{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 2.078929901123047,
      "eval_runtime": 16.1753,
      "eval_samples_per_second": 61.823,
      "eval_steps_per_second": 3.895,
      "step": 250
    },
    {
      "epoch": 2.0,
      "grad_norm": 16.615798950195312,
      "learning_rate": 6.666666666666667e-06,
      "loss": 2.6317,
      "step": 500
    }
  ],
  "logging_steps": 500,
  "max_steps": 750,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 783918600192000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}