 73.49 [%]
Global F1 score (validation) = 74.22 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[6.2772846e-01 1.3688610e-01 1.9099762e-01 4.4387821e-02]
 [6.1226273e-01 3.8647375e-01 1.2963430e-04 1.1339317e-03]
 [3.3596882e-01 6.2400031e-01 2.5100322e-03 3.7520871e-02]
 ...
 [3.0586596e-06 5.5694789e-05 7.4102907e-05 9.9986720e-01]
 [3.0224517e-06 4.5162673e-05 5.8715126e-05 9.9989307e-01]
 [2.7702441e-03 3.9571961e-03 9.2818642e-01 6.5086178e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 82.97 [%]
Global accuracy score (test) = 73.68 [%]
Global F1 score (train) = 83.14 [%]
Global F1 score (test) = 74.6 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.52      0.58      0.55       350
MODERATE-INTENSITY       0.57      0.53      0.55       350
         SEDENTARY       0.96      0.96      0.96       350
VIGOROUS-INTENSITY       0.95      0.91      0.93       299

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

2025-11-04 12:08:45.914018: 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`.
2025-11-04 12:08:45.925468: 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 00:00:1762254525.938537 1237148 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762254525.942662 1237148 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762254525.952422 1237148 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254525.952440 1237148 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254525.952442 1237148 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254525.952444 1237148 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:08:45.955643: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762254528.295054 1237148 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762254529.727481 1237286 service.cc:152] XLA service 0x7b7198218630 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762254529.727539 1237286 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:08:49.761555: 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 00:00:1762254529.883564 1237286 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762254532.193375 1237286 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:16[0m 3s/step - accuracy: 0.2031 - loss: 2.2930
[1m 36/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3379 - loss: 1.8610 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3782 - loss: 1.7025
[1m109/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3994 - loss: 1.6224
[1m145/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.4191 - loss: 1.5528
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4240 - loss: 1.5358
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m8s[0m 28ms/step - accuracy: 0.4244 - loss: 1.5341 - val_accuracy: 0.6836 - val_loss: 0.6619
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 25ms/step - accuracy: 0.5938 - loss: 0.8958
[1m 36/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6035 - loss: 0.9122 
[1m 73/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6103 - loss: 0.8998
[1m109/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6152 - loss: 0.8884
[1m146/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.6198 - loss: 0.8780
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6209 - loss: 0.8755 - val_accuracy: 0.6991 - val_loss: 0.6148
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.5938 - loss: 0.8861
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6526 - loss: 0.8048 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6655 - loss: 0.7644
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6701 - loss: 0.7504
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6723 - loss: 0.7442 - val_accuracy: 0.7128 - val_loss: 0.6177
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6875 - loss: 0.7688
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7014 - loss: 0.6931 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7032 - loss: 0.6833
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7028 - loss: 0.6804
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7021 - loss: 0.6805 - val_accuracy: 0.7152 - val_loss: 0.6240
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7188 - loss: 0.6054
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7260 - loss: 0.6128 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7188 - loss: 0.6330
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7142 - loss: 0.6416
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7122 - loss: 0.6450 - val_accuracy: 0.7346 - val_loss: 0.5920
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7188 - loss: 0.8009
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7211 - loss: 0.6302 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7210 - loss: 0.6310
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7201 - loss: 0.6330
[1m153/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7196 - loss: 0.6333
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7195 - loss: 0.6333 - val_accuracy: 0.7198 - val_loss: 0.6173
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7344 - loss: 0.5473
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7220 - loss: 0.6124 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7226 - loss: 0.6154
[1m122/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7227 - loss: 0.6160
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7228 - loss: 0.6166 - val_accuracy: 0.7472 - val_loss: 0.5967
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7656 - loss: 0.5164
[1m 36/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7353 - loss: 0.5982 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7377 - loss: 0.5963
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7391 - loss: 0.5964
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.7404 - loss: 0.5957
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7404 - loss: 0.5957 - val_accuracy: 0.7258 - val_loss: 0.6068
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7969 - loss: 0.6614
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7685 - loss: 0.5737 
[1m 72/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7608 - loss: 0.5840
[1m110/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7578 - loss: 0.5847
[1m153/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7552 - loss: 0.5863
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7550 - loss: 0.5865 - val_accuracy: 0.7226 - val_loss: 0.6070
Epoch 10/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7344 - loss: 0.7627
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7518 - loss: 0.5713 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7581 - loss: 0.5656
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7597 - loss: 0.5642
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7603 - loss: 0.5643 - val_accuracy: 0.7163 - val_loss: 0.6338

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 354ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 4: 73.68 [%]
F1-score capturado en la ejecución 4: 74.6 [%]

=== EJECUCIÓN 5 ===

--- TRAIN (ejecución 5) ---

--- TEST (ejecución 5) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:48[0m 935ms/step
[1m 68/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 750us/step  
[1m141/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 719us/step
[1m215/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 704us/step
[1m290/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 696us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m66/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 770us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 901us/step
Global accuracy score (validation) = 72.19 [%]
Global F1 score (validation) = 72.49 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[5.8751011e-01 1.3979776e-01 2.4326323e-01 2.9428853e-02]
 [7.3476189e-01 1.5702744e-01 9.3370393e-02 1.4840359e-02]
 [4.3445951e-01 5.6364888e-01 1.4838299e-03 4.0775369e-04]
 ...
 [4.7809543e-05 2.0933952e-04 2.3787901e-04 9.9950492e-01]
 [2.2540824e-05 8.1718274e-05 1.8618096e-04 9.9970955e-01]
 [1.7093970e-02 1.0898221e-02 9.5578754e-01 1.6220178e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 78.6 [%]
Global accuracy score (test) = 72.57 [%]
Global F1 score (train) = 78.7 [%]
Global F1 score (test) = 72.75 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.53      0.75      0.62       350
MODERATE-INTENSITY       0.59      0.39      0.47       350
         SEDENTARY       0.92      0.95      0.94       350
VIGOROUS-INTENSITY       0.95      0.83      0.89       299

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

2025-11-04 12:09:09.618094: 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`.
2025-11-04 12:09:09.629194: 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 00:00:1762254549.642255 1239038 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762254549.646349 1239038 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762254549.656147 1239038 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254549.656163 1239038 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254549.656164 1239038 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254549.656166 1239038 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:09:09.659063: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762254551.966873 1239038 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762254553.390398 1239145 service.cc:152] XLA service 0x761cf820b020 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762254553.390430 1239145 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:09:13.424233: 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 00:00:1762254553.546236 1239145 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762254555.812542 1239145 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:09[0m 3s/step - accuracy: 0.2344 - loss: 2.2128
[1m 31/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7393 
[1m 72/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4012 - loss: 1.6069
[1m111/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4241 - loss: 1.5212
[1m153/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.4432 - loss: 1.4534
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4440 - loss: 1.4505
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 28ms/step - accuracy: 0.4444 - loss: 1.4491 - val_accuracy: 0.6900 - val_loss: 0.6773
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 23ms/step - accuracy: 0.5156 - loss: 1.0946
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.5922 - loss: 0.9574 
[1m 75/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6073 - loss: 0.9209
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6151 - loss: 0.8985
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6202 - loss: 0.8832 - val_accuracy: 0.6977 - val_loss: 0.6111
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6562 - loss: 0.6946
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6677 - loss: 0.7651 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6706 - loss: 0.7579
[1m124/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6724 - loss: 0.7524
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6727 - loss: 0.7499 - val_accuracy: 0.7065 - val_loss: 0.6154
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7031 - loss: 0.6275
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6909 - loss: 0.6589 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6915 - loss: 0.6723
[1m114/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6914 - loss: 0.6808
[1m154/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6918 - loss: 0.6844
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6919 - loss: 0.6844 - val_accuracy: 0.7145 - val_loss: 0.6114
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.8281 - loss: 0.4666
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6964 - loss: 0.6625 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6982 - loss: 0.6577
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6995 - loss: 0.6570
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7004 - loss: 0.6581 - val_accuracy: 0.7177 - val_loss: 0.5982
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7656 - loss: 0.5859
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7127 - loss: 0.6475 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7108 - loss: 0.6496
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7113 - loss: 0.6496
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.7131 - loss: 0.6478
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7131 - loss: 0.6477 - val_accuracy: 0.7124 - val_loss: 0.6317
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7188 - loss: 0.8045
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7144 - loss: 0.6487 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7172 - loss: 0.6356
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7205 - loss: 0.6277
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.7207 - loss: 0.6247
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7207 - loss: 0.6247 - val_accuracy: 0.7244 - val_loss: 0.6036
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 23ms/step - accuracy: 0.7031 - loss: 0.6131
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7552 - loss: 0.5805 
[1m 78/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7487 - loss: 0.5864
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7471 - loss: 0.5865
[1m151/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7464 - loss: 0.5871
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7463 - loss: 0.5874 - val_accuracy: 0.7356 - val_loss: 0.5941
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7656 - loss: 0.5648
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7577 - loss: 0.5823 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7486 - loss: 0.5875
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7457 - loss: 0.5869
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7451 - loss: 0.5860 - val_accuracy: 0.7279 - val_loss: 0.6130
Epoch 10/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7344 - loss: 0.5106
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7497 - loss: 0.5685 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7527 - loss: 0.5667
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7550 - loss: 0.5666
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7548 - loss: 0.5680 - val_accuracy: 0.7251 - val_loss: 0.6057
Epoch 11/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7500 - loss: 0.5071
[1m 43/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7385 - loss: 0.5749 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7443 - loss: 0.5697
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7484 - loss: 0.5672
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7512 - loss: 0.5653 - val_accuracy: 0.7303 - val_loss: 0.6176
Epoch 12/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7969 - loss: 0.5527
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7688 - loss: 0.5478 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7655 - loss: 0.5558
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7644 - loss: 0.5583
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7642 - loss: 0.5585 - val_accuracy: 0.7310 - val_loss: 0.6239
Epoch 13/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.8438 - loss: 0.4642
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7999 - loss: 0.5120 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7937 - loss: 0.5205
[1m114/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7908 - loss: 0.5248
[1m154/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7878 - loss: 0.5284
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7876 - loss: 0.5286 - val_accuracy: 0.7388 - val_loss: 0.6117

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 356ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 5: 72.57 [%]
F1-score capturado en la ejecución 5: 72.75 [%]

=== EJECUCIÓN 6 ===

--- TRAIN (ejecución 6) ---

--- TEST (ejecución 6) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:56[0m 959ms/step
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 837us/step  
[1m133/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 765us/step
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 732us/step
[1m280/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 722us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m70/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 729us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 850us/step
Global accuracy score (validation) = 73.81 [%]
Global F1 score (validation) = 74.71 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[5.59647799e-01 4.30417478e-01 3.00518144e-03 6.92952657e-03]
 [4.53193277e-01 5.45899272e-01 4.69732564e-04 4.37752053e-04]
 [3.12437296e-01 6.80746019e-01 6.61816972e-04 6.15481567e-03]
 ...
 [1.24741700e-05 1.00195175e-04 1.21251891e-04 9.99766052e-01]
 [1.67612707e-05 1.41730605e-04 9.68527456e-05 9.99744713e-01]
 [7.85144512e-03 4.51350445e-03 8.75963032e-01 1.11672051e-01]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 81.48 [%]
Global accuracy score (test) = 75.54 [%]
Global F1 score (train) = 81.77 [%]
Global F1 score (test) = 76.47 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.57      0.58      0.57       350
MODERATE-INTENSITY       0.59      0.63      0.61       350
         SEDENTARY       0.96      0.95      0.95       350
VIGOROUS-INTENSITY       0.96      0.89      0.93       299

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

2025-11-04 12:09:34.224772: 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`.
2025-11-04 12:09:34.235956: 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 00:00:1762254574.249122 1241186 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762254574.253285 1241186 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762254574.263337 1241186 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254574.263356 1241186 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254574.263358 1241186 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254574.263359 1241186 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:09:34.266557: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762254576.577277 1241186 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762254577.981042 1241321 service.cc:152] XLA service 0x7b229c00a610 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762254577.981092 1241321 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:09:38.021168: 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 00:00:1762254578.151653 1241321 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762254580.421311 1241321 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:11[0m 3s/step - accuracy: 0.1875 - loss: 2.6552
[1m 32/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3229 - loss: 1.9727 
[1m 73/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3708 - loss: 1.7612
[1m115/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3989 - loss: 1.6469
[1m153/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.4186 - loss: 1.5712
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4195 - loss: 1.5677
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 28ms/step - accuracy: 0.4200 - loss: 1.5660 - val_accuracy: 0.6980 - val_loss: 0.6902
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 23ms/step - accuracy: 0.5938 - loss: 1.0869
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6161 - loss: 0.9374 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6183 - loss: 0.9173
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6193 - loss: 0.9032
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.6203 - loss: 0.8941
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6203 - loss: 0.8938 - val_accuracy: 0.7026 - val_loss: 0.6315
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7812 - loss: 0.6333
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6981 - loss: 0.7374 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6832 - loss: 0.7454
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6772 - loss: 0.7480
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6745 - loss: 0.7486 - val_accuracy: 0.7061 - val_loss: 0.6138
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7500 - loss: 0.6487
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6760 - loss: 0.6952 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6807 - loss: 0.6933
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6820 - loss: 0.6942
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6835 - loss: 0.6944 - val_accuracy: 0.7089 - val_loss: 0.6207
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6562 - loss: 0.7650
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7064 - loss: 0.6724 
[1m 84/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7056 - loss: 0.6686
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7051 - loss: 0.6668
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.7045 - loss: 0.6667
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7045 - loss: 0.6667 - val_accuracy: 0.7110 - val_loss: 0.6133
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7188 - loss: 0.8012
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7181 - loss: 0.6465 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7143 - loss: 0.6461
[1m124/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7146 - loss: 0.6445
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7146 - loss: 0.6443 - val_accuracy: 0.7100 - val_loss: 0.6198
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6875 - loss: 0.6547
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7203 - loss: 0.6147 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7230 - loss: 0.6130
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7250 - loss: 0.6117
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7253 - loss: 0.6130 - val_accuracy: 0.7237 - val_loss: 0.6094
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6406 - loss: 0.6492
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7178 - loss: 0.6106 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7240 - loss: 0.6097
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7257 - loss: 0.6086
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7276 - loss: 0.6069 - val_accuracy: 0.7117 - val_loss: 0.6355
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7812 - loss: 0.5154
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7508 - loss: 0.5980 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7501 - loss: 0.5853
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7511 - loss: 0.5804
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7511 - loss: 0.5799 - val_accuracy: 0.7240 - val_loss: 0.6234
Epoch 10/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7344 - loss: 0.6445
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7518 - loss: 0.5741 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7520 - loss: 0.5737
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7522 - loss: 0.5760
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7520 - loss: 0.5770 - val_accuracy: 0.7328 - val_loss: 0.6154
Epoch 11/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.8594 - loss: 0.3507
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7712 - loss: 0.5490 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7698 - loss: 0.5492
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7683 - loss: 0.5509
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7673 - loss: 0.5527 - val_accuracy: 0.7170 - val_loss: 0.6374
Epoch 12/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7344 - loss: 0.7403
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7661 - loss: 0.5530 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7698 - loss: 0.5447
[1m116/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7708 - loss: 0.5448
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.7710 - loss: 0.5460
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7710 - loss: 0.5460 - val_accuracy: 0.7195 - val_loss: 0.6517

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 363ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 6: 75.54 [%]
F1-score capturado en la ejecución 6: 76.47 [%]

=== EJECUCIÓN 7 ===

--- TRAIN (ejecución 7) ---

--- TEST (ejecución 7) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:49[0m 936ms/step
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 842us/step  
[1m127/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 799us/step
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 741us/step
[1m279/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 724us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m67/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 765us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 889us/step
Global accuracy score (validation) = 71.66 [%]
Global F1 score (validation) = 72.42 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[5.9430248e-01 4.0486324e-01 3.2931755e-04 5.0505542e-04]
 [7.0021302e-01 2.9357985e-01 4.0634642e-03 2.1436121e-03]
 [5.3845567e-01 4.6101716e-01 1.6757853e-04 3.5964904e-04]
 ...
 [1.8579023e-05 1.6038504e-04 1.2609878e-04 9.9969488e-01]
 [1.4173705e-05 1.0263061e-04 2.2505119e-04 9.9965823e-01]
 [2.4066812e-03 1.2731776e-03 9.9161363e-01 4.7065942e-03]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 80.63 [%]
Global accuracy score (test) = 71.98 [%]
Global F1 score (train) = 80.86 [%]
Global F1 score (test) = 72.94 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.50      0.61      0.55       350
MODERATE-INTENSITY       0.57      0.49      0.53       350
         SEDENTARY       0.92      0.95      0.94       350
VIGOROUS-INTENSITY       0.97      0.85      0.90       299

