{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2005513439007581,
  "eval_steps": 291,
  "global_step": 291,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06891798759476224,
      "grad_norm": 22.43581199645996,
      "learning_rate": 9.890136982846565e-06,
      "loss": 0.5932,
      "step": 100
    },
    {
      "epoch": 0.13783597518952448,
      "grad_norm": 17.24200439453125,
      "learning_rate": 9.552035901252971e-06,
      "loss": 0.5145,
      "step": 200
    },
    {
      "epoch": 0.2005513439007581,
      "eval_accuracy": 0.7659483067229899,
      "eval_loss": 0.47258511185646057,
      "eval_runtime": 1145.9546,
      "eval_samples_per_second": 73.129,
      "eval_steps_per_second": 9.142,
      "step": 291
    }
  ],
  "logging_steps": 100,
  "max_steps": 1451,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 291,
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}