{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005546311702717693,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011092623405435386,
      "grad_norm": 80.64155578613281,
      "learning_rate": 3.6697247706422022e-06,
      "loss": 13.4594,
      "step": 2
    },
    {
      "epoch": 0.0022185246810870773,
      "grad_norm": 66.91927337646484,
      "learning_rate": 7.3394495412844045e-06,
      "loss": 13.8607,
      "step": 4
    },
    {
      "epoch": 0.0033277870216306157,
      "grad_norm": 63.7406005859375,
      "learning_rate": 1.1009174311926607e-05,
      "loss": 13.0338,
      "step": 6
    },
    {
      "epoch": 0.004437049362174155,
      "grad_norm": 61.71236801147461,
      "learning_rate": 1.4678899082568809e-05,
      "loss": 12.9429,
      "step": 8
    },
    {
      "epoch": 0.005546311702717693,
      "grad_norm": 63.84341812133789,
      "learning_rate": 1.834862385321101e-05,
      "loss": 12.5906,
      "step": 10
    }
  ],
  "logging_steps": 2,
  "max_steps": 3606,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 24358315622400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}