{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.046511627906976744,
  "eval_steps": 4,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015503875968992248,
      "grad_norm": NaN,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0015503875968992248,
      "eval_loss": NaN,
      "eval_runtime": 35.283,
      "eval_samples_per_second": 7.709,
      "eval_steps_per_second": 1.927,
      "step": 1
    },
    {
      "epoch": 0.0031007751937984496,
      "grad_norm": NaN,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.004651162790697674,
      "grad_norm": NaN,
      "learning_rate": 6e-06,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.006201550387596899,
      "grad_norm": NaN,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.006201550387596899,
      "eval_loss": NaN,
      "eval_runtime": 34.7904,
      "eval_samples_per_second": 7.818,
      "eval_steps_per_second": 1.955,
      "step": 4
    },
    {
      "epoch": 0.007751937984496124,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.009302325581395349,
      "grad_norm": NaN,
      "learning_rate": 9.960573506572391e-06,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.010852713178294573,
      "grad_norm": NaN,
      "learning_rate": 9.842915805643156e-06,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.012403100775193798,
      "grad_norm": NaN,
      "learning_rate": 9.648882429441258e-06,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.012403100775193798,
      "eval_loss": NaN,
      "eval_runtime": 34.7892,
      "eval_samples_per_second": 7.819,
      "eval_steps_per_second": 1.955,
      "step": 8
    },
    {
      "epoch": 0.013953488372093023,
      "grad_norm": NaN,
      "learning_rate": 9.381533400219319e-06,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.015503875968992248,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-06,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.017054263565891473,
      "grad_norm": NaN,
      "learning_rate": 8.644843137107058e-06,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.018604651162790697,
      "grad_norm": NaN,
      "learning_rate": 8.18711994874345e-06,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.018604651162790697,
      "eval_loss": NaN,
      "eval_runtime": 34.7783,
      "eval_samples_per_second": 7.821,
      "eval_steps_per_second": 1.955,
      "step": 12
    },
    {
      "epoch": 0.020155038759689922,
      "grad_norm": NaN,
      "learning_rate": 7.679133974894984e-06,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.021705426356589147,
      "grad_norm": NaN,
      "learning_rate": 7.128896457825364e-06,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.023255813953488372,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-06,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.024806201550387597,
      "grad_norm": NaN,
      "learning_rate": 5.936906572928625e-06,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.024806201550387597,
      "eval_loss": NaN,
      "eval_runtime": 34.7803,
      "eval_samples_per_second": 7.821,
      "eval_steps_per_second": 1.955,
      "step": 16
    },
    {
      "epoch": 0.02635658914728682,
      "grad_norm": NaN,
      "learning_rate": 5.3139525976465675e-06,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.027906976744186046,
      "grad_norm": NaN,
      "learning_rate": 4.686047402353433e-06,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.02945736434108527,
      "grad_norm": NaN,
      "learning_rate": 4.063093427071376e-06,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.031007751937984496,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.031007751937984496,
      "eval_loss": NaN,
      "eval_runtime": 34.7827,
      "eval_samples_per_second": 7.82,
      "eval_steps_per_second": 1.955,
      "step": 20
    },
    {
      "epoch": 0.03255813953488372,
      "grad_norm": NaN,
      "learning_rate": 2.871103542174637e-06,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.034108527131782945,
      "grad_norm": NaN,
      "learning_rate": 2.320866025105016e-06,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.03565891472868217,
      "grad_norm": NaN,
      "learning_rate": 1.8128800512565514e-06,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.037209302325581395,
      "grad_norm": NaN,
      "learning_rate": 1.3551568628929434e-06,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.037209302325581395,
      "eval_loss": NaN,
      "eval_runtime": 34.8145,
      "eval_samples_per_second": 7.813,
      "eval_steps_per_second": 1.953,
      "step": 24
    },
    {
      "epoch": 0.03875968992248062,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-07,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.040310077519379844,
      "grad_norm": NaN,
      "learning_rate": 6.184665997806832e-07,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.04186046511627907,
      "grad_norm": NaN,
      "learning_rate": 3.511175705587433e-07,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.043410852713178294,
      "grad_norm": NaN,
      "learning_rate": 1.5708419435684463e-07,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.043410852713178294,
      "eval_loss": NaN,
      "eval_runtime": 34.7859,
      "eval_samples_per_second": 7.819,
      "eval_steps_per_second": 1.955,
      "step": 28
    },
    {
      "epoch": 0.04496124031007752,
      "grad_norm": NaN,
      "learning_rate": 3.9426493427611177e-08,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.046511627906976744,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    }
  ],
  "logging_steps": 1,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.22524620816384e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}