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

2025-11-04 12:09:58.536917: 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`.
2025-11-04 12:09:58.548049: 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 00:00:1762254598.561250 1243259 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762254598.565145 1243259 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762254598.575029 1243259 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254598.575045 1243259 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254598.575047 1243259 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254598.575048 1243259 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:09:58.578047: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762254600.937893 1243259 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762254602.346805 1243395 service.cc:152] XLA service 0x7925a4016e90 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762254602.346852 1243395 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:10:02.381339: 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 00:00:1762254602.498202 1243395 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762254604.783696 1243395 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:09[0m 3s/step - accuracy: 0.2031 - loss: 2.5220
[1m 30/155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3263 - loss: 1.8904 
[1m 64/155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3684 - loss: 1.7315
[1m106/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3971 - loss: 1.6251
[1m141/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.4160 - loss: 1.5593
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4227 - loss: 1.5363
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 28ms/step - accuracy: 0.4232 - loss: 1.5347 - val_accuracy: 0.6900 - val_loss: 0.6706
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.5312 - loss: 1.0780
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.5844 - loss: 0.9730 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.5964 - loss: 0.9516
[1m115/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6036 - loss: 0.9333
[1m151/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6086 - loss: 0.9191
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6093 - loss: 0.9173 - val_accuracy: 0.7054 - val_loss: 0.6344
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6250 - loss: 0.8162
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6494 - loss: 0.7760 
[1m 78/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6567 - loss: 0.7660
[1m115/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6609 - loss: 0.7608
[1m153/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6632 - loss: 0.7572
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6634 - loss: 0.7570 - val_accuracy: 0.7096 - val_loss: 0.6070
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7812 - loss: 0.5786
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6925 - loss: 0.6840 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6884 - loss: 0.6907
[1m122/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6859 - loss: 0.6935
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6854 - loss: 0.6945 - val_accuracy: 0.7082 - val_loss: 0.6140
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6406 - loss: 0.7385
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6875 - loss: 0.6939 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6934 - loss: 0.6876
[1m113/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6965 - loss: 0.6829
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.6984 - loss: 0.6800
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6984 - loss: 0.6799 - val_accuracy: 0.7135 - val_loss: 0.6090
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6875 - loss: 0.6874
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6961 - loss: 0.6656 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7031 - loss: 0.6583
[1m112/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7047 - loss: 0.6545
[1m151/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7052 - loss: 0.6514
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7053 - loss: 0.6510 - val_accuracy: 0.7212 - val_loss: 0.6157
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6406 - loss: 0.7501
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7113 - loss: 0.6515 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7139 - loss: 0.6458
[1m112/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7158 - loss: 0.6426
[1m152/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7179 - loss: 0.6385
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7180 - loss: 0.6381 - val_accuracy: 0.7335 - val_loss: 0.6257
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7500 - loss: 0.6315
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7445 - loss: 0.6069 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7417 - loss: 0.6094
[1m112/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7407 - loss: 0.6080
[1m154/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7389 - loss: 0.6084
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7389 - loss: 0.6084 - val_accuracy: 0.7307 - val_loss: 0.6024
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7188 - loss: 0.7224
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7306 - loss: 0.5970 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7342 - loss: 0.5987
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7357 - loss: 0.5981
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7366 - loss: 0.5969 - val_accuracy: 0.7342 - val_loss: 0.6158
Epoch 10/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.8438 - loss: 0.4356
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7688 - loss: 0.5561 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7638 - loss: 0.5610
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7604 - loss: 0.5643
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7593 - loss: 0.5659 - val_accuracy: 0.7254 - val_loss: 0.6279
Epoch 11/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7656 - loss: 0.5354
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7526 - loss: 0.5594 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7550 - loss: 0.5636
[1m124/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7558 - loss: 0.5657
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7564 - loss: 0.5652 - val_accuracy: 0.7279 - val_loss: 0.6469
Epoch 12/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6562 - loss: 0.6961
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7473 - loss: 0.5758 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7517 - loss: 0.5702
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7539 - loss: 0.5680
[1m154/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7551 - loss: 0.5665
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7552 - loss: 0.5664 - val_accuracy: 0.7251 - val_loss: 0.6382
Epoch 13/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.8281 - loss: 0.4592
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7709 - loss: 0.5423 
[1m 78/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7731 - loss: 0.5368
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7745 - loss: 0.5359
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7743 - loss: 0.5369 - val_accuracy: 0.7275 - val_loss: 0.6598

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 346ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 7: 71.98 [%]
F1-score capturado en la ejecución 7: 72.94 [%]

=== EJECUCIÓN 8 ===

--- TRAIN (ejecución 8) ---

--- TEST (ejecución 8) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:57[0m 962ms/step
[1m 69/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 741us/step  
[1m134/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 757us/step
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 736us/step
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 747us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m68/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 753us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 865us/step
Global accuracy score (validation) = 73.21 [%]
Global F1 score (validation) = 73.84 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[8.13928962e-01 1.85240105e-01 6.39217556e-04 1.91720464e-04]
 [8.13928962e-01 1.85240105e-01 6.39217556e-04 1.91720464e-04]
 [6.94878638e-01 1.62131757e-01 1.18973538e-01 2.40161493e-02]
 ...
 [5.71037981e-06 3.44568543e-05 7.80794508e-05 9.99881744e-01]
 [1.00812285e-05 5.22077098e-05 1.08697575e-04 9.99828935e-01]
 [8.70121177e-03 4.51023271e-03 9.75746870e-01 1.10417446e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 81.07 [%]
Global accuracy score (test) = 75.39 [%]
Global F1 score (train) = 81.27 [%]
Global F1 score (test) = 76.2 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.56      0.65      0.60       350
MODERATE-INTENSITY       0.60      0.54      0.57       350
         SEDENTARY       0.97      0.96      0.96       350
VIGOROUS-INTENSITY       0.94      0.89      0.91       299

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

2025-11-04 12:10:23.222150: 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`.
2025-11-04 12:10:23.233380: 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 00:00:1762254623.246445 1245418 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762254623.250522 1245418 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762254623.260585 1245418 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254623.260603 1245418 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254623.260605 1245418 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254623.260606 1245418 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:10:23.263824: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762254625.608778 1245418 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762254627.023458 1245551 service.cc:152] XLA service 0x7cca8c20a540 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762254627.023504 1245551 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:10:27.061950: 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 00:00:1762254627.179085 1245551 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762254629.488349 1245551 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:14[0m 3s/step - accuracy: 0.2500 - loss: 2.1494
[1m 35/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3352 - loss: 1.8045 
[1m 73/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3715 - loss: 1.6709
[1m115/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4002 - loss: 1.5729
[1m150/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.4181 - loss: 1.5112
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4204 - loss: 1.5034
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 28ms/step - accuracy: 0.4208 - loss: 1.5019 - val_accuracy: 0.7037 - val_loss: 0.6665
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6406 - loss: 0.9271
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6013 - loss: 0.9443 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6067 - loss: 0.9173
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6113 - loss: 0.9040
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6156 - loss: 0.8919 - val_accuracy: 0.7170 - val_loss: 0.6168
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6875 - loss: 0.7382
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6540 - loss: 0.7934 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6566 - loss: 0.7776
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6587 - loss: 0.7698
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6606 - loss: 0.7642 - val_accuracy: 0.7019 - val_loss: 0.6177
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7031 - loss: 0.7215
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6868 - loss: 0.6987 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6883 - loss: 0.6900
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6894 - loss: 0.6889
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6896 - loss: 0.6892 - val_accuracy: 0.7093 - val_loss: 0.6110
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 33ms/step - accuracy: 0.6875 - loss: 0.7534
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6921 - loss: 0.6799 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6956 - loss: 0.6720
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6972 - loss: 0.6694
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6981 - loss: 0.6682 - val_accuracy: 0.7096 - val_loss: 0.6042
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.6719 - loss: 0.7270
[1m 43/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7019 - loss: 0.6723 
[1m 84/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7038 - loss: 0.6612
[1m126/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7064 - loss: 0.6574
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7083 - loss: 0.6549 - val_accuracy: 0.7209 - val_loss: 0.5947
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7500 - loss: 0.6151
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7434 - loss: 0.5814 
[1m 84/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7365 - loss: 0.5960
[1m122/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7325 - loss: 0.6044
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7303 - loss: 0.6082 - val_accuracy: 0.7216 - val_loss: 0.6079
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7812 - loss: 0.4484
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7301 - loss: 0.5930 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7247 - loss: 0.6081
[1m113/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7255 - loss: 0.6118
[1m150/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7271 - loss: 0.6125
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7273 - loss: 0.6125 - val_accuracy: 0.7279 - val_loss: 0.6073
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7969 - loss: 0.4423
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7510 - loss: 0.5672 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7469 - loss: 0.5772
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7436 - loss: 0.5814
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7419 - loss: 0.5837 - val_accuracy: 0.7216 - val_loss: 0.6256
Epoch 10/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7344 - loss: 0.5982
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7509 - loss: 0.5673 
[1m 74/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7525 - loss: 0.5671
[1m114/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7536 - loss: 0.5667
[1m152/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7539 - loss: 0.5665
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7539 - loss: 0.5664 - val_accuracy: 0.7219 - val_loss: 0.6211
Epoch 11/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7812 - loss: 0.5198
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7533 - loss: 0.5455 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7611 - loss: 0.5406
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7644 - loss: 0.5404
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7646 - loss: 0.5432 - val_accuracy: 0.7321 - val_loss: 0.6276

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 341ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 8: 75.39 [%]
F1-score capturado en la ejecución 8: 76.2 [%]

=== EJECUCIÓN 9 ===

--- TRAIN (ejecución 9) ---

--- TEST (ejecución 9) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:46[0m 927ms/step
[1m 70/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 726us/step  
[1m140/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 722us/step
[1m209/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 725us/step
[1m277/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 729us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m61/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 839us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 949us/step
Global accuracy score (validation) = 74.79 [%]
Global F1 score (validation) = 75.26 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[6.75502121e-01 3.22776169e-01 5.95440157e-04 1.12630171e-03]
 [7.31878161e-01 1.57867789e-01 9.08932164e-02 1.93608012e-02]
 [6.28528416e-01 3.70516986e-01 3.86137399e-04 5.68390707e-04]
 ...
 [2.46307427e-05 1.01368809e-04 1.25896389e-04 9.99748051e-01]
 [1.42610315e-05 8.13541919e-05 7.09636588e-05 9.99833345e-01]
 [1.42058264e-02 2.37059146e-02 2.75188684e-01 6.86899662e-01]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 80.13 [%]
Global accuracy score (test) = 73.02 [%]
Global F1 score (train) = 80.19 [%]
Global F1 score (test) = 73.66 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.51      0.71      0.59       350
MODERATE-INTENSITY       0.59      0.40      0.48       350
         SEDENTARY       0.98      0.93      0.96       350
VIGOROUS-INTENSITY       0.94      0.90      0.92       299

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

2025-11-04 12:10:47.225460: 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`.
2025-11-04 12:10:47.236870: 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 00:00:1762254647.250161 1247400 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762254647.254118 1247400 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762254647.264356 1247400 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254647.264376 1247400 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254647.264378 1247400 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254647.264379 1247400 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:10:47.267383: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762254649.611464 1247400 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762254651.019660 1247530 service.cc:152] XLA service 0x72042401c440 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762254651.019689 1247530 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:10:51.061618: 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 00:00:1762254651.179984 1247530 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762254653.444011 1247530 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:09[0m 3s/step - accuracy: 0.2031 - loss: 2.2688
[1m 34/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3455 - loss: 1.8223 
[1m 74/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3787 - loss: 1.6831
[1m115/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4049 - loss: 1.5869
[1m153/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.4239 - loss: 1.5179
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4249 - loss: 1.5147
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 28ms/step - accuracy: 0.4253 - loss: 1.5131 - val_accuracy: 0.6861 - val_loss: 0.6811
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.6250 - loss: 0.8451
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.5935 - loss: 0.9308 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6041 - loss: 0.9128
[1m124/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6116 - loss: 0.8981
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6163 - loss: 0.8888 - val_accuracy: 0.6998 - val_loss: 0.6305
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.4844 - loss: 0.9062
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6608 - loss: 0.7575 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6686 - loss: 0.7495
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6706 - loss: 0.7475
[1m151/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6722 - loss: 0.7454
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6724 - loss: 0.7451 - val_accuracy: 0.7135 - val_loss: 0.6040
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 24ms/step - accuracy: 0.6406 - loss: 0.7839
[1m 34/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6814 - loss: 0.6893 
[1m 72/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6876 - loss: 0.6833
[1m112/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6892 - loss: 0.6842
[1m150/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6911 - loss: 0.6842
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6913 - loss: 0.6843 - val_accuracy: 0.7072 - val_loss: 0.6113
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6719 - loss: 0.7134
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7018 - loss: 0.6782 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7037 - loss: 0.6735
[1m115/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7042 - loss: 0.6696
[1m154/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7040 - loss: 0.6693
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7040 - loss: 0.6693 - val_accuracy: 0.7124 - val_loss: 0.6214
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6406 - loss: 0.6839
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7127 - loss: 0.6512 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7166 - loss: 0.6447
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7187 - loss: 0.6393
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7195 - loss: 0.6374 - val_accuracy: 0.7128 - val_loss: 0.6298
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.6562 - loss: 0.7179
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7198 - loss: 0.6098 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7185 - loss: 0.6146
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7199 - loss: 0.6158
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7217 - loss: 0.6149 - val_accuracy: 0.7110 - val_loss: 0.6225
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7188 - loss: 0.6607
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7286 - loss: 0.5919 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7292 - loss: 0.5977
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7320 - loss: 0.5988
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7335 - loss: 0.5990 - val_accuracy: 0.7286 - val_loss: 0.6212

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 343ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 9: 73.02 [%]
F1-score capturado en la ejecución 9: 73.66 [%]

=== EJECUCIÓN 10 ===

--- TRAIN (ejecución 10) ---

--- TEST (ejecución 10) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5:00[0m 973ms/step
[1m 70/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 734us/step  
[1m140/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 724us/step
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 714us/step
[1m290/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 696us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m71/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 715us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 846us/step
Global accuracy score (validation) = 72.96 [%]
Global F1 score (validation) = 73.12 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[5.4227155e-01 4.5591807e-01 4.3743761e-04 1.3729680e-03]
 [5.3518248e-01 4.5728195e-01 4.6722954e-03 2.8633005e-03]
 [3.9220613e-01 5.9940428e-01 6.3603063e-04 7.7536390e-03]
 ...
 [8.4818836e-05 2.1223555e-04 3.9358620e-04 9.9930930e-01]
 [5.6349028e-05 1.1872591e-04 6.7098637e-04 9.9915397e-01]
 [2.0461518e-02 1.8340571e-02 6.8594551e-01 2.7525243e-01]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 77.43 [%]
Global accuracy score (test) = 73.24 [%]
Global F1 score (train) = 77.18 [%]
Global F1 score (test) = 73.08 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.55      0.36      0.44       350
MODERATE-INTENSITY       0.55      0.76      0.64       350
         SEDENTARY       0.94      0.95      0.94       350
VIGOROUS-INTENSITY       0.93      0.89      0.91       299

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

2025-11-04 12:11:10.295280: 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`.
2025-11-04 12:11:10.306521: 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 00:00:1762254670.319703 1249088 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762254670.323620 1249088 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762254670.333621 1249088 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254670.333639 1249088 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254670.333641 1249088 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254670.333642 1249088 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:11:10.336759: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762254672.650312 1249088 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762254674.060428 1249219 service.cc:152] XLA service 0x70737000b1c0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762254674.060466 1249219 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:11:14.102358: 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 00:00:1762254674.225844 1249219 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762254676.468695 1249219 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:05[0m 3s/step - accuracy: 0.1094 - loss: 2.5413
[1m 35/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3619 - loss: 1.7917 
[1m 74/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3891 - loss: 1.6695
[1m108/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4072 - loss: 1.5949
[1m148/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.4243 - loss: 1.5262
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 15ms/step - accuracy: 0.4270 - loss: 1.5156
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 27ms/step - accuracy: 0.4274 - loss: 1.5142 - val_accuracy: 0.6735 - val_loss: 0.6997
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 23ms/step - accuracy: 0.5312 - loss: 0.9413
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.5873 - loss: 0.9485 
[1m 84/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.5935 - loss: 0.9337
[1m124/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6015 - loss: 0.9167
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6067 - loss: 0.9047 - val_accuracy: 0.6987 - val_loss: 0.6161
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 24ms/step - accuracy: 0.6562 - loss: 0.8578
[1m 36/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6564 - loss: 0.7877 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6607 - loss: 0.7653
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6629 - loss: 0.7577
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6644 - loss: 0.7535 - val_accuracy: 0.7184 - val_loss: 0.6020
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7500 - loss: 0.6564
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6914 - loss: 0.6935 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6898 - loss: 0.6948
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6915 - loss: 0.6917
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6921 - loss: 0.6901 - val_accuracy: 0.7170 - val_loss: 0.6064
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7500 - loss: 0.5646
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7006 - loss: 0.6449 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7024 - loss: 0.6452
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7009 - loss: 0.6505
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7001 - loss: 0.6537 - val_accuracy: 0.7149 - val_loss: 0.6116
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7031 - loss: 0.5813
[1m 33/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7098 - loss: 0.6357 
[1m 74/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7128 - loss: 0.6375
[1m113/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7131 - loss: 0.6392
[1m152/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7131 - loss: 0.6396
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7131 - loss: 0.6396 - val_accuracy: 0.7331 - val_loss: 0.5870
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7031 - loss: 0.7008
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7293 - loss: 0.6618 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7311 - loss: 0.6433
[1m116/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7317 - loss: 0.6332
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7311 - loss: 0.6276 - val_accuracy: 0.7219 - val_loss: 0.6054
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6875 - loss: 0.5760
[1m 35/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7155 - loss: 0.6415 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7203 - loss: 0.6231
[1m116/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7234 - loss: 0.6151
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7254 - loss: 0.6115 - val_accuracy: 0.7391 - val_loss: 0.5918
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 24ms/step - accuracy: 0.7031 - loss: 0.6484
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7573 - loss: 0.5786 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7523 - loss: 0.5780
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7500 - loss: 0.5789
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7480 - loss: 0.5808 - val_accuracy: 0.7293 - val_loss: 0.6225
Epoch 10/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7500 - loss: 0.5514
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7374 - loss: 0.5844 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7418 - loss: 0.5844
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7449 - loss: 0.5834
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7465 - loss: 0.5825 - val_accuracy: 0.7360 - val_loss: 0.6105
Epoch 11/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6875 - loss: 0.6730
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7547 - loss: 0.5702 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7603 - loss: 0.5666
[1m122/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7615 - loss: 0.5646
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7614 - loss: 0.5643 - val_accuracy: 0.7237 - val_loss: 0.6742

