{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 50,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 3.4515161514282227,
      "learning_rate": 0.0002,
      "loss": 14.4216,
      "step": 1
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.3591179847717285,
      "learning_rate": 0.0002,
      "loss": 6.9569,
      "step": 2
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 3.386481285095215,
      "learning_rate": 0.0002,
      "loss": 13.3884,
      "step": 3
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.6231248378753662,
      "learning_rate": 0.0002,
      "loss": 6.5371,
      "step": 4
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 1.3547041416168213,
      "learning_rate": 0.0002,
      "loss": 12.6779,
      "step": 5
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.8692656755447388,
      "learning_rate": 0.0002,
      "loss": 6.2879,
      "step": 6
    }
  ],
  "logging_steps": 1,
  "max_steps": 6,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 664020625720320.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}