{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0010100499974748751,
  "eval_steps": 5,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.7336666498325e-05,
      "eval_loss": NaN,
      "eval_runtime": 1835.8254,
      "eval_samples_per_second": 13.624,
      "eval_steps_per_second": 1.703,
      "step": 1
    },
    {
      "epoch": 0.000202009999494975,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.000336683332491625,
      "eval_loss": NaN,
      "eval_runtime": 1836.1211,
      "eval_samples_per_second": 13.622,
      "eval_steps_per_second": 1.703,
      "step": 5
    },
    {
      "epoch": 0.00040401999898995,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.000606029998484925,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00067336666498325,
      "eval_loss": NaN,
      "eval_runtime": 1837.914,
      "eval_samples_per_second": 13.609,
      "eval_steps_per_second": 1.701,
      "step": 10
    },
    {
      "epoch": 0.0008080399979799,
      "grad_norm": NaN,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0010100499974748751,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0010100499974748751,
      "eval_loss": NaN,
      "eval_runtime": 1837.3679,
      "eval_samples_per_second": 13.613,
      "eval_steps_per_second": 1.702,
      "step": 15
    }
  ],
  "logging_steps": 3,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.338196047056077e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}