{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 4707,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 42730.50390625,
      "learning_rate": 3.341494571002768e-05,
      "loss": 0.1197,
      "step": 1569
    },
    {
      "epoch": 2.0,
      "grad_norm": 56775.671875,
      "learning_rate": 1.6712795401319992e-05,
      "loss": 0.072,
      "step": 3138
    },
    {
      "epoch": 3.0,
      "grad_norm": 45534.921875,
      "learning_rate": 1.0645092612305728e-08,
      "loss": 0.0638,
      "step": 4707
    }
  ],
  "logging_steps": 500,
  "max_steps": 4707,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.5372537254903808e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}