{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.995169082125604,
  "eval_steps": 500,
  "global_step": 465,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8,
      "learning_rate": 4.592916195656322e-05,
      "loss": 0.2521,
      "step": 124
    },
    {
      "epoch": 1.6,
      "learning_rate": 2.650224885357251e-05,
      "loss": 0.0304,
      "step": 248
    },
    {
      "epoch": 2.4,
      "learning_rate": 5.86231516774709e-06,
      "loss": 0.0144,
      "step": 372
    }
  ],
  "logging_steps": 124,
  "max_steps": 465,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 3941964849205248.0,
  "trial_name": null,
  "trial_params": null
}