trainer_state.json

{
  "best_metric": 0.8825914161641272,
  "best_model_checkpoint": "/mnt/d/models_iberlef22/exist22/task1/models_es/retrained_BSC-TeMU/checkpoint-322",
  "epoch": 3.0,
  "global_step": 483,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 5.2402087303147016e-05,
      "loss": 0.3659,
      "step": 161
    },
    {
      "epoch": 1.0,
      "eval_f1-score": 0.8762599995046685,
      "eval_loss": 0.32265210151672363,
      "eval_precision": 0.8820436657141424,
      "eval_recall": 0.874809413732048,
      "eval_runtime": 0.7263,
      "eval_samples_per_second": 786.163,
      "eval_steps_per_second": 12.391,
      "eval_support": 571,
      "step": 161
    },
    {
      "epoch": 2.0,
      "learning_rate": 2.6201043651573508e-05,
      "loss": 0.1328,
      "step": 322
    },
    {
      "epoch": 2.0,
      "eval_f1-score": 0.8825914161641272,
      "eval_loss": 0.3923543691635132,
      "eval_precision": 0.8826217642007116,
      "eval_recall": 0.8834780149518001,
      "eval_runtime": 0.7091,
      "eval_samples_per_second": 805.279,
      "eval_steps_per_second": 12.693,
      "eval_support": 571,
      "step": 322
    },
    {
      "epoch": 3.0,
      "learning_rate": 1.627394015625684e-07,
      "loss": 0.026,
      "step": 483
    },
    {
      "epoch": 3.0,
      "eval_f1-score": 0.8790866823182801,
      "eval_loss": 0.5471494793891907,
      "eval_precision": 0.8791191264875475,
      "eval_recall": 0.8799675388550069,
      "eval_runtime": 0.7205,
      "eval_samples_per_second": 792.548,
      "eval_steps_per_second": 12.492,
      "eval_support": 571,
      "step": 483
    }
  ],
  "max_steps": 483,
  "num_train_epochs": 3,
  "total_flos": 1012319785497600.0,
  "trial_name": null,
  "trial_params": null
}