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 350ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 10: 73.24 [%]
F1-score capturado en la ejecución 10: 73.08 [%]

=== EJECUCIÓN 11 ===

--- TRAIN (ejecución 11) ---

--- TEST (ejecución 11) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:44[0m 919ms/step
[1m 62/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 834us/step  
[1m133/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 768us/step
[1m206/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 740us/step
[1m271/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 749us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m64/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 800us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 905us/step
Global accuracy score (validation) = 71.52 [%]
Global F1 score (validation) = 72.35 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[2.8147703e-01 7.1192980e-01 4.0695554e-04 6.1861901e-03]
 [4.0066841e-01 5.9745109e-01 4.7934966e-04 1.4011763e-03]
 [7.2577566e-01 2.0323545e-01 5.4503199e-02 1.6485646e-02]
 ...
 [1.7451353e-05 8.5907006e-05 1.8131598e-04 9.9971527e-01]
 [3.2118354e-05 1.4945221e-04 3.3639112e-04 9.9948204e-01]
 [5.7383543e-03 4.5613181e-03 9.8075712e-01 8.9432113e-03]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 79.6 [%]
Global accuracy score (test) = 75.17 [%]
Global F1 score (train) = 79.92 [%]
Global F1 score (test) = 75.99 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.57      0.63      0.60       350
MODERATE-INTENSITY       0.61      0.59      0.60       350
         SEDENTARY       0.93      0.96      0.94       350
VIGOROUS-INTENSITY       0.97      0.84      0.90       299

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

2025-11-04 12:11:34.144632: 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`.
2025-11-04 12:11:34.155654: 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 00:00:1762254694.168711 1251064 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762254694.172804 1251064 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762254694.182447 1251064 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254694.182463 1251064 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254694.182464 1251064 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254694.182465 1251064 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:11:34.185562: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762254696.499874 1251064 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762254697.892718 1251196 service.cc:152] XLA service 0x73089c20a720 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762254697.892747 1251196 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:11:37.929314: 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 00:00:1762254698.055812 1251196 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762254700.386403 1251196 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:17[0m 3s/step - accuracy: 0.2656 - loss: 2.3385
[1m 32/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3602 - loss: 1.8029 
[1m 69/155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3956 - loss: 1.6505
[1m109/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4168 - loss: 1.5592
[1m148/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.4337 - loss: 1.4944
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4364 - loss: 1.4843
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 28ms/step - accuracy: 0.4368 - loss: 1.4829 - val_accuracy: 0.6973 - val_loss: 0.6773
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.6094 - loss: 0.7328
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6201 - loss: 0.8765 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6194 - loss: 0.8827
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6212 - loss: 0.8784
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6233 - loss: 0.8720 - val_accuracy: 0.7026 - val_loss: 0.6218
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7031 - loss: 0.6964
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6617 - loss: 0.7884 
[1m 72/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6616 - loss: 0.7762
[1m109/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6637 - loss: 0.7653
[1m151/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6666 - loss: 0.7570
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6670 - loss: 0.7562 - val_accuracy: 0.7135 - val_loss: 0.6278
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7656 - loss: 0.5317
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7026 - loss: 0.6657 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6951 - loss: 0.6883
[1m116/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6915 - loss: 0.6960
[1m153/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6896 - loss: 0.6991
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6895 - loss: 0.6991 - val_accuracy: 0.7138 - val_loss: 0.6138
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7656 - loss: 0.5440
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7220 - loss: 0.6246 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7164 - loss: 0.6393
[1m110/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7123 - loss: 0.6453
[1m149/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7102 - loss: 0.6497
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7099 - loss: 0.6504 - val_accuracy: 0.7177 - val_loss: 0.6010
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 23ms/step - accuracy: 0.7500 - loss: 0.5492
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7246 - loss: 0.6287 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7197 - loss: 0.6375
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7192 - loss: 0.6412
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7190 - loss: 0.6406 - val_accuracy: 0.7226 - val_loss: 0.6043
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7188 - loss: 0.5812
[1m 43/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7156 - loss: 0.5916 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7168 - loss: 0.6053
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7194 - loss: 0.6083
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7205 - loss: 0.6100 - val_accuracy: 0.7205 - val_loss: 0.6095
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 26ms/step - accuracy: 0.7188 - loss: 0.6474
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7306 - loss: 0.6159 
[1m 73/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7330 - loss: 0.6136
[1m113/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7335 - loss: 0.6136
[1m149/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7345 - loss: 0.6112
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7346 - loss: 0.6107 - val_accuracy: 0.7331 - val_loss: 0.6125
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 25ms/step - accuracy: 0.7344 - loss: 0.5745
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7522 - loss: 0.5512 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7517 - loss: 0.5621
[1m115/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7504 - loss: 0.5690
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.7487 - loss: 0.5742
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7486 - loss: 0.5743 - val_accuracy: 0.7282 - val_loss: 0.6396
Epoch 10/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7188 - loss: 0.6318
[1m 43/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7512 - loss: 0.5925 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7514 - loss: 0.5910
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7515 - loss: 0.5881
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7521 - loss: 0.5851 - val_accuracy: 0.7286 - val_loss: 0.6429

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 373ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 11: 75.17 [%]
F1-score capturado en la ejecución 11: 75.99 [%]

=== EJECUCIÓN 12 ===

--- TRAIN (ejecución 12) ---

--- TEST (ejecución 12) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:59[0m 968ms/step
[1m 51/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step    
[1m127/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 798us/step
[1m199/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 762us/step
[1m270/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 748us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 17ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m71/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 716us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 874us/step
Global accuracy score (validation) = 72.19 [%]
Global F1 score (validation) = 72.86 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[6.36981130e-01 1.65295392e-01 1.75007179e-01 2.27162950e-02]
 [7.62376606e-01 2.34273449e-01 2.14612880e-03 1.20388169e-03]
 [3.10339093e-01 6.83774710e-01 2.75748869e-04 5.61040407e-03]
 ...
 [2.47446569e-05 1.06167805e-04 3.44587344e-04 9.99524415e-01]
 [1.52978537e-05 5.29219178e-05 3.25456436e-04 9.99606252e-01]
 [3.54396855e-03 2.55719339e-03 9.54624414e-01 3.92744951e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 79.41 [%]
Global accuracy score (test) = 73.39 [%]
Global F1 score (train) = 79.61 [%]
Global F1 score (test) = 74.33 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.54      0.61      0.57       350
MODERATE-INTENSITY       0.57      0.54      0.56       350
         SEDENTARY       0.93      0.95      0.94       350
VIGOROUS-INTENSITY       0.97      0.85      0.90       299

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

2025-11-04 12:11:57.875933: 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`.
2025-11-04 12:11:57.887151: 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 00:00:1762254717.900243 1252948 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762254717.904282 1252948 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762254717.913939 1252948 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254717.913956 1252948 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254717.913957 1252948 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254717.913958 1252948 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:11:57.917063: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762254720.239919 1252948 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762254721.642221 1253049 service.cc:152] XLA service 0x7b729c006490 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762254721.642253 1253049 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:12:01.680302: 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 00:00:1762254721.797864 1253049 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762254724.106995 1253049 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:14[0m 3s/step - accuracy: 0.2188 - loss: 2.2915
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3489 - loss: 1.7815 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3884 - loss: 1.6489
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4127 - loss: 1.5577
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 15ms/step - accuracy: 0.4295 - loss: 1.4979
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 27ms/step - accuracy: 0.4300 - loss: 1.4965 - val_accuracy: 0.6742 - val_loss: 0.6912
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 26ms/step - accuracy: 0.5625 - loss: 1.0097
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6069 - loss: 0.9396 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6098 - loss: 0.9259
[1m116/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6116 - loss: 0.9136
[1m153/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6137 - loss: 0.9045
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6138 - loss: 0.9038 - val_accuracy: 0.7065 - val_loss: 0.6166
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7031 - loss: 0.6995
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6758 - loss: 0.7504 
[1m 72/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6747 - loss: 0.7466
[1m110/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6733 - loss: 0.7445
[1m150/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6724 - loss: 0.7424
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6723 - loss: 0.7420 - val_accuracy: 0.7022 - val_loss: 0.6130
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6562 - loss: 0.6303
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6839 - loss: 0.6904 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6851 - loss: 0.6920
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6864 - loss: 0.6923
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6864 - loss: 0.6934 - val_accuracy: 0.7079 - val_loss: 0.6116
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7656 - loss: 0.6593
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7040 - loss: 0.6520 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7012 - loss: 0.6613
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7012 - loss: 0.6628
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7016 - loss: 0.6632 - val_accuracy: 0.7107 - val_loss: 0.6058
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 26ms/step - accuracy: 0.6719 - loss: 0.7204
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7043 - loss: 0.6520 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7068 - loss: 0.6508
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7078 - loss: 0.6485
[1m149/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7082 - loss: 0.6477
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7083 - loss: 0.6477 - val_accuracy: 0.7100 - val_loss: 0.6221
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6719 - loss: 0.5921
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7303 - loss: 0.5957 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7312 - loss: 0.6011
[1m125/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7301 - loss: 0.6060
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7293 - loss: 0.6090 - val_accuracy: 0.7121 - val_loss: 0.6190
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.8281 - loss: 0.4402
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7293 - loss: 0.5751 
[1m 78/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7295 - loss: 0.5855
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7298 - loss: 0.5913
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7301 - loss: 0.5939 - val_accuracy: 0.7258 - val_loss: 0.6081
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 23ms/step - accuracy: 0.7812 - loss: 0.4943
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7481 - loss: 0.5805 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7461 - loss: 0.5853
[1m115/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7455 - loss: 0.5857
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7448 - loss: 0.5878 - val_accuracy: 0.7202 - val_loss: 0.6183
Epoch 10/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7969 - loss: 0.4898
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7612 - loss: 0.5653 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7582 - loss: 0.5700
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7575 - loss: 0.5704
[1m154/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7568 - loss: 0.5718
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7567 - loss: 0.5719 - val_accuracy: 0.7360 - val_loss: 0.6067

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 347ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 12: 73.39 [%]
F1-score capturado en la ejecución 12: 74.33 [%]

=== EJECUCIÓN 13 ===

--- TRAIN (ejecución 13) ---

--- TEST (ejecución 13) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:56[0m 961ms/step
[1m 66/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 772us/step  
[1m138/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 731us/step
[1m212/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 714us/step
[1m284/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 710us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/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) = 73.49 [%]
Global F1 score (validation) = 74.51 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[5.4317361e-01 4.5465478e-01 9.1862521e-04 1.2530083e-03]
 [3.4161004e-01 6.5759623e-01 7.9208301e-05 7.1452936e-04]
 [6.3008547e-01 2.4625325e-01 9.1307350e-02 3.2353945e-02]
 ...
 [3.4891207e-05 1.3866811e-04 2.0641812e-04 9.9961996e-01]
 [2.8387820e-05 8.1408936e-05 2.8053121e-04 9.9960971e-01]
 [5.4462673e-03 3.4354599e-03 8.1481874e-01 1.7629942e-01]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 79.31 [%]
Global accuracy score (test) = 75.83 [%]
Global F1 score (train) = 79.62 [%]
Global F1 score (test) = 76.9 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.57      0.62      0.59       350
MODERATE-INTENSITY       0.59      0.59      0.59       350
         SEDENTARY       0.98      0.95      0.96       350
VIGOROUS-INTENSITY       0.97      0.90      0.93       299

          accuracy                           0.76      1349
         macro avg       0.78      0.76      0.77      1349
      weighted avg       0.77      0.76      0.76      1349

2025-11-04 12:12:21.548836: 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`.
2025-11-04 12:12:21.560537: 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 00:00:1762254741.573648 1254839 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762254741.577704 1254839 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762254741.587573 1254839 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254741.587591 1254839 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254741.587592 1254839 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254741.587594 1254839 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:12:21.590500: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762254743.886983 1254839 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762254745.312843 1254950 service.cc:152] XLA service 0x7aaf7801ac10 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762254745.312875 1254950 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:12:25.349050: 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 00:00:1762254745.467158 1254950 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762254747.733786 1254950 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:11[0m 3s/step - accuracy: 0.1875 - loss: 2.1023
[1m 34/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3384 - loss: 1.7696 
[1m 70/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3788 - loss: 1.6388
[1m110/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4063 - loss: 1.5452
[1m145/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.4251 - loss: 1.4821
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4297 - loss: 1.4664
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 28ms/step - accuracy: 0.4301 - loss: 1.4649 - val_accuracy: 0.6791 - val_loss: 0.6982
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.5625 - loss: 0.8344
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.5880 - loss: 0.9281 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.5940 - loss: 0.9215
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6017 - loss: 0.9044
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.6085 - loss: 0.8890
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6087 - loss: 0.8886 - val_accuracy: 0.7040 - val_loss: 0.6108
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7031 - loss: 0.7215
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6726 - loss: 0.7510 
[1m 68/155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6690 - loss: 0.7478
[1m108/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6688 - loss: 0.7456
[1m149/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6698 - loss: 0.7447
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6700 - loss: 0.7447 - val_accuracy: 0.7037 - val_loss: 0.6153
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7344 - loss: 0.6353
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6999 - loss: 0.6950 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6959 - loss: 0.6960
[1m122/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6950 - loss: 0.6965
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6955 - loss: 0.6948 - val_accuracy: 0.7061 - val_loss: 0.6074
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7344 - loss: 0.5720
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6969 - loss: 0.6765 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7005 - loss: 0.6702
[1m112/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7022 - loss: 0.6681
[1m145/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.7025 - loss: 0.6673
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7026 - loss: 0.6671 - val_accuracy: 0.7114 - val_loss: 0.6122
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7344 - loss: 0.5993
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7171 - loss: 0.6325 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7182 - loss: 0.6361
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7192 - loss: 0.6346
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7201 - loss: 0.6340 - val_accuracy: 0.7015 - val_loss: 0.6221
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7500 - loss: 0.7499
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7420 - loss: 0.6033 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7395 - loss: 0.6041
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7379 - loss: 0.6083
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7370 - loss: 0.6099 - val_accuracy: 0.7282 - val_loss: 0.5962
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7344 - loss: 0.5532
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7614 - loss: 0.5755 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7517 - loss: 0.5880
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7483 - loss: 0.5920
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7464 - loss: 0.5940 - val_accuracy: 0.7377 - val_loss: 0.6076
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7656 - loss: 0.4594
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7307 - loss: 0.5806 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7379 - loss: 0.5799
[1m122/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7405 - loss: 0.5807
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7416 - loss: 0.5808 - val_accuracy: 0.7177 - val_loss: 0.6199
Epoch 10/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.8125 - loss: 0.5123
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7720 - loss: 0.5754 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7658 - loss: 0.5761
[1m116/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7631 - loss: 0.5763
[1m154/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7619 - loss: 0.5756
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7618 - loss: 0.5756 - val_accuracy: 0.7272 - val_loss: 0.6152
Epoch 11/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7031 - loss: 0.6225
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7597 - loss: 0.5438 
[1m 73/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7664 - loss: 0.5407
[1m108/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7668 - loss: 0.5425
[1m148/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7666 - loss: 0.5449
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7666 - loss: 0.5454 - val_accuracy: 0.7244 - val_loss: 0.6231
Epoch 12/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7656 - loss: 0.5535
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7821 - loss: 0.5242 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7809 - loss: 0.5305
[1m122/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7802 - loss: 0.5331
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7789 - loss: 0.5357 - val_accuracy: 0.7258 - val_loss: 0.6361

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 362ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 13: 75.83 [%]
F1-score capturado en la ejecución 13: 76.9 [%]

=== EJECUCIÓN 14 ===

--- TRAIN (ejecución 14) ---

--- TEST (ejecución 14) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:39[0m 905ms/step
[1m 71/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 717us/step  
[1m147/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 690us/step
[1m218/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 697us/step
[1m293/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 691us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m68/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 754us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 877us/step
Global accuracy score (validation) = 72.51 [%]
Global F1 score (validation) = 73.56 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[6.4949793e-01 1.3861512e-01 1.8135805e-01 3.0528871e-02]
 [4.1813901e-01 5.7882279e-01 6.3045701e-04 2.4077836e-03]
 [5.4180986e-01 4.5490485e-01 1.2196959e-03 2.0656358e-03]
 ...
 [1.3245570e-05 7.5025455e-05 9.0674810e-05 9.9982107e-01]
 [4.1486030e-05 3.0364524e-04 1.4889697e-04 9.9950600e-01]
 [2.1889018e-02 3.2160394e-02 8.5243142e-01 9.3519226e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 81.32 [%]
Global accuracy score (test) = 72.94 [%]
Global F1 score (train) = 81.66 [%]
Global F1 score (test) = 73.99 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.53      0.58      0.55       350
MODERATE-INTENSITY       0.55      0.55      0.55       350
         SEDENTARY       0.94      0.95      0.95       350
VIGOROUS-INTENSITY       0.97      0.86      0.91       299

