{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 2138,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.23386342376052385,
      "grad_norm": 8.736445426940918,
      "learning_rate": 6.350629773686866e-06,
      "loss": 0.5901,
      "step": 500
    },
    {
      "epoch": 0.4677268475210477,
      "grad_norm": 3.966376543045044,
      "learning_rate": 4.412098096737272e-06,
      "loss": 0.5471,
      "step": 1000
    },
    {
      "epoch": 0.7015902712815716,
      "grad_norm": 31.678607940673828,
      "learning_rate": 2.47356641978768e-06,
      "loss": 0.522,
      "step": 1500
    },
    {
      "epoch": 0.9354536950420954,
      "grad_norm": 2.151951789855957,
      "learning_rate": 5.350347428380876e-07,
      "loss": 0.5237,
      "step": 2000
    }
  ],
  "logging_steps": 500,
  "max_steps": 2138,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 32508327551424.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 8.289161450636458e-06,
    "num_train_epochs": 1,
    "per_device_train_batch_size": 4,
    "seed": 2
  }
}