{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.986666666666667,
  "eval_steps": 1000,
  "global_step": 336,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 5.800321578979492,
      "learning_rate": 0.00019500000000000002,
      "loss": 1.885,
      "step": 200
    }
  ],
  "logging_steps": 200,
  "max_steps": 336,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.305980358426624e+19,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}