trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 456,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.0,
      "step": 456,
      "total_flos": 131122250941500.0,
      "train_loss": 0.01635488606335824,
      "train_runtime": 158.3006,
      "train_samples_per_second": 23.026,
      "train_steps_per_second": 2.881
    },
    {
      "epoch": 3.0,
      "eval_Accuracy": 1.0,
      "eval_F1": 1.0,
      "eval_Precision": 1.0,
      "eval_Recall": 1.0,
      "eval_loss": 1.6744012100389227e-05,
      "eval_runtime": 1.5175,
      "eval_samples_per_second": 100.163,
      "eval_steps_per_second": 12.52,
      "step": 456
    },
    {
      "epoch": 3.0,
      "eval_Accuracy": 1.0,
      "eval_F1": 1.0,
      "eval_Precision": 1.0,
      "eval_Recall": 1.0,
      "eval_loss": 1.6744012100389227e-05,
      "eval_runtime": 1.5168,
      "eval_samples_per_second": 100.214,
      "eval_steps_per_second": 12.527,
      "step": 456
    }
  ],
  "logging_steps": 500,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 131122250941500.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}