{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 32,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15625,
      "grad_norm": 2.5280188432077177,
      "learning_rate": 4.950832101651063e-05,
      "loss": 0.8169,
      "num_tokens": 453332.0,
      "step": 5
    },
    {
      "epoch": 0.3125,
      "grad_norm": 0.9475344961205666,
      "learning_rate": 4.422075857324137e-05,
      "loss": 0.7187,
      "num_tokens": 962061.0,
      "step": 10
    },
    {
      "epoch": 0.46875,
      "grad_norm": 0.8669499876238266,
      "learning_rate": 3.4452882373436316e-05,
      "loss": 0.6962,
      "num_tokens": 1480011.0,
      "step": 15
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.7414502601393275,
      "learning_rate": 2.282198695660042e-05,
      "loss": 0.6864,
      "num_tokens": 2036201.0,
      "step": 20
    },
    {
      "epoch": 0.78125,
      "grad_norm": 0.7321573052542948,
      "learning_rate": 1.2444561356925697e-05,
      "loss": 0.7114,
      "num_tokens": 2546314.0,
      "step": 25
    },
    {
      "epoch": 0.9375,
      "grad_norm": 0.6540265945690075,
      "learning_rate": 6.1012283833590465e-06,
      "loss": 0.6695,
      "num_tokens": 2995452.0,
      "step": 30
    },
    {
      "epoch": 1.0,
      "num_tokens": 3103934.0,
      "step": 32,
      "total_flos": 6336405323776.0,
      "train_loss": 0.7175193056464195,
      "train_runtime": 236.3521,
      "train_samples_per_second": 2.115,
      "train_steps_per_second": 0.135
    }
  ],
  "logging_steps": 5,
  "max_steps": 32,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6336405323776.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}