{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.175226586102719,
  "eval_steps": 500,
  "global_step": 174,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.02,
      "learning_rate": 6.6e-05,
      "loss": 0.6806,
      "step": 66
    },
    {
      "epoch": 2.05,
      "learning_rate": 9.641657334826429e-05,
      "loss": 0.1371,
      "step": 132
    }
  ],
  "logging_steps": 66,
  "max_steps": 993,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 4.126063812673536e+16,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}