{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 68,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 25.125,
      "learning_rate": 8.676470588235295e-06,
      "loss": 4.8964,
      "step": 10
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 16.875,
      "learning_rate": 7.205882352941177e-06,
      "loss": 2.6002,
      "step": 20
    },
    {
      "epoch": 1.7878787878787878,
      "grad_norm": 14.875,
      "learning_rate": 5.735294117647059e-06,
      "loss": 2.3388,
      "step": 30
    },
    {
      "epoch": 2.3636363636363638,
      "grad_norm": 14.3125,
      "learning_rate": 4.264705882352942e-06,
      "loss": 2.0516,
      "step": 40
    },
    {
      "epoch": 2.9696969696969697,
      "grad_norm": 14.4375,
      "learning_rate": 2.7941176470588237e-06,
      "loss": 2.0798,
      "step": 50
    },
    {
      "epoch": 3.5454545454545454,
      "grad_norm": 13.625,
      "learning_rate": 1.323529411764706e-06,
      "loss": 1.9136,
      "step": 60
    },
    {
      "epoch": 4.0,
      "step": 68,
      "total_flos": 9144106739564544.0,
      "train_loss": 2.558909444247975,
      "train_runtime": 325.4125,
      "train_samples_per_second": 3.319,
      "train_steps_per_second": 0.209
    }
  ],
  "logging_steps": 10,
  "max_steps": 68,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 16,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9144106739564544.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}