{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0854700854700856,
  "eval_steps": 500,
  "global_step": 90,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.03,
      "learning_rate": 0.0001320754716981132,
      "loss": 2.756,
      "step": 70
    }
  ],
  "logging_steps": 70,
  "max_steps": 1053,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 7316470581166080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}