{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1892744479495268,
  "eval_steps": 4,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006309148264984227,
      "grad_norm": NaN,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.006309148264984227,
      "eval_loss": NaN,
      "eval_runtime": 6.1533,
      "eval_samples_per_second": 10.889,
      "eval_steps_per_second": 2.763,
      "step": 1
    },
    {
      "epoch": 0.012618296529968454,
      "grad_norm": NaN,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.01892744479495268,
      "grad_norm": NaN,
      "learning_rate": 6e-06,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.025236593059936908,
      "grad_norm": NaN,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.025236593059936908,
      "eval_loss": NaN,
      "eval_runtime": 4.613,
      "eval_samples_per_second": 14.524,
      "eval_steps_per_second": 3.685,
      "step": 4
    },
    {
      "epoch": 0.031545741324921134,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.03785488958990536,
      "grad_norm": NaN,
      "learning_rate": 9.960573506572391e-06,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.04416403785488959,
      "grad_norm": NaN,
      "learning_rate": 9.842915805643156e-06,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.050473186119873815,
      "grad_norm": NaN,
      "learning_rate": 9.648882429441258e-06,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.050473186119873815,
      "eval_loss": NaN,
      "eval_runtime": 4.6089,
      "eval_samples_per_second": 14.537,
      "eval_steps_per_second": 3.689,
      "step": 8
    },
    {
      "epoch": 0.056782334384858045,
      "grad_norm": NaN,
      "learning_rate": 9.381533400219319e-06,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.06309148264984227,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-06,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0694006309148265,
      "grad_norm": NaN,
      "learning_rate": 8.644843137107058e-06,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.07570977917981073,
      "grad_norm": NaN,
      "learning_rate": 8.18711994874345e-06,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.07570977917981073,
      "eval_loss": NaN,
      "eval_runtime": 4.6133,
      "eval_samples_per_second": 14.523,
      "eval_steps_per_second": 3.685,
      "step": 12
    },
    {
      "epoch": 0.08201892744479496,
      "grad_norm": NaN,
      "learning_rate": 7.679133974894984e-06,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.08832807570977919,
      "grad_norm": NaN,
      "learning_rate": 7.128896457825364e-06,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.0946372239747634,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-06,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.10094637223974763,
      "grad_norm": NaN,
      "learning_rate": 5.936906572928625e-06,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.10094637223974763,
      "eval_loss": NaN,
      "eval_runtime": 4.6088,
      "eval_samples_per_second": 14.537,
      "eval_steps_per_second": 3.689,
      "step": 16
    },
    {
      "epoch": 0.10725552050473186,
      "grad_norm": NaN,
      "learning_rate": 5.3139525976465675e-06,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.11356466876971609,
      "grad_norm": NaN,
      "learning_rate": 4.686047402353433e-06,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.11987381703470032,
      "grad_norm": NaN,
      "learning_rate": 4.063093427071376e-06,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.12618296529968454,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.12618296529968454,
      "eval_loss": NaN,
      "eval_runtime": 4.6163,
      "eval_samples_per_second": 14.514,
      "eval_steps_per_second": 3.683,
      "step": 20
    },
    {
      "epoch": 0.13249211356466878,
      "grad_norm": NaN,
      "learning_rate": 2.871103542174637e-06,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.138801261829653,
      "grad_norm": NaN,
      "learning_rate": 2.320866025105016e-06,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.14511041009463724,
      "grad_norm": NaN,
      "learning_rate": 1.8128800512565514e-06,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.15141955835962145,
      "grad_norm": NaN,
      "learning_rate": 1.3551568628929434e-06,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.15141955835962145,
      "eval_loss": NaN,
      "eval_runtime": 4.6246,
      "eval_samples_per_second": 14.488,
      "eval_steps_per_second": 3.676,
      "step": 24
    },
    {
      "epoch": 0.15772870662460567,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-07,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.1640378548895899,
      "grad_norm": NaN,
      "learning_rate": 6.184665997806832e-07,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.17034700315457413,
      "grad_norm": NaN,
      "learning_rate": 3.511175705587433e-07,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.17665615141955837,
      "grad_norm": NaN,
      "learning_rate": 1.5708419435684463e-07,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.17665615141955837,
      "eval_loss": NaN,
      "eval_runtime": 4.6139,
      "eval_samples_per_second": 14.521,
      "eval_steps_per_second": 3.684,
      "step": 28
    },
    {
      "epoch": 0.1829652996845426,
      "grad_norm": NaN,
      "learning_rate": 3.9426493427611177e-08,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.1892744479495268,
      "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": 4192264393850880.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}