{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.582278481012658,
  "eval_steps": 500,
  "global_step": 1840,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.43,
      "learning_rate": 2.2964135021097045e-05,
      "loss": 2.9246,
      "step": 1010
    }
  ],
  "logging_steps": 1010,
  "max_steps": 3160,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 94770466652160.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}