{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.21119324181626187,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004223864836325237,
      "eval_loss": NaN,
      "eval_runtime": 5.1758,
      "eval_samples_per_second": 19.321,
      "eval_steps_per_second": 9.66,
      "step": 1
    },
    {
      "epoch": 0.021119324181626188,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.042238648363252376,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.042238648363252376,
      "eval_loss": NaN,
      "eval_runtime": 4.1024,
      "eval_samples_per_second": 24.376,
      "eval_steps_per_second": 12.188,
      "step": 10
    },
    {
      "epoch": 0.06335797254487856,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.08447729672650475,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.08447729672650475,
      "eval_loss": NaN,
      "eval_runtime": 4.2138,
      "eval_samples_per_second": 23.732,
      "eval_steps_per_second": 11.866,
      "step": 20
    },
    {
      "epoch": 0.10559662090813093,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.12671594508975711,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.12671594508975711,
      "eval_loss": NaN,
      "eval_runtime": 4.1196,
      "eval_samples_per_second": 24.274,
      "eval_steps_per_second": 12.137,
      "step": 30
    },
    {
      "epoch": 0.14783526927138332,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.1689545934530095,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.1689545934530095,
      "eval_loss": NaN,
      "eval_runtime": 4.1873,
      "eval_samples_per_second": 23.882,
      "eval_steps_per_second": 11.941,
      "step": 40
    },
    {
      "epoch": 0.1900739176346357,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.21119324181626187,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.21119324181626187,
      "eval_loss": NaN,
      "eval_runtime": 4.0847,
      "eval_samples_per_second": 24.482,
      "eval_steps_per_second": 12.241,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1840392617066496.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}