trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "global_step": 106,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 1.9816285371780396,
      "eval_runtime": 1.7583,
      "eval_samples_per_second": 36.398,
      "eval_steps_per_second": 2.275,
      "step": 53
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.4194130897521973,
      "eval_runtime": 1.9283,
      "eval_samples_per_second": 33.19,
      "eval_steps_per_second": 2.074,
      "step": 106
    }
  ],
  "max_steps": 530,
  "num_train_epochs": 10,
  "total_flos": 329625858622464.0,
  "trial_name": null,
  "trial_params": null
}