{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008333333333333333,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "grad_norm": 2.3380820751190186,
      "learning_rate": 3e-06,
      "loss": 1.0991,
      "step": 10
    },
    {
      "grad_norm": 0.9051423072814941,
      "learning_rate": 6.333333333333334e-06,
      "loss": 1.062,
      "step": 20
    },
    {
      "grad_norm": 0.9199342727661133,
      "learning_rate": 9.666666666666667e-06,
      "loss": 1.0577,
      "step": 30
    },
    {
      "grad_norm": 0.5548149943351746,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 1.0346,
      "step": 40
    },
    {
      "grad_norm": 0.7406973838806152,
      "learning_rate": 1.6333333333333335e-05,
      "loss": 1.0301,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 6000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}