trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03088803088803089,
  "global_step": 1,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 2e-05,
      "loss": 1.1672,
      "step": 1
    },
    {
      "epoch": 0.03,
      "eval_loss": 1.1604644060134888,
      "eval_runtime": 7.2577,
      "eval_samples_per_second": 31.139,
      "eval_steps_per_second": 3.996,
      "step": 1
    },
    {
      "epoch": 0.03,
      "step": 1,
      "total_flos": 745396137623552.0,
      "train_loss": 1.1672077178955078,
      "train_runtime": 23.0652,
      "train_samples_per_second": 2.775,
      "train_steps_per_second": 0.043
    }
  ],
  "max_steps": 1,
  "num_train_epochs": 1,
  "total_flos": 745396137623552.0,
  "trial_name": null,
  "trial_params": null
}