{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 63,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 0.43154916167259216,
      "learning_rate": 2.095238095238095e-05,
      "loss": 0.1419,
      "step": 20
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 0.08845952898263931,
      "learning_rate": 1.1428571428571429e-05,
      "loss": 0.0067,
      "step": 40
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.061147306114435196,
      "learning_rate": 1.9047619047619047e-06,
      "loss": 0.0028,
      "step": 60
    }
  ],
  "logging_steps": 20,
  "max_steps": 63,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 65777763840000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}