{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 13.0,
  "eval_steps": 500,
  "global_step": 13,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 3.8962098330259325,
      "epoch": 10.0,
      "grad_norm": 368.0,
      "learning_rate": 8e-05,
      "loss": 5.190721893310547,
      "mean_token_accuracy": 0.37155905868858097,
      "num_tokens": 6910.0,
      "step": 10
    }
  ],
  "logging_steps": 10,
  "max_steps": 15,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 167262041137152.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}