{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.5723270440251573,
  "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": 0.6438709677419355,
      "eval_loss": 0.23163336515426636,
      "eval_runtime": 5.7827,
      "eval_samples_per_second": 536.083,
      "eval_steps_per_second": 11.24,
      "step": 318
    },
    {
      "epoch": 1.57,
      "learning_rate": 1.606918238993711e-05,
      "loss": 0.3713,
      "step": 500
    }
  ],
  "logging_steps": 500,
  "max_steps": 2544,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 500,
  "total_flos": 129219778448376.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.9894659129615386,
    "num_train_epochs": 8,
    "temperature": 5
  }
}