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

2025-11-04 12:12:45.769157: 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`.
2025-11-04 12:12:45.780982: 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 00:00:1762254765.794564 1256883 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762254765.798799 1256883 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762254765.808908 1256883 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254765.808928 1256883 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254765.808929 1256883 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254765.808930 1256883 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:12:45.812194: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762254768.125749 1256883 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762254769.551145 1257016 service.cc:152] XLA service 0x7302a820a0e0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762254769.551172 1257016 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:12:49.584517: 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 00:00:1762254769.706368 1257016 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762254772.045038 1257016 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:22[0m 3s/step - accuracy: 0.1406 - loss: 2.2313
[1m 34/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3490 - loss: 1.7932 
[1m 73/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3861 - loss: 1.6572
[1m115/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4084 - loss: 1.5694
[1m149/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.4234 - loss: 1.5130
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4259 - loss: 1.5040
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m8s[0m 28ms/step - accuracy: 0.4263 - loss: 1.5026 - val_accuracy: 0.6886 - val_loss: 0.6908
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.5938 - loss: 1.0964
[1m 36/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6032 - loss: 0.9543 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6072 - loss: 0.9358
[1m115/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6116 - loss: 0.9194
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6154 - loss: 0.9053 - val_accuracy: 0.7061 - val_loss: 0.6042
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7656 - loss: 0.6368
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6766 - loss: 0.7629 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6765 - loss: 0.7600
[1m114/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6776 - loss: 0.7528
[1m153/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6781 - loss: 0.7482
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6782 - loss: 0.7479 - val_accuracy: 0.7180 - val_loss: 0.5890
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7188 - loss: 0.6531
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6951 - loss: 0.6979 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6974 - loss: 0.6915
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6959 - loss: 0.6930
[1m154/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6943 - loss: 0.6943
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6943 - loss: 0.6943 - val_accuracy: 0.7170 - val_loss: 0.5972
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7188 - loss: 0.6214
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7108 - loss: 0.6506 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7082 - loss: 0.6559
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7076 - loss: 0.6602
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7075 - loss: 0.6611 - val_accuracy: 0.7296 - val_loss: 0.5938
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7500 - loss: 0.6810
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7216 - loss: 0.6384 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7195 - loss: 0.6444
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7175 - loss: 0.6474
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7164 - loss: 0.6475 - val_accuracy: 0.7184 - val_loss: 0.6161
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6562 - loss: 0.6104
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6962 - loss: 0.6413 
[1m 74/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7076 - loss: 0.6303
[1m112/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7109 - loss: 0.6265
[1m151/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7128 - loss: 0.6261
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7130 - loss: 0.6261 - val_accuracy: 0.7128 - val_loss: 0.6012
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.8281 - loss: 0.5053
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7305 - loss: 0.6071 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7246 - loss: 0.6162
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7247 - loss: 0.6177
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7265 - loss: 0.6156 - val_accuracy: 0.7188 - val_loss: 0.6229

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 345ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 14: 72.94 [%]
F1-score capturado en la ejecución 14: 73.99 [%]

=== EJECUCIÓN 15 ===

--- TRAIN (ejecución 15) ---

--- TEST (ejecución 15) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:44[0m 920ms/step
[1m 70/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 734us/step  
[1m132/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 774us/step
[1m192/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 794us/step
[1m257/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 791us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m68/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 749us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 876us/step
Global accuracy score (validation) = 71.59 [%]
Global F1 score (validation) = 72.34 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[5.7960218e-01 4.2013910e-01 8.0143072e-05 1.7858349e-04]
 [6.2504971e-01 1.6938095e-01 1.6832028e-01 3.7249021e-02]
 [6.2773347e-01 1.7198843e-01 1.6311432e-01 3.7163842e-02]
 ...
 [4.6903286e-05 1.0105056e-04 7.0659432e-04 9.9914551e-01]
 [4.6917896e-05 9.5638956e-05 5.1882543e-04 9.9933857e-01]
 [6.0980693e-03 3.0703547e-03 9.6236849e-01 2.8463047e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 77.2 [%]
Global accuracy score (test) = 72.94 [%]
Global F1 score (train) = 77.54 [%]
Global F1 score (test) = 74.27 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.53      0.65      0.58       350
MODERATE-INTENSITY       0.60      0.56      0.58       350
         SEDENTARY       0.93      0.87      0.90       350
VIGOROUS-INTENSITY       0.97      0.85      0.91       299

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

2025-11-04 12:13:08.802175: 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`.
2025-11-04 12:13:08.813272: 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 00:00:1762254788.827028 1258593 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762254788.831410 1258593 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762254788.841928 1258593 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254788.841947 1258593 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254788.841949 1258593 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254788.841950 1258593 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:13:08.845284: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762254791.174317 1258593 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762254792.578168 1258704 service.cc:152] XLA service 0x7c2e90003fa0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762254792.578218 1258704 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:13:12.616755: 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 00:00:1762254792.743906 1258704 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762254795.062646 1258704 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:17[0m 3s/step - accuracy: 0.3125 - loss: 1.8850
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3657 - loss: 1.7332 
[1m 78/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3975 - loss: 1.6231
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4192 - loss: 1.5424
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 15ms/step - accuracy: 0.4367 - loss: 1.4789
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 27ms/step - accuracy: 0.4371 - loss: 1.4774 - val_accuracy: 0.6921 - val_loss: 0.6734
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.6562 - loss: 0.8934
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6357 - loss: 0.9035 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6348 - loss: 0.8901
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6366 - loss: 0.8792
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6382 - loss: 0.8705 - val_accuracy: 0.7103 - val_loss: 0.5923
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.5781 - loss: 0.8092
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6504 - loss: 0.7534 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6576 - loss: 0.7478
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6611 - loss: 0.7464
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6625 - loss: 0.7452 - val_accuracy: 0.7103 - val_loss: 0.5991
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.6406 - loss: 0.6903
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6844 - loss: 0.7109 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6850 - loss: 0.7059
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6850 - loss: 0.7043
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.6848 - loss: 0.7027
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6848 - loss: 0.7027 - val_accuracy: 0.7089 - val_loss: 0.6045
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6250 - loss: 0.6853
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6983 - loss: 0.6515 
[1m 74/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6999 - loss: 0.6532
[1m109/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7013 - loss: 0.6518
[1m147/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.7018 - loss: 0.6522
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7018 - loss: 0.6525 - val_accuracy: 0.7258 - val_loss: 0.5880
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.8438 - loss: 0.4794
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7481 - loss: 0.6093 
[1m 78/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7414 - loss: 0.6151
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7358 - loss: 0.6210
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7331 - loss: 0.6240 - val_accuracy: 0.7223 - val_loss: 0.5844
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7656 - loss: 0.5541
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7206 - loss: 0.6021 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7227 - loss: 0.6082
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7251 - loss: 0.6098
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7259 - loss: 0.6121 - val_accuracy: 0.7219 - val_loss: 0.5912
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.8281 - loss: 0.5330
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7384 - loss: 0.6165 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7385 - loss: 0.6083
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7381 - loss: 0.6060
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7382 - loss: 0.6049 - val_accuracy: 0.7261 - val_loss: 0.5942
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7969 - loss: 0.5549
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7428 - loss: 0.5942 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7443 - loss: 0.5899
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7452 - loss: 0.5868
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7449 - loss: 0.5872 - val_accuracy: 0.7212 - val_loss: 0.5934
Epoch 10/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6406 - loss: 0.8684
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7384 - loss: 0.6101 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7434 - loss: 0.5976
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7451 - loss: 0.5914
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7457 - loss: 0.5894 - val_accuracy: 0.7275 - val_loss: 0.5951
Epoch 11/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.8125 - loss: 0.4564
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7796 - loss: 0.5462 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7767 - loss: 0.5501
[1m116/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7744 - loss: 0.5527
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.7729 - loss: 0.5547
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7728 - loss: 0.5548 - val_accuracy: 0.7356 - val_loss: 0.6009

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 356ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 15: 72.94 [%]
F1-score capturado en la ejecución 15: 74.27 [%]

=== EJECUCIÓN 16 ===

--- TRAIN (ejecución 16) ---

--- TEST (ejecución 16) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:53[0m 950ms/step
[1m 52/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 984us/step  
[1m127/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 800us/step
[1m198/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 767us/step
[1m276/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 733us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m62/89[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 821us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 931us/step
Global accuracy score (validation) = 73.46 [%]
Global F1 score (validation) = 74.24 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[7.1610987e-01 2.8307849e-01 4.6513771e-04 3.4645869e-04]
 [4.9484491e-01 5.0419766e-01 2.8226903e-04 6.7510479e-04]
 [3.2497087e-01 6.7390686e-01 2.0976974e-04 9.1254659e-04]
 ...
 [1.6617487e-05 1.2181004e-04 9.1046808e-05 9.9977058e-01]
 [1.1586502e-05 6.0861450e-05 8.3356725e-05 9.9984407e-01]
 [1.1387837e-02 1.1228245e-02 8.6985451e-01 1.0752943e-01]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 80.31 [%]
Global accuracy score (test) = 75.02 [%]
Global F1 score (train) = 80.53 [%]
Global F1 score (test) = 75.92 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.55      0.63      0.58       350
MODERATE-INTENSITY       0.59      0.55      0.57       350
         SEDENTARY       0.97      0.96      0.97       350
VIGOROUS-INTENSITY       0.95      0.89      0.92       299

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

2025-11-04 12:13:32.817742: 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`.
2025-11-04 12:13:32.828975: 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 00:00:1762254812.842182 1260565 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762254812.846160 1260565 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762254812.856224 1260565 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254812.856240 1260565 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254812.856241 1260565 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254812.856242 1260565 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:13:32.859165: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762254815.169650 1260565 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762254816.568911 1260681 service.cc:152] XLA service 0x7de9e400b2d0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762254816.568940 1260681 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:13:36.603543: 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 00:00:1762254816.724007 1260681 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762254818.958476 1260681 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:02[0m 3s/step - accuracy: 0.1562 - loss: 2.4785
[1m 28/155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3288 - loss: 1.8919 
[1m 68/155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3737 - loss: 1.7072
[1m107/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4020 - loss: 1.6019
[1m147/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.4240 - loss: 1.5235
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4278 - loss: 1.5101
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 28ms/step - accuracy: 0.4283 - loss: 1.5085 - val_accuracy: 0.6787 - val_loss: 0.6723
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 23ms/step - accuracy: 0.5469 - loss: 1.0609
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.5984 - loss: 0.9507 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6049 - loss: 0.9267
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6097 - loss: 0.9099
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6141 - loss: 0.8968 - val_accuracy: 0.7121 - val_loss: 0.6041
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 24ms/step - accuracy: 0.6875 - loss: 0.9194
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6695 - loss: 0.7613 
[1m 78/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6658 - loss: 0.7634
[1m113/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6662 - loss: 0.7605
[1m152/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6672 - loss: 0.7567
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6672 - loss: 0.7563 - val_accuracy: 0.7040 - val_loss: 0.5884
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6406 - loss: 0.6408
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7098 - loss: 0.6535 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7031 - loss: 0.6669
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6991 - loss: 0.6749
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.6971 - loss: 0.6792
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6970 - loss: 0.6792 - val_accuracy: 0.7135 - val_loss: 0.5861
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6875 - loss: 0.5318
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6993 - loss: 0.6497 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7035 - loss: 0.6519
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7032 - loss: 0.6549
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7037 - loss: 0.6554 - val_accuracy: 0.7163 - val_loss: 0.5979
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6406 - loss: 0.7416
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7179 - loss: 0.6219 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7184 - loss: 0.6252
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7183 - loss: 0.6278
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7184 - loss: 0.6281 - val_accuracy: 0.7166 - val_loss: 0.5893
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6875 - loss: 0.5133
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6888 - loss: 0.6630 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7007 - loss: 0.6490
[1m124/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7073 - loss: 0.6422
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7106 - loss: 0.6387 - val_accuracy: 0.7374 - val_loss: 0.5794
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7188 - loss: 0.6048
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7495 - loss: 0.5838 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7489 - loss: 0.5926
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7467 - loss: 0.5971
[1m153/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7459 - loss: 0.5986
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7459 - loss: 0.5987 - val_accuracy: 0.7346 - val_loss: 0.5921
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.6719 - loss: 0.6931
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7426 - loss: 0.6289 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7490 - loss: 0.6111
[1m113/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7500 - loss: 0.6057
[1m154/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7506 - loss: 0.6010
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7506 - loss: 0.6008 - val_accuracy: 0.7335 - val_loss: 0.5844
Epoch 10/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7812 - loss: 0.6206
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7726 - loss: 0.5923 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7684 - loss: 0.5886
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7668 - loss: 0.5834
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7653 - loss: 0.5799 - val_accuracy: 0.7370 - val_loss: 0.5960
Epoch 11/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7656 - loss: 0.5038
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7690 - loss: 0.5351 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7673 - loss: 0.5472
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7661 - loss: 0.5522
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7658 - loss: 0.5540 - val_accuracy: 0.7279 - val_loss: 0.6041
Epoch 12/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7812 - loss: 0.5960
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7668 - loss: 0.5349 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7665 - loss: 0.5355
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7681 - loss: 0.5356
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7687 - loss: 0.5362 - val_accuracy: 0.7272 - val_loss: 0.6119

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 342ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 16: 75.02 [%]
F1-score capturado en la ejecución 16: 75.92 [%]

=== EJECUCIÓN 17 ===

--- TRAIN (ejecución 17) ---

--- TEST (ejecución 17) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:46[0m 928ms/step
[1m 69/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 739us/step  
[1m145/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 699us/step
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 713us/step
[1m285/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 711us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m65/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 783us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 915us/step
Global accuracy score (validation) = 73.46 [%]
Global F1 score (validation) = 74.06 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[1.3133346e-01 8.6534739e-01 3.6958454e-04 2.9496090e-03]
 [7.7055424e-01 2.2671670e-01 1.4578986e-03 1.2712089e-03]
 [2.9791614e-01 7.0123655e-01 2.1092428e-04 6.3640671e-04]
 ...
 [1.0980964e-05 3.0253734e-05 1.2226208e-04 9.9983644e-01]
 [1.9255167e-05 5.0966140e-05 2.8080426e-04 9.9964893e-01]
 [5.2200598e-03 4.0716105e-03 9.4641012e-01 4.4298176e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 80.21 [%]
Global accuracy score (test) = 74.13 [%]
Global F1 score (train) = 80.42 [%]
Global F1 score (test) = 75.06 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.53      0.61      0.57       350
MODERATE-INTENSITY       0.60      0.56      0.58       350
         SEDENTARY       0.94      0.94      0.94       350
VIGOROUS-INTENSITY       0.95      0.88      0.91       299

