{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.1474654377880182,
  "eval_steps": 500,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7373271889400922,
      "grad_norm": 3.5594277055722987,
      "learning_rate": 6.989700043360187e-06,
      "loss": 0.2551,
      "step": 5
    },
    {
      "epoch": 1.4423963133640554,
      "grad_norm": 2.372242854274958,
      "learning_rate": 9.999999999999999e-06,
      "loss": 0.1799,
      "step": 10
    },
    {
      "epoch": 2.1474654377880182,
      "grad_norm": 1.6282442964267505,
      "learning_rate": 1.1760912590556813e-05,
      "loss": 0.1006,
      "step": 15
    }
  ],
  "logging_steps": 5,
  "max_steps": 35,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 168007351402496.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}