{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.992555831265509,
  "eval_steps": 500,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.9528535980148884,
      "grad_norm": 0.2596491436134033,
      "learning_rate": 7.660160382576683e-06,
      "loss": 0.6825,
      "step": 50
    },
    {
      "epoch": 3.9925558312655087,
      "grad_norm": 0.2211565177698784,
      "learning_rate": 1.2717891755841722e-06,
      "loss": 0.5625,
      "step": 100
    }
  ],
  "logging_steps": 50,
  "max_steps": 125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 237791669649408.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}