{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2647058823529412,
  "eval_steps": 9,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014705882352941176,
      "eval_loss": NaN,
      "eval_runtime": 17.0771,
      "eval_samples_per_second": 6.734,
      "eval_steps_per_second": 0.878,
      "step": 1
    },
    {
      "epoch": 0.04411764705882353,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 2.2991,
      "step": 3
    },
    {
      "epoch": 0.08823529411764706,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 2.5431,
      "step": 6
    },
    {
      "epoch": 0.1323529411764706,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 13.2201,
      "step": 9
    },
    {
      "epoch": 0.1323529411764706,
      "eval_loss": NaN,
      "eval_runtime": 16.7373,
      "eval_samples_per_second": 6.871,
      "eval_steps_per_second": 0.896,
      "step": 9
    },
    {
      "epoch": 0.17647058823529413,
      "grad_norm": NaN,
      "learning_rate": 9.987820251299122e-05,
      "loss": 16.8201,
      "step": 12
    },
    {
      "epoch": 0.22058823529411764,
      "grad_norm": NaN,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.7364,
      "step": 15
    },
    {
      "epoch": 0.2647058823529412,
      "grad_norm": NaN,
      "learning_rate": 9.806308479691595e-05,
      "loss": 3.6238,
      "step": 18
    },
    {
      "epoch": 0.2647058823529412,
      "eval_loss": NaN,
      "eval_runtime": 16.7549,
      "eval_samples_per_second": 6.864,
      "eval_steps_per_second": 0.895,
      "step": 18
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.118799267233792e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}