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

2025-11-04 12:13:57.069973: 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`.
2025-11-04 12:13:57.081204: 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 00:00:1762254837.094354 1262615 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762254837.098498 1262615 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762254837.108414 1262615 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254837.108431 1262615 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254837.108433 1262615 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254837.108434 1262615 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:13:57.111573: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762254839.421209 1262615 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762254840.827583 1262744 service.cc:152] XLA service 0x703be000bb20 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762254840.827609 1262744 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:14:00.861258: 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 00:00:1762254840.978247 1262744 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762254843.243979 1262744 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:07[0m 3s/step - accuracy: 0.2344 - loss: 2.3783
[1m 33/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3299 - loss: 1.8915 
[1m 74/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3688 - loss: 1.7300
[1m114/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3955 - loss: 1.6293
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4174 - loss: 1.5503
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 28ms/step - accuracy: 0.4179 - loss: 1.5487 - val_accuracy: 0.6871 - val_loss: 0.6745
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 24ms/step - accuracy: 0.5312 - loss: 1.0835
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6043 - loss: 0.9522 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6138 - loss: 0.9250
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6195 - loss: 0.9077
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6233 - loss: 0.8965 - val_accuracy: 0.7051 - val_loss: 0.6319
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.5625 - loss: 0.8818
[1m 36/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6662 - loss: 0.7754 
[1m 74/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6723 - loss: 0.7591
[1m113/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6763 - loss: 0.7521
[1m154/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6779 - loss: 0.7494
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6780 - loss: 0.7492 - val_accuracy: 0.7191 - val_loss: 0.6236
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6562 - loss: 0.6923
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6836 - loss: 0.6721 
[1m 73/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6877 - loss: 0.6743
[1m114/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6906 - loss: 0.6761
[1m153/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6916 - loss: 0.6792
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6917 - loss: 0.6794 - val_accuracy: 0.7131 - val_loss: 0.6211
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7969 - loss: 0.5313
[1m 32/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7283 - loss: 0.6628 
[1m 68/155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7206 - loss: 0.6563
[1m108/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7183 - loss: 0.6558
[1m146/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.7166 - loss: 0.6573
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7164 - loss: 0.6574 - val_accuracy: 0.7184 - val_loss: 0.6093
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6719 - loss: 0.5708
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7085 - loss: 0.6473 
[1m 74/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7138 - loss: 0.6442
[1m113/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7165 - loss: 0.6424
[1m149/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7184 - loss: 0.6412
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7187 - loss: 0.6410 - val_accuracy: 0.7216 - val_loss: 0.6055
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7188 - loss: 0.6903
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7266 - loss: 0.6087 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7318 - loss: 0.6056
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7345 - loss: 0.6043
[1m153/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7346 - loss: 0.6053
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7345 - loss: 0.6055 - val_accuracy: 0.7195 - val_loss: 0.6203
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7031 - loss: 0.5568
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7381 - loss: 0.5930 
[1m 78/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7386 - loss: 0.5950
[1m116/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7380 - loss: 0.5966
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.7381 - loss: 0.5980
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7381 - loss: 0.5981 - val_accuracy: 0.7286 - val_loss: 0.6041
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7344 - loss: 0.5957
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7647 - loss: 0.5508 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7589 - loss: 0.5621
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7554 - loss: 0.5685
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7539 - loss: 0.5716 - val_accuracy: 0.7279 - val_loss: 0.6298
Epoch 10/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6562 - loss: 0.8227
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7551 - loss: 0.5764 
[1m 78/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7603 - loss: 0.5773
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7605 - loss: 0.5786
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7609 - loss: 0.5782 - val_accuracy: 0.7398 - val_loss: 0.6119
Epoch 11/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 23ms/step - accuracy: 0.7812 - loss: 0.5363
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7635 - loss: 0.5656 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7650 - loss: 0.5666
[1m115/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7662 - loss: 0.5645
[1m149/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7666 - loss: 0.5630
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7667 - loss: 0.5628 - val_accuracy: 0.7381 - val_loss: 0.6140
Epoch 12/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7969 - loss: 0.5785
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7751 - loss: 0.5191 
[1m 78/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7722 - loss: 0.5228
[1m116/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7711 - loss: 0.5277
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7711 - loss: 0.5303 - val_accuracy: 0.7226 - val_loss: 0.6461
Epoch 13/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.8438 - loss: 0.5689
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7801 - loss: 0.5474 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7807 - loss: 0.5456
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7806 - loss: 0.5442
[1m152/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7802 - loss: 0.5428
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7802 - loss: 0.5427 - val_accuracy: 0.7219 - val_loss: 0.6633

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 361ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 17: 74.13 [%]
F1-score capturado en la ejecución 17: 75.06 [%]

=== EJECUCIÓN 18 ===

--- TRAIN (ejecución 18) ---

--- TEST (ejecución 18) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:55[0m 957ms/step
[1m 69/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 741us/step  
[1m136/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 748us/step
[1m193/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 787us/step
[1m262/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 771us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m73/89[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 703us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 830us/step
Global accuracy score (validation) = 72.33 [%]
Global F1 score (validation) = 73.15 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[1.9845147e-01 8.0127698e-01 3.6592464e-05 2.3493322e-04]
 [5.9562778e-01 1.5473673e-01 2.1053618e-01 3.9099302e-02]
 [2.1086630e-01 7.8887951e-01 1.8759647e-05 2.3535109e-04]
 ...
 [1.0168360e-05 8.9198322e-05 4.9766088e-05 9.9985087e-01]
 [1.0160251e-05 4.9465878e-05 3.9517149e-04 9.9954516e-01]
 [5.7668732e-03 7.1602091e-03 9.4946963e-01 3.7603181e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 80.67 [%]
Global accuracy score (test) = 74.05 [%]
Global F1 score (train) = 80.96 [%]
Global F1 score (test) = 75.0 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.55      0.51      0.53       350
MODERATE-INTENSITY       0.55      0.63      0.59       350
         SEDENTARY       0.97      0.96      0.96       350
VIGOROUS-INTENSITY       0.97      0.89      0.92       299

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

2025-11-04 12:14:21.818695: 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`.
2025-11-04 12:14:21.830083: 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 00:00:1762254861.843476 1264785 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762254861.847646 1264785 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762254861.857461 1264785 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254861.857479 1264785 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254861.857480 1264785 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254861.857494 1264785 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:14:21.860659: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762254864.201412 1264785 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762254865.608507 1264909 service.cc:152] XLA service 0x70d9d000bbd0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762254865.608552 1264909 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:14:25.642496: 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 00:00:1762254865.760664 1264909 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762254868.082275 1264909 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:17[0m 3s/step - accuracy: 0.2812 - loss: 1.9297
[1m 36/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3701 - loss: 1.7360 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4001 - loss: 1.6197
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4201 - loss: 1.5388
[1m154/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.4364 - loss: 1.4794
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4369 - loss: 1.4778
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m8s[0m 28ms/step - accuracy: 0.4373 - loss: 1.4763 - val_accuracy: 0.6963 - val_loss: 0.6561
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 23ms/step - accuracy: 0.6250 - loss: 0.8499
[1m 36/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6165 - loss: 0.8742 
[1m 75/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6211 - loss: 0.8776
[1m113/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6240 - loss: 0.8766
[1m151/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6275 - loss: 0.8708
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6278 - loss: 0.8700 - val_accuracy: 0.7093 - val_loss: 0.6043
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 25ms/step - accuracy: 0.6562 - loss: 0.9101
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6802 - loss: 0.7497 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6815 - loss: 0.7440
[1m115/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6815 - loss: 0.7402
[1m154/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6808 - loss: 0.7374
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6807 - loss: 0.7373 - val_accuracy: 0.7075 - val_loss: 0.5953
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7344 - loss: 0.7085
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7116 - loss: 0.6646 
[1m 75/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6972 - loss: 0.6774
[1m112/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6932 - loss: 0.6826
[1m151/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6929 - loss: 0.6840
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6929 - loss: 0.6840 - val_accuracy: 0.7075 - val_loss: 0.5972
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7188 - loss: 0.7078
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7057 - loss: 0.6681 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7011 - loss: 0.6730
[1m122/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6999 - loss: 0.6723
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6999 - loss: 0.6707 - val_accuracy: 0.7177 - val_loss: 0.5887
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7656 - loss: 0.5737
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7272 - loss: 0.6339 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7206 - loss: 0.6351
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7181 - loss: 0.6378
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7179 - loss: 0.6383 - val_accuracy: 0.7156 - val_loss: 0.5981
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 29ms/step - accuracy: 0.6719 - loss: 0.7114
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7361 - loss: 0.6240 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7335 - loss: 0.6225
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7324 - loss: 0.6218
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7319 - loss: 0.6209 - val_accuracy: 0.7198 - val_loss: 0.6124
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.8125 - loss: 0.4706
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7470 - loss: 0.5863 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7449 - loss: 0.5889
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7420 - loss: 0.5913
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7410 - loss: 0.5924 - val_accuracy: 0.7335 - val_loss: 0.5857
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7812 - loss: 0.5666
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7417 - loss: 0.5757 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7442 - loss: 0.5782
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7457 - loss: 0.5798
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7462 - loss: 0.5799 - val_accuracy: 0.7293 - val_loss: 0.6231
Epoch 10/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 25ms/step - accuracy: 0.6875 - loss: 0.5259
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7803 - loss: 0.5226 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7752 - loss: 0.5405
[1m116/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7710 - loss: 0.5507
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7675 - loss: 0.5568 - val_accuracy: 0.7402 - val_loss: 0.5984
Epoch 11/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.8125 - loss: 0.4332
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7734 - loss: 0.5611 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7732 - loss: 0.5604
[1m124/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7717 - loss: 0.5604
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7706 - loss: 0.5607 - val_accuracy: 0.7258 - val_loss: 0.6234
Epoch 12/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7500 - loss: 0.6539
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7677 - loss: 0.5433 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7673 - loss: 0.5426
[1m122/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7679 - loss: 0.5423
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7685 - loss: 0.5439 - val_accuracy: 0.7367 - val_loss: 0.6394
Epoch 13/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.8281 - loss: 0.5597
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.8052 - loss: 0.5267 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7997 - loss: 0.5243
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7964 - loss: 0.5246
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7936 - loss: 0.5265 - val_accuracy: 0.7293 - val_loss: 0.6326

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 344ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 18: 74.05 [%]
F1-score capturado en la ejecución 18: 75.0 [%]

=== EJECUCIÓN 19 ===

--- TRAIN (ejecución 19) ---

--- TEST (ejecución 19) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:45[0m 925ms/step
[1m 69/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 743us/step  
[1m141/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 721us/step
[1m210/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 723us/step
[1m280/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 723us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m57/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 898us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 969us/step
Global accuracy score (validation) = 72.86 [%]
Global F1 score (validation) = 73.64 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[7.3682886e-01 1.9531915e-01 5.6537230e-02 1.1314739e-02]
 [3.4187570e-01 6.5350765e-01 4.0484269e-04 4.2118542e-03]
 [5.5997217e-01 4.3948025e-01 2.6448790e-04 2.8316554e-04]
 ...
 [1.2970347e-05 1.1678959e-04 1.3240559e-04 9.9973780e-01]
 [1.2007191e-05 1.0465535e-04 8.2730556e-05 9.9980056e-01]
 [1.7263079e-03 7.9571974e-04 9.8686463e-01 1.0613356e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 80.8 [%]
Global accuracy score (test) = 73.02 [%]
Global F1 score (train) = 81.01 [%]
Global F1 score (test) = 74.18 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.53      0.59      0.56       350
MODERATE-INTENSITY       0.56      0.55      0.55       350
         SEDENTARY       0.96      0.93      0.94       350
VIGOROUS-INTENSITY       0.96      0.87      0.92       299

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

2025-11-04 12:14:46.471539: 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`.
2025-11-04 12:14:46.483189: 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 00:00:1762254886.496795 1266944 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762254886.501042 1266944 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762254886.510867 1266944 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254886.510883 1266944 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254886.510884 1266944 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254886.510886 1266944 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:14:46.513960: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762254888.826236 1266944 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762254890.236756 1267070 service.cc:152] XLA service 0x7501b820a860 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762254890.236800 1267070 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:14:50.272099: 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 00:00:1762254890.393636 1267070 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762254892.716808 1267070 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:17[0m 3s/step - accuracy: 0.2812 - loss: 2.1126
[1m 36/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3403 - loss: 1.8465 
[1m 75/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3751 - loss: 1.7067
[1m114/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3985 - loss: 1.6142
[1m150/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.4167 - loss: 1.5467
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4190 - loss: 1.5384
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 28ms/step - accuracy: 0.4194 - loss: 1.5368 - val_accuracy: 0.6752 - val_loss: 0.7300
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 23ms/step - accuracy: 0.5938 - loss: 0.9786
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6029 - loss: 0.9438 
[1m 75/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6053 - loss: 0.9314
[1m114/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6087 - loss: 0.9195
[1m152/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6131 - loss: 0.9065
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6136 - loss: 0.9051 - val_accuracy: 0.7191 - val_loss: 0.6194
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7188 - loss: 0.8309
[1m 36/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6858 - loss: 0.7863 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6818 - loss: 0.7709
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6793 - loss: 0.7615
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6783 - loss: 0.7558 - val_accuracy: 0.7173 - val_loss: 0.6287
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.5938 - loss: 0.9110
[1m 43/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6818 - loss: 0.6929 
[1m 84/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6792 - loss: 0.6979
[1m122/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6810 - loss: 0.6950
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6823 - loss: 0.6932 - val_accuracy: 0.7149 - val_loss: 0.6287
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.5781 - loss: 0.7595
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6983 - loss: 0.6606 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7055 - loss: 0.6565
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7068 - loss: 0.6564
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7071 - loss: 0.6567 - val_accuracy: 0.7195 - val_loss: 0.6307
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7500 - loss: 0.6629
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7387 - loss: 0.6303 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7323 - loss: 0.6349
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7295 - loss: 0.6362
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7269 - loss: 0.6380 - val_accuracy: 0.7233 - val_loss: 0.6335
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7656 - loss: 0.5374
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7478 - loss: 0.6107 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7430 - loss: 0.6105
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7407 - loss: 0.6101
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7390 - loss: 0.6108 - val_accuracy: 0.7412 - val_loss: 0.6164
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7344 - loss: 0.6841
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7379 - loss: 0.5953 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7358 - loss: 0.5998
[1m122/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7352 - loss: 0.6023
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7353 - loss: 0.6028 - val_accuracy: 0.7412 - val_loss: 0.6198
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7812 - loss: 0.5653
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7624 - loss: 0.5524 
[1m 78/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7571 - loss: 0.5655
[1m116/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7533 - loss: 0.5732
[1m153/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7515 - loss: 0.5768
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7513 - loss: 0.5770 - val_accuracy: 0.7268 - val_loss: 0.6570
Epoch 10/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7812 - loss: 0.4212
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7546 - loss: 0.5597 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7525 - loss: 0.5661
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7528 - loss: 0.5685
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7534 - loss: 0.5702 - val_accuracy: 0.7240 - val_loss: 0.6542
Epoch 11/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 23ms/step - accuracy: 0.7344 - loss: 0.6850
[1m 36/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7721 - loss: 0.5850 
[1m 74/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7716 - loss: 0.5668
[1m112/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7699 - loss: 0.5608
[1m152/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7681 - loss: 0.5601
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7679 - loss: 0.5602 - val_accuracy: 0.7346 - val_loss: 0.6334
Epoch 12/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7969 - loss: 0.5345
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7863 - loss: 0.5446 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7865 - loss: 0.5440
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7843 - loss: 0.5463
[1m154/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7827 - loss: 0.5464
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7826 - loss: 0.5464 - val_accuracy: 0.7300 - val_loss: 0.6461

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 331ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 13ms/step
Saved model to disk.

Accuracy capturado en la ejecución 19: 73.02 [%]
F1-score capturado en la ejecución 19: 74.18 [%]

=== EJECUCIÓN 20 ===

--- TRAIN (ejecución 20) ---

--- TEST (ejecución 20) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:45[0m 925ms/step
[1m 66/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 770us/step  
[1m140/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 724us/step
[1m217/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 702us/step
[1m296/310[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 684us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m69/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 745us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 882us/step
Global accuracy score (validation) = 72.58 [%]
Global F1 score (validation) = 73.29 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[4.7279394e-01 5.2585906e-01 7.0876064e-05 1.2761228e-03]
 [7.0119190e-01 2.9801279e-01 2.8499958e-04 5.1027001e-04]
 [6.2260896e-01 1.7997965e-01 1.7295147e-01 2.4459878e-02]
 ...
 [1.7956836e-05 7.8877500e-05 2.3008215e-04 9.9967307e-01]
 [1.7180308e-05 5.9308328e-05 2.3651564e-04 9.9968690e-01]
 [2.8570765e-03 2.2202416e-03 9.6595520e-01 2.8967479e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 80.69 [%]
Global accuracy score (test) = 76.06 [%]
Global F1 score (train) = 80.97 [%]
Global F1 score (test) = 76.73 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.58      0.55      0.56       350
MODERATE-INTENSITY       0.60      0.65      0.62       350
         SEDENTARY       0.98      0.95      0.97       350
VIGOROUS-INTENSITY       0.92      0.92      0.92       299

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

2025-11-04 12:15:10.748803: 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`.
2025-11-04 12:15:10.760162: 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 00:00:1762254910.773193 1269013 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762254910.777143 1269013 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762254910.787355 1269013 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254910.787373 1269013 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254910.787374 1269013 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254910.787375 1269013 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:15:10.790623: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762254913.103163 1269013 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762254914.491759 1269143 service.cc:152] XLA service 0x733fa82055d0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762254914.491806 1269143 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:15:14.535141: 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 00:00:1762254914.658891 1269143 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762254916.969996 1269143 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:15[0m 3s/step - accuracy: 0.1406 - loss: 2.7554
[1m 32/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3416 - loss: 1.8711 
[1m 72/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3762 - loss: 1.7188
[1m110/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3986 - loss: 1.6279
[1m148/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.4166 - loss: 1.5572
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4196 - loss: 1.5456
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m8s[0m 28ms/step - accuracy: 0.4201 - loss: 1.5440 - val_accuracy: 0.6836 - val_loss: 0.6674
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 25ms/step - accuracy: 0.5312 - loss: 0.9397
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.5684 - loss: 0.9599 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.5820 - loss: 0.9418
[1m122/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.5940 - loss: 0.9225
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6019 - loss: 0.9082 - val_accuracy: 0.7012 - val_loss: 0.6189
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6250 - loss: 0.8618
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6521 - loss: 0.7686 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6582 - loss: 0.7611
[1m124/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6640 - loss: 0.7553
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6665 - loss: 0.7517 - val_accuracy: 0.7037 - val_loss: 0.6243
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 28ms/step - accuracy: 0.7188 - loss: 0.6848
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6989 - loss: 0.6870 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6993 - loss: 0.6854
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6980 - loss: 0.6869
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6974 - loss: 0.6865 - val_accuracy: 0.7138 - val_loss: 0.6026
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7500 - loss: 0.6753
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7056 - loss: 0.6598 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7045 - loss: 0.6616
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7053 - loss: 0.6637
[1m154/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7069 - loss: 0.6630
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7070 - loss: 0.6630 - val_accuracy: 0.7093 - val_loss: 0.6000
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7344 - loss: 0.6291
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7306 - loss: 0.6422 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7232 - loss: 0.6451
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7206 - loss: 0.6466
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7199 - loss: 0.6454 - val_accuracy: 0.7205 - val_loss: 0.5920
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7500 - loss: 0.6190
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7413 - loss: 0.6111 
[1m 78/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7377 - loss: 0.6125
[1m116/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7365 - loss: 0.6142
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7356 - loss: 0.6143 - val_accuracy: 0.7131 - val_loss: 0.6213
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7188 - loss: 0.6422
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7481 - loss: 0.5767 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7495 - loss: 0.5798
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7476 - loss: 0.5831
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7460 - loss: 0.5856 - val_accuracy: 0.7096 - val_loss: 0.6154
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7969 - loss: 0.4857
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7756 - loss: 0.5462 
[1m 78/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7645 - loss: 0.5656
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7614 - loss: 0.5699
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7597 - loss: 0.5721 - val_accuracy: 0.7198 - val_loss: 0.6042
Epoch 10/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 24ms/step - accuracy: 0.7969 - loss: 0.4730
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7598 - loss: 0.5636 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7606 - loss: 0.5661
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7596 - loss: 0.5687
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7590 - loss: 0.5703 - val_accuracy: 0.7177 - val_loss: 0.6224
Epoch 11/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7500 - loss: 0.5286
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7774 - loss: 0.5493 
[1m 73/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7758 - loss: 0.5504
[1m113/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7731 - loss: 0.5516
[1m150/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7711 - loss: 0.5525
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7708 - loss: 0.5527 - val_accuracy: 0.7216 - val_loss: 0.6210

