{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 786,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "learning_rate": 0.00017991513437057993,
      "loss": 0.6215,
      "step": 157
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001357850070721358,
      "loss": 0.4901,
      "step": 314
    },
    {
      "epoch": 0.6,
      "learning_rate": 9.165487977369166e-05,
      "loss": 0.4843,
      "step": 471
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.7241867043847245e-05,
      "loss": 0.274,
      "step": 628
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.828854314002829e-06,
      "loss": 0.1995,
      "step": 785
    }
  ],
  "logging_steps": 157,
  "max_steps": 786,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}