{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.011379800853485065,
  "eval_steps": 8,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005689900426742532,
      "eval_loss": 9.121294021606445,
      "eval_runtime": 43.1024,
      "eval_samples_per_second": 17.168,
      "eval_steps_per_second": 8.584,
      "step": 1
    },
    {
      "epoch": 0.0017069701280227596,
      "grad_norm": 16.72486686706543,
      "learning_rate": 6e-05,
      "loss": 8.6592,
      "step": 3
    },
    {
      "epoch": 0.0034139402560455193,
      "grad_norm": 14.888457298278809,
      "learning_rate": 0.00012,
      "loss": 7.913,
      "step": 6
    },
    {
      "epoch": 0.004551920341394026,
      "eval_loss": 3.8307814598083496,
      "eval_runtime": 42.5013,
      "eval_samples_per_second": 17.411,
      "eval_steps_per_second": 8.706,
      "step": 8
    },
    {
      "epoch": 0.005120910384068279,
      "grad_norm": 12.3302001953125,
      "learning_rate": 0.00018,
      "loss": 4.487,
      "step": 9
    },
    {
      "epoch": 0.0068278805120910386,
      "grad_norm": 18.477922439575195,
      "learning_rate": 0.00019510565162951537,
      "loss": 3.4117,
      "step": 12
    },
    {
      "epoch": 0.008534850640113799,
      "grad_norm": 13.56683349609375,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.1899,
      "step": 15
    },
    {
      "epoch": 0.009103840682788052,
      "eval_loss": 1.833335280418396,
      "eval_runtime": 42.6016,
      "eval_samples_per_second": 17.37,
      "eval_steps_per_second": 8.685,
      "step": 16
    },
    {
      "epoch": 0.010241820768136558,
      "grad_norm": 18.128826141357422,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.728,
      "step": 18
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7418872835604480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}