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 350ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 20: 76.06 [%]
F1-score capturado en la ejecución 20: 76.73 [%]

=== EJECUCIÓN 21 ===

--- TRAIN (ejecución 21) ---

--- TEST (ejecución 21) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:56[0m 960ms/step
[1m 70/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 725us/step  
[1m143/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 708us/step
[1m218/310[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 694us/step
[1m288/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 700us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step 
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m63/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 809us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 945us/step
Global accuracy score (validation) = 73.14 [%]
Global F1 score (validation) = 73.75 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[4.0943971e-01 5.8312070e-01 1.7787957e-03 5.6607453e-03]
 [6.3354385e-01 2.0081231e-01 1.3425541e-01 3.1388368e-02]
 [1.7538811e-01 8.2372403e-01 8.3897532e-05 8.0394099e-04]
 ...
 [1.6985481e-05 1.0061573e-04 1.2293768e-04 9.9975950e-01]
 [1.8044875e-05 1.0931279e-04 1.4381068e-04 9.9972886e-01]
 [2.5211868e-03 1.6095336e-03 9.5922661e-01 3.6642712e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 80.61 [%]
Global accuracy score (test) = 74.43 [%]
Global F1 score (train) = 80.89 [%]
Global F1 score (test) = 75.31 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.54      0.61      0.57       350
MODERATE-INTENSITY       0.60      0.55      0.57       350
         SEDENTARY       0.94      0.96      0.95       350
VIGOROUS-INTENSITY       0.97      0.87      0.92       299

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

2025-11-04 12:15:34.744954: 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`.
2025-11-04 12:15:34.756883: 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 00:00:1762254934.771001 1270990 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762254934.775017 1270990 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762254934.785244 1270990 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254934.785263 1270990 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254934.785264 1270990 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254934.785266 1270990 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:15:34.788563: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762254937.112727 1270990 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762254938.554222 1271101 service.cc:152] XLA service 0x749b8801bf60 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762254938.554261 1271101 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:15:38.592608: 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 00:00:1762254938.709228 1271101 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762254940.999870 1271101 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:13[0m 3s/step - accuracy: 0.2344 - loss: 2.5239
[1m 34/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3501 - loss: 1.8424 
[1m 73/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3866 - loss: 1.6847
[1m111/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4068 - loss: 1.5957
[1m150/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.4256 - loss: 1.5240
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4277 - loss: 1.5162
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m8s[0m 28ms/step - accuracy: 0.4281 - loss: 1.5146 - val_accuracy: 0.6928 - val_loss: 0.6480
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 23ms/step - accuracy: 0.5938 - loss: 1.0090
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.5901 - loss: 0.9735 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6002 - loss: 0.9459
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6069 - loss: 0.9245
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6118 - loss: 0.9095 - val_accuracy: 0.6949 - val_loss: 0.6270
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7031 - loss: 0.7453
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6657 - loss: 0.7614 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6639 - loss: 0.7617
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6660 - loss: 0.7586
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6673 - loss: 0.7552 - val_accuracy: 0.7117 - val_loss: 0.6093
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7344 - loss: 0.6916
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6648 - loss: 0.7139 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6752 - loss: 0.7038
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6778 - loss: 0.7016
[1m154/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6793 - loss: 0.7009
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6794 - loss: 0.7008 - val_accuracy: 0.7205 - val_loss: 0.5867
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7031 - loss: 0.6603
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7014 - loss: 0.6901 
[1m 85/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7013 - loss: 0.6870
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7002 - loss: 0.6844
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7006 - loss: 0.6805 - val_accuracy: 0.7096 - val_loss: 0.6183
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7031 - loss: 0.6153
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7058 - loss: 0.6328 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7061 - loss: 0.6414
[1m124/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7077 - loss: 0.6415
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7086 - loss: 0.6414 - val_accuracy: 0.7163 - val_loss: 0.6000
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 24ms/step - accuracy: 0.7344 - loss: 0.5736
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7183 - loss: 0.6261 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7236 - loss: 0.6218
[1m124/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7247 - loss: 0.6205
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7259 - loss: 0.6197 - val_accuracy: 0.7177 - val_loss: 0.6080
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.8125 - loss: 0.4870
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7427 - loss: 0.5828 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7391 - loss: 0.5931
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7381 - loss: 0.5968
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7374 - loss: 0.5983 - val_accuracy: 0.7230 - val_loss: 0.5979
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7188 - loss: 0.5325
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7514 - loss: 0.5682 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7502 - loss: 0.5742
[1m124/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7472 - loss: 0.5783
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7453 - loss: 0.5808 - val_accuracy: 0.7223 - val_loss: 0.6079

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 361ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 21: 74.43 [%]
F1-score capturado en la ejecución 21: 75.31 [%]

=== EJECUCIÓN 22 ===

--- TRAIN (ejecución 22) ---

--- TEST (ejecución 22) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:33[0m 886ms/step
[1m 69/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 744us/step  
[1m139/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 729us/step
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 713us/step
[1m287/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 705us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m68/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 755us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 880us/step
Global accuracy score (validation) = 72.23 [%]
Global F1 score (validation) = 73.01 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[5.9042668e-01 4.0748310e-01 1.2497861e-03 8.4044092e-04]
 [6.9292110e-01 1.9313575e-01 1.0026120e-01 1.3682033e-02]
 [4.9529850e-01 5.0347775e-01 3.4425853e-04 8.7938679e-04]
 ...
 [5.1052404e-05 2.2228155e-04 3.3480488e-04 9.9939179e-01]
 [3.2139353e-05 1.2618877e-04 2.3061066e-04 9.9961102e-01]
 [7.9508265e-03 4.3897685e-03 9.5993161e-01 2.7727850e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 78.44 [%]
Global accuracy score (test) = 71.31 [%]
Global F1 score (train) = 78.66 [%]
Global F1 score (test) = 72.26 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.50      0.60      0.55       350
MODERATE-INTENSITY       0.55      0.48      0.51       350
         SEDENTARY       0.91      0.95      0.93       350
VIGOROUS-INTENSITY       0.97      0.85      0.90       299

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

2025-11-04 12:15:57.884733: 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`.
2025-11-04 12:15:57.896704: 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 00:00:1762254957.911023 1272760 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762254957.915513 1272760 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762254957.926073 1272760 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254957.926090 1272760 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254957.926092 1272760 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254957.926093 1272760 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:15:57.929385: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762254960.255391 1272760 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762254961.696295 1272892 service.cc:152] XLA service 0x7f4058008db0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762254961.696326 1272892 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:16:01.732214: 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 00:00:1762254961.849161 1272892 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762254964.119806 1272892 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:08[0m 3s/step - accuracy: 0.2969 - loss: 2.5323
[1m 34/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3648 - loss: 1.8857 
[1m 71/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3873 - loss: 1.7429
[1m115/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4080 - loss: 1.6363
[1m150/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.4233 - loss: 1.5705
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 15ms/step - accuracy: 0.4253 - loss: 1.5621
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 27ms/step - accuracy: 0.4257 - loss: 1.5605 - val_accuracy: 0.6808 - val_loss: 0.6897
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.6719 - loss: 0.8455
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6065 - loss: 0.9317 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6058 - loss: 0.9265
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6098 - loss: 0.9142
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6125 - loss: 0.9045 - val_accuracy: 0.7012 - val_loss: 0.6385
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.5781 - loss: 0.8851
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6619 - loss: 0.7517 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6657 - loss: 0.7464
[1m122/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6686 - loss: 0.7422
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6700 - loss: 0.7408 - val_accuracy: 0.7082 - val_loss: 0.6115
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6406 - loss: 0.9844
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6749 - loss: 0.7256 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6810 - loss: 0.7089
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6844 - loss: 0.7030
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6866 - loss: 0.7003 - val_accuracy: 0.7272 - val_loss: 0.6007
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6719 - loss: 0.6949
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7220 - loss: 0.6669 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7125 - loss: 0.6722
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7098 - loss: 0.6697
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7092 - loss: 0.6669 - val_accuracy: 0.7166 - val_loss: 0.6034
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6875 - loss: 0.5892
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7118 - loss: 0.6305 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7157 - loss: 0.6327
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7174 - loss: 0.6339
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7174 - loss: 0.6355 - val_accuracy: 0.7173 - val_loss: 0.6056
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6562 - loss: 0.5959
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7219 - loss: 0.6065 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7222 - loss: 0.6149
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7224 - loss: 0.6169
[1m152/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7226 - loss: 0.6179
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7226 - loss: 0.6180 - val_accuracy: 0.7114 - val_loss: 0.6359
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7188 - loss: 0.5665
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7432 - loss: 0.5743 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7409 - loss: 0.5831
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7410 - loss: 0.5856
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7400 - loss: 0.5885 - val_accuracy: 0.7226 - val_loss: 0.6004
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7500 - loss: 0.6243
[1m 43/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7463 - loss: 0.5942 
[1m 85/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7482 - loss: 0.5902
[1m127/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7485 - loss: 0.5892
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7483 - loss: 0.5890 - val_accuracy: 0.7300 - val_loss: 0.6045
Epoch 10/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7812 - loss: 0.5026
[1m 35/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7602 - loss: 0.5519 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7599 - loss: 0.5537
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7597 - loss: 0.5551
[1m153/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7582 - loss: 0.5588
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7581 - loss: 0.5590 - val_accuracy: 0.7367 - val_loss: 0.6000
Epoch 11/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7969 - loss: 0.5093
[1m 34/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7595 - loss: 0.5783 
[1m 73/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7608 - loss: 0.5683
[1m112/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7605 - loss: 0.5654
[1m150/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7598 - loss: 0.5639
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7597 - loss: 0.5637 - val_accuracy: 0.7317 - val_loss: 0.6225
Epoch 12/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.8125 - loss: 0.5022
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7806 - loss: 0.5463 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7784 - loss: 0.5482
[1m114/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7769 - loss: 0.5480
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.7749 - loss: 0.5492
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7748 - loss: 0.5492 - val_accuracy: 0.7261 - val_loss: 0.6459
Epoch 13/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 27ms/step - accuracy: 0.7812 - loss: 0.4901
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7695 - loss: 0.5521 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7708 - loss: 0.5501
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7724 - loss: 0.5470
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7735 - loss: 0.5446 - val_accuracy: 0.7398 - val_loss: 0.6280
Epoch 14/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.8125 - loss: 0.4381
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7838 - loss: 0.5094 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7840 - loss: 0.5165
[1m122/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7831 - loss: 0.5214
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7822 - loss: 0.5234 - val_accuracy: 0.7360 - val_loss: 0.6491
Epoch 15/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7344 - loss: 0.5519
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7768 - loss: 0.5341 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7782 - loss: 0.5348
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7793 - loss: 0.5342
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7804 - loss: 0.5331 - val_accuracy: 0.7419 - val_loss: 0.6398

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 351ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 22: 71.31 [%]
F1-score capturado en la ejecución 22: 72.26 [%]

=== EJECUCIÓN 23 ===

--- TRAIN (ejecución 23) ---

--- TEST (ejecución 23) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:38[0m 902ms/step
[1m 64/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 795us/step  
[1m133/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 763us/step
[1m201/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 757us/step
[1m274/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 738us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m71/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 727us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 870us/step
Global accuracy score (validation) = 74.23 [%]
Global F1 score (validation) = 75.03 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[3.6832952e-01 6.2945557e-01 4.1833639e-04 1.7965042e-03]
 [4.4819924e-01 5.4730546e-01 2.7563676e-04 4.2197043e-03]
 [5.0715995e-01 4.9171475e-01 3.2939657e-04 7.9592637e-04]
 ...
 [5.2093319e-06 4.2774096e-05 6.0537375e-05 9.9989140e-01]
 [3.5635214e-06 3.2797954e-05 8.9112684e-05 9.9987447e-01]
 [1.9981561e-03 1.9817576e-03 9.5772433e-01 3.8295679e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 81.78 [%]
Global accuracy score (test) = 73.17 [%]
Global F1 score (train) = 82.0 [%]
Global F1 score (test) = 73.83 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.52      0.65      0.58       350
MODERATE-INTENSITY       0.58      0.46      0.51       350
         SEDENTARY       0.95      0.96      0.95       350
VIGOROUS-INTENSITY       0.94      0.88      0.91       299

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

2025-11-04 12:16:22.929720: 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`.
2025-11-04 12:16:22.940994: 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 00:00:1762254982.954370 1275098 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762254982.958258 1275098 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762254982.968228 1275098 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254982.968245 1275098 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254982.968246 1275098 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762254982.968247 1275098 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:16:22.971151: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762254985.327010 1275098 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762254986.721263 1275231 service.cc:152] XLA service 0x79a6f8205570 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762254986.721308 1275231 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:16:26.758724: 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 00:00:1762254986.880900 1275231 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762254989.194145 1275231 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:14[0m 3s/step - accuracy: 0.2969 - loss: 2.0700
[1m 32/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3498 - loss: 1.7660 
[1m 67/155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3845 - loss: 1.6436
[1m106/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4095 - loss: 1.5597
[1m141/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.4275 - loss: 1.4991
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4338 - loss: 1.4779
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 28ms/step - accuracy: 0.4343 - loss: 1.4764 - val_accuracy: 0.7061 - val_loss: 0.6717
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 23ms/step - accuracy: 0.5938 - loss: 0.9776
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6132 - loss: 0.9116 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6209 - loss: 0.8840
[1m109/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6235 - loss: 0.8731
[1m144/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.6261 - loss: 0.8646
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6270 - loss: 0.8617 - val_accuracy: 0.7096 - val_loss: 0.6378
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 25ms/step - accuracy: 0.6250 - loss: 0.6147
[1m 43/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6584 - loss: 0.7228 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6612 - loss: 0.7313
[1m124/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6641 - loss: 0.7338
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6657 - loss: 0.7336 - val_accuracy: 0.7135 - val_loss: 0.6113
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6875 - loss: 0.6579
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6872 - loss: 0.6901 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6847 - loss: 0.6956
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6841 - loss: 0.6955
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6849 - loss: 0.6938 - val_accuracy: 0.7198 - val_loss: 0.6115
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6250 - loss: 0.7591
[1m 36/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7097 - loss: 0.6617 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7117 - loss: 0.6553
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7098 - loss: 0.6550
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7094 - loss: 0.6534 - val_accuracy: 0.7163 - val_loss: 0.6166
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6719 - loss: 0.5545
[1m 34/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.7097 - loss: 0.6284 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7116 - loss: 0.6353
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7126 - loss: 0.6363
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7126 - loss: 0.6363 - val_accuracy: 0.7219 - val_loss: 0.6069
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 23ms/step - accuracy: 0.7812 - loss: 0.5352
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7323 - loss: 0.6163 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7298 - loss: 0.6150
[1m122/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7301 - loss: 0.6135
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7299 - loss: 0.6135 - val_accuracy: 0.7166 - val_loss: 0.6251
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.6562 - loss: 0.7107
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7329 - loss: 0.6012 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7358 - loss: 0.5993
[1m124/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7377 - loss: 0.5973
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7381 - loss: 0.5971 - val_accuracy: 0.7114 - val_loss: 0.6373
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 30ms/step - accuracy: 0.7031 - loss: 0.6901
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7515 - loss: 0.5897 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7439 - loss: 0.5970
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7418 - loss: 0.5983
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7416 - loss: 0.5965 - val_accuracy: 0.7346 - val_loss: 0.6107
Epoch 10/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7656 - loss: 0.7586
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7515 - loss: 0.5775 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7495 - loss: 0.5776
[1m115/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7489 - loss: 0.5787
[1m152/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7490 - loss: 0.5784
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7491 - loss: 0.5783 - val_accuracy: 0.7233 - val_loss: 0.6242
Epoch 11/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7656 - loss: 0.5655
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7629 - loss: 0.5418 
[1m 78/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7646 - loss: 0.5418
[1m115/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7629 - loss: 0.5454
[1m154/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7615 - loss: 0.5491
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7614 - loss: 0.5493 - val_accuracy: 0.7265 - val_loss: 0.6215

