{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004891171435558816,
  "eval_steps": 4,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016303904785196053,
      "grad_norm": NaN,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.00016303904785196053,
      "eval_loss": NaN,
      "eval_runtime": 159.1332,
      "eval_samples_per_second": 16.232,
      "eval_steps_per_second": 4.059,
      "step": 1
    },
    {
      "epoch": 0.00032607809570392107,
      "grad_norm": NaN,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0004891171435558817,
      "grad_norm": NaN,
      "learning_rate": 6e-06,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0006521561914078421,
      "grad_norm": NaN,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0006521561914078421,
      "eval_loss": NaN,
      "eval_runtime": 157.6821,
      "eval_samples_per_second": 16.381,
      "eval_steps_per_second": 4.097,
      "step": 4
    },
    {
      "epoch": 0.0008151952392598027,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0009782342871117633,
      "grad_norm": NaN,
      "learning_rate": 9.960573506572391e-06,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0011412733349637238,
      "grad_norm": NaN,
      "learning_rate": 9.842915805643156e-06,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0013043123828156843,
      "grad_norm": NaN,
      "learning_rate": 9.648882429441258e-06,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0013043123828156843,
      "eval_loss": NaN,
      "eval_runtime": 157.7205,
      "eval_samples_per_second": 16.377,
      "eval_steps_per_second": 4.096,
      "step": 8
    },
    {
      "epoch": 0.001467351430667645,
      "grad_norm": NaN,
      "learning_rate": 9.381533400219319e-06,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0016303904785196055,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-06,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.001793429526371566,
      "grad_norm": NaN,
      "learning_rate": 8.644843137107058e-06,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.0019564685742235266,
      "grad_norm": NaN,
      "learning_rate": 8.18711994874345e-06,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0019564685742235266,
      "eval_loss": NaN,
      "eval_runtime": 157.7477,
      "eval_samples_per_second": 16.374,
      "eval_steps_per_second": 4.095,
      "step": 12
    },
    {
      "epoch": 0.002119507622075487,
      "grad_norm": NaN,
      "learning_rate": 7.679133974894984e-06,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.0022825466699274476,
      "grad_norm": NaN,
      "learning_rate": 7.128896457825364e-06,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.002445585717779408,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-06,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0026086247656313686,
      "grad_norm": NaN,
      "learning_rate": 5.936906572928625e-06,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.0026086247656313686,
      "eval_loss": NaN,
      "eval_runtime": 157.9311,
      "eval_samples_per_second": 16.355,
      "eval_steps_per_second": 4.09,
      "step": 16
    },
    {
      "epoch": 0.0027716638134833295,
      "grad_norm": NaN,
      "learning_rate": 5.3139525976465675e-06,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.00293470286133529,
      "grad_norm": NaN,
      "learning_rate": 4.686047402353433e-06,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0030977419091872504,
      "grad_norm": NaN,
      "learning_rate": 4.063093427071376e-06,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.003260780957039211,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.003260780957039211,
      "eval_loss": NaN,
      "eval_runtime": 157.6495,
      "eval_samples_per_second": 16.384,
      "eval_steps_per_second": 4.098,
      "step": 20
    },
    {
      "epoch": 0.0034238200048911714,
      "grad_norm": NaN,
      "learning_rate": 2.871103542174637e-06,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.003586859052743132,
      "grad_norm": NaN,
      "learning_rate": 2.320866025105016e-06,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.0037498981005950924,
      "grad_norm": NaN,
      "learning_rate": 1.8128800512565514e-06,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.003912937148447053,
      "grad_norm": NaN,
      "learning_rate": 1.3551568628929434e-06,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.003912937148447053,
      "eval_loss": NaN,
      "eval_runtime": 157.7151,
      "eval_samples_per_second": 16.378,
      "eval_steps_per_second": 4.096,
      "step": 24
    },
    {
      "epoch": 0.004075976196299014,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-07,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.004239015244150974,
      "grad_norm": NaN,
      "learning_rate": 6.184665997806832e-07,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.004402054292002935,
      "grad_norm": NaN,
      "learning_rate": 3.511175705587433e-07,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.004565093339854895,
      "grad_norm": NaN,
      "learning_rate": 1.5708419435684463e-07,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.004565093339854895,
      "eval_loss": NaN,
      "eval_runtime": 157.9793,
      "eval_samples_per_second": 16.35,
      "eval_steps_per_second": 4.089,
      "step": 28
    },
    {
      "epoch": 0.004728132387706856,
      "grad_norm": NaN,
      "learning_rate": 3.9426493427611177e-08,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.004891171435558816,
      "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": 3402500187095040.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}