{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.974025974025974,
  "eval_steps": 500,
  "global_step": 114,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.7077,
      "step": 46
    },
    {
      "epoch": 1.59,
      "learning_rate": 4.313725490196079e-05,
      "loss": 0.5052,
      "step": 92
    }
  ],
  "logging_steps": 46,
  "max_steps": 114,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 2.965609408899318e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}