{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.23,
  "eval_steps": 500,
  "global_step": 69,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.5566,
      "step": 20
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0001925925925925926,
      "loss": 1.389,
      "step": 40
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00017777777777777779,
      "loss": 1.2155,
      "step": 60
    }
  ],
  "logging_steps": 20,
  "max_steps": 300,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 1.1218588224454656e+16,
  "trial_name": null,
  "trial_params": null
}