{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9821782178217822,
  "eval_steps": 500,
  "global_step": 31,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.31683168316831684,
      "grad_norm": 3.1086041927337646,
      "learning_rate": 0.00019853538358476932,
      "loss": 1.3199,
      "step": 10
    },
    {
      "epoch": 0.6336633663366337,
      "grad_norm": 2.342080593109131,
      "learning_rate": 0.0001736741137876405,
      "loss": 0.4194,
      "step": 20
    },
    {
      "epoch": 0.9504950495049505,
      "grad_norm": 1.8433202505111694,
      "learning_rate": 0.00012542183341934872,
      "loss": 0.3086,
      "step": 30
    }
  ],
  "logging_steps": 10,
  "max_steps": 62,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2512368436690944.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}