trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "global_step": 580,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.3067856431007385,
      "eval_runtime": 17.8304,
      "eval_samples_per_second": 35.782,
      "eval_steps_per_second": 2.243,
      "step": 290
    },
    {
      "epoch": 1.72,
      "learning_rate": 3.508587904974522e-05,
      "loss": 0.3404,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.27310052514076233,
      "eval_runtime": 17.9797,
      "eval_samples_per_second": 35.485,
      "eval_steps_per_second": 2.225,
      "step": 580
    }
  ],
  "max_steps": 1160,
  "num_train_epochs": 4,
  "total_flos": 2050812231828480.0,
  "trial_name": null,
  "trial_params": null
}