{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 256,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.999924701839145e-05,
      "loss": 1.1317,
      "step": 1
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.939778208732605,
      "eval_runtime": 86.8536,
      "eval_samples_per_second": 177.667,
      "eval_steps_per_second": 0.357,
      "step": 256
    },
    {
      "epoch": 1.0,
      "step": 256,
      "total_flos": 428809534832640.0,
      "train_loss": 0.9700739588588476,
      "train_runtime": 2923.7602,
      "train_samples_per_second": 44.731,
      "train_steps_per_second": 0.088
    }
  ],
  "logging_steps": 500,
  "max_steps": 256,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 428809534832640.0,
  "trial_name": null,
  "trial_params": null
}