checkpoint-16/trainer_state.json

{
  "best_metric": 0.5410245060920715,
  "best_model_checkpoint": "modelo-mobilenetv2-clasificador-bananas/checkpoint-16",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 16,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5,
      "grad_norm": 17.590492248535156,
      "learning_rate": 2.5e-05,
      "loss": 0.655,
      "step": 1
    },
    {
      "epoch": 1.0,
      "grad_norm": 19.860876083374023,
      "learning_rate": 5e-05,
      "loss": 0.8373,
      "step": 2
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.0,
      "eval_auc": 0.0,
      "eval_f1": 0.0,
      "eval_loss": 0.8076530694961548,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 0.1401,
      "eval_samples_per_second": 14.28,
      "eval_steps_per_second": 7.14,
      "step": 2
    },
    {
      "epoch": 1.5,
      "grad_norm": 19.957738876342773,
      "learning_rate": 4.722222222222222e-05,
      "loss": 0.7749,
      "step": 3
    },
    {
      "epoch": 2.0,
      "grad_norm": 16.67332649230957,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.6925,
      "step": 4
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.0,
      "eval_auc": 0.0,
      "eval_f1": 0.0,
      "eval_loss": 0.9083307981491089,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 0.0921,
      "eval_samples_per_second": 21.72,
      "eval_steps_per_second": 10.86,
      "step": 4
    },
    {
      "epoch": 2.5,
      "grad_norm": 21.811174392700195,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.8728,
      "step": 5
    },
    {
      "epoch": 3.0,
      "grad_norm": 18.857229232788086,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.7361,
      "step": 6
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5,
      "eval_auc": 0.0,
      "eval_f1": 0.0,
      "eval_loss": 0.7463452816009521,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 0.1036,
      "eval_samples_per_second": 19.31,
      "eval_steps_per_second": 9.655,
      "step": 6
    },
    {
      "epoch": 3.5,
      "grad_norm": 18.541675567626953,
      "learning_rate": 3.611111111111111e-05,
      "loss": 0.6406,
      "step": 7
    },
    {
      "epoch": 4.0,
      "grad_norm": 18.739696502685547,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.5845,
      "step": 8
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5,
      "eval_auc": 1.0,
      "eval_f1": 0.0,
      "eval_loss": 0.7052843570709229,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 0.0903,
      "eval_samples_per_second": 22.139,
      "eval_steps_per_second": 11.07,
      "step": 8
    },
    {
      "epoch": 4.5,
      "grad_norm": 14.008564949035645,
      "learning_rate": 3.055555555555556e-05,
      "loss": 0.514,
      "step": 9
    },
    {
      "epoch": 5.0,
      "grad_norm": 13.883323669433594,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.4907,
      "step": 10
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5,
      "eval_auc": 0.0,
      "eval_f1": 0.0,
      "eval_loss": 0.6211875677108765,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 0.1298,
      "eval_samples_per_second": 15.409,
      "eval_steps_per_second": 7.704,
      "step": 10
    },
    {
      "epoch": 5.5,
      "grad_norm": 23.929750442504883,
      "learning_rate": 2.5e-05,
      "loss": 0.7162,
      "step": 11
    },
    {
      "epoch": 6.0,
      "grad_norm": 12.069799423217773,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.4294,
      "step": 12
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.0,
      "eval_auc": 0.0,
      "eval_f1": 0.0,
      "eval_loss": 0.8354901075363159,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 0.0885,
      "eval_samples_per_second": 22.603,
      "eval_steps_per_second": 11.302,
      "step": 12
    },
    {
      "epoch": 6.5,
      "grad_norm": 13.07221794128418,
      "learning_rate": 1.9444444444444445e-05,
      "loss": 0.5174,
      "step": 13
    },
    {
      "epoch": 7.0,
      "grad_norm": 17.840425491333008,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.5621,
      "step": 14
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.5,
      "eval_auc": 0.0,
      "eval_f1": 0.6666666666666666,
      "eval_loss": 0.7863453030586243,
      "eval_precision": 0.5,
      "eval_recall": 1.0,
      "eval_runtime": 0.0884,
      "eval_samples_per_second": 22.618,
      "eval_steps_per_second": 11.309,
      "step": 14
    },
    {
      "epoch": 7.5,
      "grad_norm": 11.327210426330566,
      "learning_rate": 1.388888888888889e-05,
      "loss": 0.3556,
      "step": 15
    },
    {
      "epoch": 8.0,
      "grad_norm": 14.13537311553955,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.5251,
      "step": 16
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 1.0,
      "eval_auc": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.5410245060920715,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.0972,
      "eval_samples_per_second": 20.577,
      "eval_steps_per_second": 10.289,
      "step": 16
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.01
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 168090138574848.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}