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 350ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 23: 73.17 [%]
F1-score capturado en la ejecución 23: 73.83 [%]

=== EJECUCIÓN 24 ===

--- TRAIN (ejecución 24) ---

--- TEST (ejecución 24) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:42[0m 915ms/step
[1m 63/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 807us/step  
[1m128/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 792us/step
[1m196/310[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 775us/step
[1m260/310[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 779us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m65/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 787us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 897us/step
Global accuracy score (validation) = 72.09 [%]
Global F1 score (validation) = 72.77 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[5.7328117e-01 4.2327520e-01 1.1977451e-03 2.2458450e-03]
 [6.6370159e-01 3.3576423e-01 3.7980007e-04 1.5443566e-04]
 [5.8195686e-01 4.1464388e-01 1.7816040e-03 1.6176825e-03]
 ...
 [9.7460297e-06 5.4713324e-05 1.2924394e-04 9.9980628e-01]
 [1.1285983e-05 7.4386488e-05 1.0331421e-04 9.9981093e-01]
 [2.4149241e-03 1.5174664e-03 9.5649427e-01 3.9573334e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 79.62 [%]
Global accuracy score (test) = 73.39 [%]
Global F1 score (train) = 79.85 [%]
Global F1 score (test) = 74.11 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.54      0.47      0.50       350
MODERATE-INTENSITY       0.55      0.65      0.59       350
         SEDENTARY       0.94      0.95      0.94       350
VIGOROUS-INTENSITY       0.95      0.90      0.92       299

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

2025-11-04 12:16:47.003005: 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`.
2025-11-04 12:16:47.014527: 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 00:00:1762255007.027663 1277070 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762255007.031762 1277070 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762255007.041592 1277070 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762255007.041609 1277070 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762255007.041617 1277070 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762255007.041619 1277070 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:16:47.044794: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762255009.386910 1277070 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762255010.787815 1277207 service.cc:152] XLA service 0x77992400a130 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762255010.787838 1277207 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:16:50.821272: 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 00:00:1762255010.939013 1277207 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762255013.272816 1277207 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:16[0m 3s/step - accuracy: 0.1562 - loss: 2.4223
[1m 34/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 1.9343 
[1m 75/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3685 - loss: 1.7463
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3966 - loss: 1.6385
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 15ms/step - accuracy: 0.4164 - loss: 1.5647
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 27ms/step - accuracy: 0.4169 - loss: 1.5629 - val_accuracy: 0.6900 - val_loss: 0.6671
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.6406 - loss: 1.0017
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6359 - loss: 0.8912 
[1m 74/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6301 - loss: 0.8912
[1m113/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6298 - loss: 0.8827
[1m153/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6317 - loss: 0.8733
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6318 - loss: 0.8726 - val_accuracy: 0.7159 - val_loss: 0.6079
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 25ms/step - accuracy: 0.6562 - loss: 0.6844
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6691 - loss: 0.7487 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6710 - loss: 0.7491
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6707 - loss: 0.7503
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6707 - loss: 0.7489 - val_accuracy: 0.7110 - val_loss: 0.6285
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 25ms/step - accuracy: 0.7031 - loss: 0.7232
[1m 36/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6998 - loss: 0.7177 
[1m 73/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6921 - loss: 0.7217
[1m111/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6921 - loss: 0.7141
[1m148/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6929 - loss: 0.7075
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6932 - loss: 0.7064 - val_accuracy: 0.7180 - val_loss: 0.5838
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6875 - loss: 0.7981
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6908 - loss: 0.6742 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6958 - loss: 0.6606
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6988 - loss: 0.6568
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7011 - loss: 0.6556 - val_accuracy: 0.7300 - val_loss: 0.5926
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7812 - loss: 0.4771
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7107 - loss: 0.6223 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7152 - loss: 0.6275
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7172 - loss: 0.6296
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7182 - loss: 0.6310 - val_accuracy: 0.7514 - val_loss: 0.5811
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7344 - loss: 0.6783
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7410 - loss: 0.5994 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7362 - loss: 0.6041
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7364 - loss: 0.6029
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7356 - loss: 0.6044 - val_accuracy: 0.7303 - val_loss: 0.5986
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.8125 - loss: 0.4971
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7556 - loss: 0.5847 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7511 - loss: 0.5832
[1m124/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7464 - loss: 0.5883
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7447 - loss: 0.5894 - val_accuracy: 0.7391 - val_loss: 0.5925
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7812 - loss: 0.5327
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7544 - loss: 0.5655 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7517 - loss: 0.5694
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7508 - loss: 0.5709
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.7502 - loss: 0.5741
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7502 - loss: 0.5741 - val_accuracy: 0.7391 - val_loss: 0.6075
Epoch 10/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6562 - loss: 0.6339
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7396 - loss: 0.5839 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7510 - loss: 0.5727
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7551 - loss: 0.5692
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7573 - loss: 0.5671 - val_accuracy: 0.7398 - val_loss: 0.6158
Epoch 11/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7188 - loss: 0.5220
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7524 - loss: 0.5372 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7570 - loss: 0.5433
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7586 - loss: 0.5478
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7596 - loss: 0.5490 - val_accuracy: 0.7479 - val_loss: 0.6153

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 358ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 24: 73.39 [%]
F1-score capturado en la ejecución 24: 74.11 [%]

=== EJECUCIÓN 25 ===

--- TRAIN (ejecución 25) ---

--- TEST (ejecución 25) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:50[0m 939ms/step
[1m 68/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 748us/step  
[1m137/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 739us/step
[1m205/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 739us/step
[1m276/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 732us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m70/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 732us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 862us/step
Global accuracy score (validation) = 73.88 [%]
Global F1 score (validation) = 74.83 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[6.3044888e-01 3.6431381e-01 1.0928151e-03 4.1444185e-03]
 [7.6495296e-01 2.3413889e-01 6.6117023e-04 2.4697196e-04]
 [6.0063404e-01 3.9818811e-01 5.7790312e-04 5.9993350e-04]
 ...
 [4.2777836e-05 2.3858466e-04 2.5292789e-04 9.9946576e-01]
 [6.3049411e-05 4.0916225e-04 1.7603094e-04 9.9935168e-01]
 [1.7360216e-02 1.3426006e-02 8.9775908e-01 7.1454652e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 79.8 [%]
Global accuracy score (test) = 73.68 [%]
Global F1 score (train) = 80.21 [%]
Global F1 score (test) = 74.98 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.54      0.62      0.58       350
MODERATE-INTENSITY       0.55      0.55      0.55       350
         SEDENTARY       0.98      0.93      0.95       350
VIGOROUS-INTENSITY       0.97      0.87      0.92       299

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

2025-11-04 12:17:10.880027: 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`.
2025-11-04 12:17:10.891123: 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 00:00:1762255030.904038 1279052 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762255030.907934 1279052 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762255030.918090 1279052 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762255030.918105 1279052 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762255030.918107 1279052 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762255030.918108 1279052 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:17:10.921240: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762255033.231859 1279052 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762255034.650242 1279163 service.cc:152] XLA service 0x7bbba8008c40 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762255034.650301 1279163 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:17:14.691502: 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 00:00:1762255034.813232 1279163 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762255037.136301 1279163 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:20[0m 3s/step - accuracy: 0.2969 - loss: 2.0483
[1m 27/155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3392 - loss: 1.8608 
[1m 68/155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3798 - loss: 1.7078
[1m106/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4026 - loss: 1.6215
[1m148/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.4226 - loss: 1.5466
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4255 - loss: 1.5357
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m8s[0m 28ms/step - accuracy: 0.4259 - loss: 1.5341 - val_accuracy: 0.6622 - val_loss: 0.7211
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.5781 - loss: 1.1385
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6180 - loss: 0.9256 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6207 - loss: 0.9080
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6246 - loss: 0.8931
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6270 - loss: 0.8826 - val_accuracy: 0.7152 - val_loss: 0.6125
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 26ms/step - accuracy: 0.7188 - loss: 0.7628
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6831 - loss: 0.7570 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6790 - loss: 0.7549
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6782 - loss: 0.7511
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6773 - loss: 0.7483 - val_accuracy: 0.7138 - val_loss: 0.6118
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7500 - loss: 0.6126
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6920 - loss: 0.6951 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6907 - loss: 0.6943
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6903 - loss: 0.6936
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6903 - loss: 0.6924 - val_accuracy: 0.7152 - val_loss: 0.5997
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7812 - loss: 0.6370
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7097 - loss: 0.6579 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7102 - loss: 0.6583
[1m122/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7096 - loss: 0.6584
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7095 - loss: 0.6570 - val_accuracy: 0.7275 - val_loss: 0.5823
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6406 - loss: 0.6974
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6971 - loss: 0.6688 
[1m 78/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7024 - loss: 0.6603
[1m115/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7037 - loss: 0.6570
[1m150/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7053 - loss: 0.6540
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7056 - loss: 0.6532 - val_accuracy: 0.7279 - val_loss: 0.5947
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6562 - loss: 0.7560
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7258 - loss: 0.6153 
[1m 75/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7281 - loss: 0.6130
[1m113/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7282 - loss: 0.6124
[1m144/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.7273 - loss: 0.6130
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7271 - loss: 0.6133 - val_accuracy: 0.7184 - val_loss: 0.6056
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7031 - loss: 0.8038
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7323 - loss: 0.6068 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7336 - loss: 0.6021
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7350 - loss: 0.5995
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7352 - loss: 0.5985 - val_accuracy: 0.7272 - val_loss: 0.5942
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7031 - loss: 0.8132
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7265 - loss: 0.6230 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7332 - loss: 0.6015
[1m116/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7358 - loss: 0.5946
[1m152/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7370 - loss: 0.5924
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7372 - loss: 0.5923 - val_accuracy: 0.7321 - val_loss: 0.5929
Epoch 10/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.6875 - loss: 0.6197
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7499 - loss: 0.5756 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7504 - loss: 0.5746
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7527 - loss: 0.5725
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7538 - loss: 0.5710 - val_accuracy: 0.7293 - val_loss: 0.6111

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 350ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 25: 73.68 [%]
F1-score capturado en la ejecución 25: 74.98 [%]

=== EJECUCIÓN 26 ===

--- TRAIN (ejecución 26) ---

--- TEST (ejecución 26) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:53[0m 949ms/step
[1m 63/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 811us/step  
[1m131/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 775us/step
[1m204/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 745us/step
[1m275/310[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 735us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m56/89[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 919us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 979us/step
Global accuracy score (validation) = 73.42 [%]
Global F1 score (validation) = 74.16 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[3.9444259e-01 6.0439420e-01 9.7649208e-05 1.0655663e-03]
 [7.2334892e-01 2.7454412e-01 9.6618949e-04 1.1407371e-03]
 [7.1987885e-01 2.7980468e-01 1.1856870e-04 1.9785410e-04]
 ...
 [2.5232193e-05 8.1054393e-05 2.9883967e-04 9.9959481e-01]
 [2.6015145e-05 7.3601645e-05 2.0479246e-04 9.9969548e-01]
 [5.5227331e-03 3.4081992e-03 9.7635603e-01 1.4713013e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 79.29 [%]
Global accuracy score (test) = 74.35 [%]
Global F1 score (train) = 79.66 [%]
Global F1 score (test) = 75.33 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.54      0.59      0.56       350
MODERATE-INTENSITY       0.57      0.56      0.56       350
         SEDENTARY       0.97      0.95      0.96       350
VIGOROUS-INTENSITY       0.96      0.90      0.93       299

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

2025-11-04 12:17:34.697633: 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`.
2025-11-04 12:17:34.708706: 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 00:00:1762255054.721781 1280918 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762255054.725729 1280918 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762255054.735742 1280918 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762255054.735758 1280918 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762255054.735760 1280918 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762255054.735761 1280918 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:17:34.738683: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762255057.047069 1280918 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762255058.445977 1281047 service.cc:152] XLA service 0x781cec00b380 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762255058.446029 1281047 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:17:38.481285: 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 00:00:1762255058.614553 1281047 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762255060.848429 1281047 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:04[0m 3s/step - accuracy: 0.2656 - loss: 2.0674
[1m 32/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3331 - loss: 1.8485 
[1m 69/155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3729 - loss: 1.7090
[1m111/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4027 - loss: 1.6057
[1m149/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.4224 - loss: 1.5362
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4252 - loss: 1.5263
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 28ms/step - accuracy: 0.4257 - loss: 1.5247 - val_accuracy: 0.6921 - val_loss: 0.6742
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.6094 - loss: 0.8522
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.5969 - loss: 0.9317 
[1m 83/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6040 - loss: 0.9166
[1m126/155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6089 - loss: 0.9017
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6122 - loss: 0.8919 - val_accuracy: 0.7040 - val_loss: 0.6145
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7031 - loss: 0.7612
[1m 36/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6522 - loss: 0.7786 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6600 - loss: 0.7663
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6631 - loss: 0.7591
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6652 - loss: 0.7537 - val_accuracy: 0.7261 - val_loss: 0.5912
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7344 - loss: 0.7563
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6513 - loss: 0.7437 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6647 - loss: 0.7250
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6717 - loss: 0.7154
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6756 - loss: 0.7091 - val_accuracy: 0.7065 - val_loss: 0.6273
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6562 - loss: 0.6753
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7199 - loss: 0.6323 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7166 - loss: 0.6389
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7144 - loss: 0.6422
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7130 - loss: 0.6443 - val_accuracy: 0.7209 - val_loss: 0.5903
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7031 - loss: 0.6918
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7212 - loss: 0.6062 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7243 - loss: 0.6082
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7244 - loss: 0.6123
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7237 - loss: 0.6155 - val_accuracy: 0.7233 - val_loss: 0.6056
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7344 - loss: 0.5680
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7410 - loss: 0.5845 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7401 - loss: 0.5898
[1m122/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7373 - loss: 0.5953
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7359 - loss: 0.5976 - val_accuracy: 0.7254 - val_loss: 0.5995
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7812 - loss: 0.5306
[1m 42/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7371 - loss: 0.5825 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7408 - loss: 0.5849
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7433 - loss: 0.5856
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7442 - loss: 0.5862 - val_accuracy: 0.7286 - val_loss: 0.6183
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 23ms/step - accuracy: 0.7188 - loss: 0.5692
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7533 - loss: 0.5533 
[1m 81/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7517 - loss: 0.5599
[1m123/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7505 - loss: 0.5628
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7502 - loss: 0.5646 - val_accuracy: 0.7374 - val_loss: 0.5979
Epoch 10/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7188 - loss: 0.6110
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7481 - loss: 0.5993 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7532 - loss: 0.5913
[1m115/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7543 - loss: 0.5868
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.7552 - loss: 0.5835
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7552 - loss: 0.5835 - val_accuracy: 0.7335 - val_loss: 0.6258

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 372ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 26: 74.35 [%]
F1-score capturado en la ejecución 26: 75.33 [%]

=== EJECUCIÓN 27 ===

--- TRAIN (ejecución 27) ---

--- TEST (ejecución 27) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:51[0m 943ms/step
[1m 67/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 760us/step  
[1m144/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 704us/step
[1m214/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 709us/step
[1m287/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 705us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m71/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 719us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 902us/step
Global accuracy score (validation) = 71.63 [%]
Global F1 score (validation) = 72.5 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[5.4907507e-01 4.5072967e-01 4.4904293e-05 1.5029676e-04]
 [7.3638618e-01 2.6245895e-01 5.0102407e-04 6.5384922e-04]
 [4.6503478e-01 5.3465194e-01 7.7284792e-05 2.3598081e-04]
 ...
 [2.9546760e-05 1.3918016e-04 2.8664735e-04 9.9954456e-01]
 [2.8055012e-05 1.3834272e-04 3.4653459e-04 9.9948704e-01]
 [6.8565034e-03 4.0243198e-03 9.7567546e-01 1.3443790e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 79.7 [%]
Global accuracy score (test) = 75.02 [%]
Global F1 score (train) = 79.99 [%]
Global F1 score (test) = 75.96 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.57      0.63      0.60       350
MODERATE-INTENSITY       0.61      0.61      0.61       350
         SEDENTARY       0.93      0.93      0.93       350
VIGOROUS-INTENSITY       0.97      0.84      0.90       299

