{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9643564356435643,
  "eval_steps": 500,
  "global_step": 62,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.31683168316831684,
      "grad_norm": 3.118149757385254,
      "learning_rate": 0.00019853538358476932,
      "loss": 1.3203,
      "step": 10
    },
    {
      "epoch": 0.6336633663366337,
      "grad_norm": 2.3026437759399414,
      "learning_rate": 0.0001736741137876405,
      "loss": 0.4201,
      "step": 20
    },
    {
      "epoch": 0.9504950495049505,
      "grad_norm": 1.8703222274780273,
      "learning_rate": 0.0001362807705350641,
      "loss": 0.3188,
      "step": 30
    },
    {
      "epoch": 1.2673267326732673,
      "grad_norm": 1.66342031955719,
      "learning_rate": 8.014095333542548e-05,
      "loss": 0.2563,
      "step": 40
    },
    {
      "epoch": 1.5841584158415842,
      "grad_norm": 1.1295819282531738,
      "learning_rate": 3.030624313447067e-05,
      "loss": 0.2174,
      "step": 50
    },
    {
      "epoch": 1.900990099009901,
      "grad_norm": 2.049751043319702,
      "learning_rate": 2.5988083057666533e-06,
      "loss": 0.1957,
      "step": 60
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4959013881077760.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}