{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0482180293501049,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9190322580645162,
      "eval_loss": 1.2163052558898926,
      "eval_runtime": 17.8659,
      "eval_samples_per_second": 173.515,
      "eval_steps_per_second": 5.429,
      "step": 477
    },
    {
      "epoch": 1.0482180293501049,
      "grad_norm": 20.34007453918457,
      "learning_rate": 1.4769392033542977e-05,
      "loss": 6.3832,
      "step": 500
    }
  ],
  "logging_steps": 500,
  "max_steps": 1908,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 224151802852992.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.8450808914228156,
    "num_train_epochs": 4,
    "temperature": 2.172574230033706
  }
}