{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007668711656441718,
  "eval_steps": 4,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002556237218813906,
      "grad_norm": NaN,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0002556237218813906,
      "eval_loss": NaN,
      "eval_runtime": 174.0269,
      "eval_samples_per_second": 9.47,
      "eval_steps_per_second": 2.367,
      "step": 1
    },
    {
      "epoch": 0.0005112474437627812,
      "grad_norm": NaN,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0007668711656441718,
      "grad_norm": NaN,
      "learning_rate": 6e-06,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0010224948875255625,
      "grad_norm": NaN,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0010224948875255625,
      "eval_loss": NaN,
      "eval_runtime": 173.9954,
      "eval_samples_per_second": 9.472,
      "eval_steps_per_second": 2.368,
      "step": 4
    },
    {
      "epoch": 0.001278118609406953,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0015337423312883436,
      "grad_norm": NaN,
      "learning_rate": 9.960573506572391e-06,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0017893660531697342,
      "grad_norm": NaN,
      "learning_rate": 9.842915805643156e-06,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.002044989775051125,
      "grad_norm": NaN,
      "learning_rate": 9.648882429441258e-06,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.002044989775051125,
      "eval_loss": NaN,
      "eval_runtime": 173.9734,
      "eval_samples_per_second": 9.473,
      "eval_steps_per_second": 2.368,
      "step": 8
    },
    {
      "epoch": 0.0023006134969325155,
      "grad_norm": NaN,
      "learning_rate": 9.381533400219319e-06,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.002556237218813906,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-06,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0028118609406952966,
      "grad_norm": NaN,
      "learning_rate": 8.644843137107058e-06,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.003067484662576687,
      "grad_norm": NaN,
      "learning_rate": 8.18711994874345e-06,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.003067484662576687,
      "eval_loss": NaN,
      "eval_runtime": 174.0067,
      "eval_samples_per_second": 9.471,
      "eval_steps_per_second": 2.368,
      "step": 12
    },
    {
      "epoch": 0.0033231083844580778,
      "grad_norm": NaN,
      "learning_rate": 7.679133974894984e-06,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.0035787321063394683,
      "grad_norm": NaN,
      "learning_rate": 7.128896457825364e-06,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.003834355828220859,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-06,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.00408997955010225,
      "grad_norm": NaN,
      "learning_rate": 5.936906572928625e-06,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.00408997955010225,
      "eval_loss": NaN,
      "eval_runtime": 174.0854,
      "eval_samples_per_second": 9.467,
      "eval_steps_per_second": 2.367,
      "step": 16
    },
    {
      "epoch": 0.0043456032719836404,
      "grad_norm": NaN,
      "learning_rate": 5.3139525976465675e-06,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.004601226993865031,
      "grad_norm": NaN,
      "learning_rate": 4.686047402353433e-06,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0048568507157464216,
      "grad_norm": NaN,
      "learning_rate": 4.063093427071376e-06,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.005112474437627812,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.005112474437627812,
      "eval_loss": NaN,
      "eval_runtime": 174.2011,
      "eval_samples_per_second": 9.46,
      "eval_steps_per_second": 2.365,
      "step": 20
    },
    {
      "epoch": 0.005368098159509203,
      "grad_norm": NaN,
      "learning_rate": 2.871103542174637e-06,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.005623721881390593,
      "grad_norm": NaN,
      "learning_rate": 2.320866025105016e-06,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.005879345603271984,
      "grad_norm": NaN,
      "learning_rate": 1.8128800512565514e-06,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.006134969325153374,
      "grad_norm": NaN,
      "learning_rate": 1.3551568628929434e-06,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.006134969325153374,
      "eval_loss": NaN,
      "eval_runtime": 174.2467,
      "eval_samples_per_second": 9.458,
      "eval_steps_per_second": 2.364,
      "step": 24
    },
    {
      "epoch": 0.006390593047034765,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-07,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0066462167689161555,
      "grad_norm": NaN,
      "learning_rate": 6.184665997806832e-07,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.006901840490797546,
      "grad_norm": NaN,
      "learning_rate": 3.511175705587433e-07,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.007157464212678937,
      "grad_norm": NaN,
      "learning_rate": 1.5708419435684463e-07,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.007157464212678937,
      "eval_loss": NaN,
      "eval_runtime": 174.0326,
      "eval_samples_per_second": 9.469,
      "eval_steps_per_second": 2.367,
      "step": 28
    },
    {
      "epoch": 0.007413087934560327,
      "grad_norm": NaN,
      "learning_rate": 3.9426493427611177e-08,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.007668711656441718,
      "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": 1.054713575374848e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}