trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 2,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5,
      "grad_norm": 0.9979434013366699,
      "learning_rate": 0.0002,
      "loss": 4.0828,
      "step": 1
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.0152065753936768,
      "learning_rate": 0.0,
      "loss": 4.0279,
      "step": 2
    }
  ],
  "logging_steps": 1,
  "max_steps": 2,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 657223814479872.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}