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

2025-11-04 12:17:58.230100: 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`.
2025-11-04 12:17:58.241340: 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 00:00:1762255078.254634 1282800 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762255078.258692 1282800 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762255078.268385 1282800 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762255078.268401 1282800 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762255078.268403 1282800 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762255078.268404 1282800 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:17:58.271521: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762255080.598432 1282800 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762255082.029540 1282928 service.cc:152] XLA service 0x729a60003ca0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762255082.029566 1282928 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:18:02.063428: 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 00:00:1762255082.185891 1282928 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762255084.502449 1282928 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:16[0m 3s/step - accuracy: 0.1875 - loss: 2.1652
[1m 36/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3601 - loss: 1.7617 
[1m 75/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3927 - loss: 1.6436
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4162 - loss: 1.5550
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4333 - loss: 1.4929
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 27ms/step - accuracy: 0.4337 - loss: 1.4915 - val_accuracy: 0.6900 - val_loss: 0.6928
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7031 - loss: 0.7537
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6163 - loss: 0.9038 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6167 - loss: 0.9023
[1m114/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6197 - loss: 0.8951
[1m152/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6234 - loss: 0.8858
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6237 - loss: 0.8848 - val_accuracy: 0.7072 - val_loss: 0.6204
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6406 - loss: 0.7688
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6727 - loss: 0.7590 
[1m 75/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6711 - loss: 0.7567
[1m116/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6704 - loss: 0.7542
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6710 - loss: 0.7496 - val_accuracy: 0.7065 - val_loss: 0.6235
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 28ms/step - accuracy: 0.7656 - loss: 0.6462
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6691 - loss: 0.7159 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6717 - loss: 0.7121
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6754 - loss: 0.7079
[1m154/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6779 - loss: 0.7051
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6780 - loss: 0.7050 - val_accuracy: 0.7166 - val_loss: 0.6020
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6406 - loss: 0.6538
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6894 - loss: 0.6780 
[1m 78/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6938 - loss: 0.6759
[1m114/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6953 - loss: 0.6732
[1m152/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6969 - loss: 0.6704
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6970 - loss: 0.6703 - val_accuracy: 0.7163 - val_loss: 0.6084
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6719 - loss: 0.7918
[1m 34/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.6674 - loss: 0.6751 
[1m 72/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6869 - loss: 0.6558
[1m107/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6976 - loss: 0.6442
[1m149/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7042 - loss: 0.6390
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7049 - loss: 0.6386 - val_accuracy: 0.7166 - val_loss: 0.6046
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.6875 - loss: 0.6165
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7259 - loss: 0.6375 
[1m 72/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7285 - loss: 0.6309
[1m112/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7291 - loss: 0.6293
[1m152/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7288 - loss: 0.6290
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7288 - loss: 0.6289 - val_accuracy: 0.7173 - val_loss: 0.6008
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7812 - loss: 0.5622
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7387 - loss: 0.5743 
[1m 78/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7340 - loss: 0.5900
[1m112/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7337 - loss: 0.5945
[1m152/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7336 - loss: 0.5971
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7337 - loss: 0.5972 - val_accuracy: 0.7223 - val_loss: 0.6135
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.8281 - loss: 0.6063
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7459 - loss: 0.5785 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7454 - loss: 0.5781
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7452 - loss: 0.5788
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.7448 - loss: 0.5801
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7448 - loss: 0.5802 - val_accuracy: 0.7230 - val_loss: 0.6179
Epoch 10/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7031 - loss: 0.4834
[1m 36/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7465 - loss: 0.5615 
[1m 78/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7447 - loss: 0.5728
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7458 - loss: 0.5756
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7472 - loss: 0.5762 - val_accuracy: 0.7244 - val_loss: 0.6262
Epoch 11/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 24ms/step - accuracy: 0.7500 - loss: 0.6411
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7548 - loss: 0.5711 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7551 - loss: 0.5644
[1m118/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7558 - loss: 0.5624
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7562 - loss: 0.5616 - val_accuracy: 0.7251 - val_loss: 0.6250
Epoch 12/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.8281 - loss: 0.4317
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7870 - loss: 0.5076 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7782 - loss: 0.5217
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7742 - loss: 0.5309
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7718 - loss: 0.5362 - val_accuracy: 0.7149 - val_loss: 0.6613

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 341ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 13ms/step
Saved model to disk.

Accuracy capturado en la ejecución 27: 75.02 [%]
F1-score capturado en la ejecución 27: 75.96 [%]

=== EJECUCIÓN 28 ===

--- TRAIN (ejecución 28) ---

--- TEST (ejecución 28) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:45[0m 923ms/step
[1m 61/310[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 838us/step  
[1m132/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 766us/step
[1m208/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 728us/step
[1m280/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 720us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m63/89[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 807us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 907us/step
Global accuracy score (validation) = 72.02 [%]
Global F1 score (validation) = 72.72 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[3.01628977e-01 6.96405172e-01 3.48419795e-04 1.61738077e-03]
 [3.96555036e-01 6.02668345e-01 3.78878118e-04 3.97756521e-04]
 [5.91031909e-01 4.07451749e-01 3.40098486e-04 1.17622467e-03]
 ...
 [1.69239556e-05 1.46318940e-04 1.15495524e-04 9.99721229e-01]
 [1.40147522e-05 7.07932995e-05 3.13881173e-04 9.99601245e-01]
 [3.16962763e-03 1.78889208e-03 9.86696541e-01 8.34491011e-03]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 79.6 [%]
Global accuracy score (test) = 74.94 [%]
Global F1 score (train) = 79.83 [%]
Global F1 score (test) = 75.71 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.58      0.56      0.57       350
MODERATE-INTENSITY       0.59      0.65      0.61       350
         SEDENTARY       0.92      0.96      0.94       350
VIGOROUS-INTENSITY       0.97      0.85      0.91       299

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

2025-11-04 12:18:22.591649: 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`.
2025-11-04 12:18:22.603313: 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 00:00:1762255102.616676 1284868 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762255102.620671 1284868 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762255102.630850 1284868 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762255102.630869 1284868 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762255102.630870 1284868 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762255102.630871 1284868 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:18:22.633962: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762255104.950872 1284868 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762255106.371382 1284985 service.cc:152] XLA service 0x7d9ff421d3c0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762255106.371417 1284985 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:18:26.406115: 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 00:00:1762255106.529234 1284985 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762255108.818944 1284985 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:13[0m 3s/step - accuracy: 0.2969 - loss: 1.8767
[1m 31/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3435 - loss: 1.7855 
[1m 71/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3829 - loss: 1.6415
[1m109/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4059 - loss: 1.5559
[1m151/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.4253 - loss: 1.4851
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4270 - loss: 1.4791
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 28ms/step - accuracy: 0.4275 - loss: 1.4777 - val_accuracy: 0.6924 - val_loss: 0.6731
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.6250 - loss: 0.8805
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6049 - loss: 0.9105 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6079 - loss: 0.8988
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6127 - loss: 0.8857
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6162 - loss: 0.8758 - val_accuracy: 0.7061 - val_loss: 0.6260
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7031 - loss: 0.7818
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6790 - loss: 0.7250 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6779 - loss: 0.7319
[1m115/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6775 - loss: 0.7319
[1m153/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6767 - loss: 0.7310
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6767 - loss: 0.7309 - val_accuracy: 0.7093 - val_loss: 0.6027
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.6719 - loss: 0.9175
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6858 - loss: 0.7302 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6869 - loss: 0.7150
[1m121/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6896 - loss: 0.7089
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6905 - loss: 0.7065 - val_accuracy: 0.7251 - val_loss: 0.6024
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7031 - loss: 0.6013
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7078 - loss: 0.6708 
[1m 79/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7092 - loss: 0.6657
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7112 - loss: 0.6624
[1m153/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7119 - loss: 0.6607
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7120 - loss: 0.6606 - val_accuracy: 0.7254 - val_loss: 0.6083
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.6562 - loss: 0.6732
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7166 - loss: 0.6440 
[1m 75/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7158 - loss: 0.6410
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7161 - loss: 0.6396
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7172 - loss: 0.6387 - val_accuracy: 0.7086 - val_loss: 0.6111
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7500 - loss: 0.5470
[1m 36/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7326 - loss: 0.6244 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7270 - loss: 0.6279
[1m115/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7280 - loss: 0.6248
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7294 - loss: 0.6217 - val_accuracy: 0.7353 - val_loss: 0.6124
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7812 - loss: 0.6083
[1m 38/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7636 - loss: 0.5766 
[1m 74/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7545 - loss: 0.5780
[1m111/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7499 - loss: 0.5790
[1m151/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7460 - loss: 0.5823
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7457 - loss: 0.5826 - val_accuracy: 0.7261 - val_loss: 0.6165
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7188 - loss: 0.5772
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7392 - loss: 0.5788 
[1m 80/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7415 - loss: 0.5794
[1m120/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7423 - loss: 0.5789
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 1ms/step - accuracy: 0.7429 - loss: 0.5791
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7429 - loss: 0.5791 - val_accuracy: 0.7426 - val_loss: 0.6185

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 360ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 28: 74.94 [%]
F1-score capturado en la ejecución 28: 75.71 [%]

=== EJECUCIÓN 29 ===

--- TRAIN (ejecución 29) ---

--- TEST (ejecución 29) ---
['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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:44[0m 921ms/step
[1m 67/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 759us/step  
[1m135/310[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 748us/step
[1m209/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 729us/step
[1m282/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 719us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m70/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 729us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 861us/step
Global accuracy score (validation) = 74.51 [%]
Global F1 score (validation) = 75.07 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[4.26843584e-01 5.69057167e-01 3.84934800e-04 3.71433678e-03]
 [6.29676938e-01 2.04150110e-01 1.38696343e-01 2.74765845e-02]
 [6.92444384e-01 1.96684182e-01 9.27423537e-02 1.81290451e-02]
 ...
 [6.24534368e-05 1.47652070e-04 2.14086802e-04 9.99575794e-01]
 [5.76492930e-05 1.21042656e-04 4.53636720e-04 9.99367595e-01]
 [7.24711083e-03 7.37980334e-03 6.82730258e-01 3.02642792e-01]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 78.58 [%]
Global accuracy score (test) = 74.57 [%]
Global F1 score (train) = 78.86 [%]
Global F1 score (test) = 75.52 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.55      0.52      0.53       350
MODERATE-INTENSITY       0.56      0.65      0.60       350
         SEDENTARY       0.97      0.94      0.96       350
VIGOROUS-INTENSITY       0.96      0.90      0.93       299

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

2025-11-04 12:18:45.939344: 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`.
2025-11-04 12:18:45.951057: 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 00:00:1762255125.965289 1286651 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762255125.969534 1286651 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762255125.980213 1286651 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762255125.980232 1286651 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762255125.980234 1286651 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762255125.980235 1286651 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-04 12:18:45.983387: 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/keras/src/layers/core/input_layer.py:27: UserWarning: Argument `input_shape` is deprecated. Use `shape` instead.
  warnings.warn(
I0000 00:00:1762255128.340133 1286651 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13768 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/82
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762255129.743875 1286769 service.cc:152] XLA service 0x70fe7001bb50 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762255129.743900 1286769 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-04 12:18:49.777452: 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 00:00:1762255129.899126 1286769 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762255132.194566 1286769 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:11[0m 3s/step - accuracy: 0.2188 - loss: 2.0509
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3504 - loss: 1.7796 
[1m 75/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.3858 - loss: 1.6510
[1m114/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.4097 - loss: 1.5649
[1m154/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.4290 - loss: 1.4972
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step - accuracy: 0.4295 - loss: 1.4957
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m7s[0m 28ms/step - accuracy: 0.4299 - loss: 1.4942 - val_accuracy: 0.6808 - val_loss: 0.6975
Epoch 2/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.6094 - loss: 0.8975
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6299 - loss: 0.8881 
[1m 78/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6261 - loss: 0.8865
[1m116/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6255 - loss: 0.8826
[1m153/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6267 - loss: 0.8759
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6268 - loss: 0.8753 - val_accuracy: 0.6945 - val_loss: 0.6062
Epoch 3/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step - accuracy: 0.7969 - loss: 0.5215
[1m 36/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6708 - loss: 0.7480 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6675 - loss: 0.7497
[1m119/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6695 - loss: 0.7453
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6712 - loss: 0.7420 - val_accuracy: 0.7022 - val_loss: 0.6049
Epoch 4/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7344 - loss: 0.5522
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7026 - loss: 0.6554 
[1m 77/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6994 - loss: 0.6792
[1m117/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6968 - loss: 0.6866
[1m151/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6961 - loss: 0.6884
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6961 - loss: 0.6885 - val_accuracy: 0.7093 - val_loss: 0.5894
Epoch 5/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6875 - loss: 0.7003
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6874 - loss: 0.6732 
[1m 76/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6918 - loss: 0.6728
[1m113/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.6954 - loss: 0.6694
[1m153/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.6977 - loss: 0.6661
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.6978 - loss: 0.6659 - val_accuracy: 0.7170 - val_loss: 0.5997
Epoch 6/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.7031 - loss: 0.7113
[1m 39/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7014 - loss: 0.6454 
[1m 74/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7079 - loss: 0.6322
[1m114/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7092 - loss: 0.6314
[1m148/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7098 - loss: 0.6315
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7100 - loss: 0.6316 - val_accuracy: 0.7026 - val_loss: 0.6013
Epoch 7/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.6250 - loss: 0.8748
[1m 40/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7150 - loss: 0.6257 
[1m 75/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7176 - loss: 0.6195
[1m115/155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7202 - loss: 0.6167
[1m152/155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step - accuracy: 0.7219 - loss: 0.6163
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7221 - loss: 0.6163 - val_accuracy: 0.7124 - val_loss: 0.6123
Epoch 8/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7656 - loss: 0.6263
[1m 41/155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7484 - loss: 0.5914 
[1m 82/155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7435 - loss: 0.5963
[1m122/155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7425 - loss: 0.5953
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7418 - loss: 0.5951 - val_accuracy: 0.7254 - val_loss: 0.5991
Epoch 9/82

[1m  1/155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step - accuracy: 0.7500 - loss: 0.5783
[1m 37/155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7457 - loss: 0.5805 
[1m 72/155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7482 - loss: 0.5805
[1m105/155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step - accuracy: 0.7488 - loss: 0.5785
[1m144/155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step - accuracy: 0.7491 - loss: 0.5785
[1m155/155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.7493 - loss: 0.5786 - val_accuracy: 0.7131 - val_loss: 0.6448

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 352ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step  
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
Saved model to disk.

Accuracy capturado en la ejecución 29: 74.57 [%]
F1-score capturado en la ejecución 29: 75.52 [%]

=== 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)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv1d (Conv1D)                 │ (None, 6, 128)         │        96,128 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization             │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv1d_1 (Conv1D)               │ (None, 6, 128)         │        49,280 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ layer_normalization_1           │ (None, 6, 128)         │           256 │
│ (LayerNormalization)            │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 6, 128)         │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ global_average_pooling1d        │ (None, 128)            │             0 │
│ (GlobalAveragePooling1D)        │                        │               │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_2 (Dropout)             │ (None, 128)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 4)              │           516 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 146,436 (572.02 KB)
 Trainable params: 146,436 (572.02 KB)
 Non-trainable params: 0 (0.00 B)
Loaded model from disk.
(1349, 6, 250)
(9904, 6, 250)

[1m  1/310[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4:49[0m 936ms/step
[1m 69/310[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 744us/step  
[1m142/310[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 717us/step
[1m213/310[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 714us/step
[1m286/310[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 707us/step
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m310/310[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 3ms/step

[1m 1/43[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m43/43[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step

[1m 1/89[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m68/89[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 753us/step
[1m89/89[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 882us/step
Global accuracy score (validation) = 72.16 [%]
Global F1 score (validation) = 72.74 [%]
[[0.]
 [0.]
 [0.]
 ...
 [3.]
 [3.]
 [3.]]
(1349, 1)
[[2.42067993e-01 7.42766857e-01 7.30961561e-04 1.44342305e-02]
 [6.30143225e-01 3.61060083e-01 6.56643370e-03 2.23022094e-03]
 [2.82295495e-01 7.14095354e-01 3.44146654e-04 3.26501369e-03]
 ...
 [2.18190671e-05 1.03328901e-04 3.76609416e-04 9.99498248e-01]
 [2.23449315e-05 7.99902118e-05 6.29017653e-04 9.99268711e-01]
 [3.65922321e-03 2.22052331e-03 9.78096902e-01 1.60233937e-02]]
(1349, 4)
-------------------------------------------------

Global accuracy score (train) = 78.86 [%]
Global accuracy score (test) = 72.94 [%]
Global F1 score (train) = 79.07 [%]
Global F1 score (test) = 73.7 [%]
                    precision    recall  f1-score   support

   LIGHT-INTENSITY       0.53      0.51      0.52       350
MODERATE-INTENSITY       0.57      0.62      0.59       350
         SEDENTARY       0.93      0.94      0.93       350
VIGOROUS-INTENSITY       0.94      0.87      0.90       299

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


Accuracy capturado en la ejecución 30: 72.94 [%]
F1-score capturado en la ejecución 30: 73.7 [%]

=== RESUMEN FINAL ===
Accuracies: [73.09, 73.02, 75.09, 73.68, 72.57, 75.54, 71.98, 75.39, 73.02, 73.24, 75.17, 73.39, 75.83, 72.94, 72.94, 75.02, 74.13, 74.05, 73.02, 76.06, 74.43, 71.31, 73.17, 73.39, 73.68, 74.35, 75.02, 74.94, 74.57, 72.94]
F1-scores: [73.97, 74.26, 76.01, 74.6, 72.75, 76.47, 72.94, 76.2, 73.66, 73.08, 75.99, 74.33, 76.9, 73.99, 74.27, 75.92, 75.06, 75.0, 74.18, 76.73, 75.31, 72.26, 73.83, 74.11, 74.98, 75.33, 75.96, 75.71, 75.52, 73.7]
Accuracy mean: 73.8990 | std: 1.1608
F1 mean: 74.7673 | std: 1.2100

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