{
  "best_metric": 10.362602233886719,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.2796225096120238,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005592450192240475,
      "grad_norm": 0.1390429437160492,
      "learning_rate": 5e-05,
      "loss": 10.383,
      "step": 1
    },
    {
      "epoch": 0.005592450192240475,
      "eval_loss": 10.380449295043945,
      "eval_runtime": 0.096,
      "eval_samples_per_second": 520.665,
      "eval_steps_per_second": 135.373,
      "step": 1
    },
    {
      "epoch": 0.01118490038448095,
      "grad_norm": 0.13009823858737946,
      "learning_rate": 0.0001,
      "loss": 10.3826,
      "step": 2
    },
    {
      "epoch": 0.016777350576721427,
      "grad_norm": 0.12154008448123932,
      "learning_rate": 9.990365154573717e-05,
      "loss": 10.3829,
      "step": 3
    },
    {
      "epoch": 0.0223698007689619,
      "grad_norm": 0.11613494157791138,
      "learning_rate": 9.961501876182148e-05,
      "loss": 10.3805,
      "step": 4
    },
    {
      "epoch": 0.027962250961202376,
      "grad_norm": 0.10675308853387833,
      "learning_rate": 9.913533761814537e-05,
      "loss": 10.3801,
      "step": 5
    },
    {
      "epoch": 0.033554701153442855,
      "grad_norm": 0.10143845528364182,
      "learning_rate": 9.846666218300807e-05,
      "loss": 10.3803,
      "step": 6
    },
    {
      "epoch": 0.03914715134568333,
      "grad_norm": 0.0989459678530693,
      "learning_rate": 9.761185582727977e-05,
      "loss": 10.3798,
      "step": 7
    },
    {
      "epoch": 0.0447396015379238,
      "grad_norm": 0.10024382174015045,
      "learning_rate": 9.657457896300791e-05,
      "loss": 10.3799,
      "step": 8
    },
    {
      "epoch": 0.05033205173016428,
      "grad_norm": 0.100783571600914,
      "learning_rate": 9.535927336897098e-05,
      "loss": 10.3795,
      "step": 9
    },
    {
      "epoch": 0.05592450192240475,
      "grad_norm": 0.10001285374164581,
      "learning_rate": 9.397114317029975e-05,
      "loss": 10.3779,
      "step": 10
    },
    {
      "epoch": 0.06151695211464523,
      "grad_norm": 0.10107259452342987,
      "learning_rate": 9.241613255361455e-05,
      "loss": 10.3739,
      "step": 11
    },
    {
      "epoch": 0.06710940230688571,
      "grad_norm": 0.10555021464824677,
      "learning_rate": 9.070090031310558e-05,
      "loss": 10.3721,
      "step": 12
    },
    {
      "epoch": 0.07270185249912618,
      "grad_norm": 0.14678636193275452,
      "learning_rate": 8.883279133655399e-05,
      "loss": 10.3768,
      "step": 13
    },
    {
      "epoch": 0.07829430269136665,
      "grad_norm": 0.1420448124408722,
      "learning_rate": 8.681980515339464e-05,
      "loss": 10.3765,
      "step": 14
    },
    {
      "epoch": 0.08388675288360713,
      "grad_norm": 0.13489459455013275,
      "learning_rate": 8.467056167950311e-05,
      "loss": 10.3757,
      "step": 15
    },
    {
      "epoch": 0.0894792030758476,
      "grad_norm": 0.1267830729484558,
      "learning_rate": 8.239426430539243e-05,
      "loss": 10.3754,
      "step": 16
    },
    {
      "epoch": 0.09507165326808809,
      "grad_norm": 0.12438750267028809,
      "learning_rate": 8.000066048588211e-05,
      "loss": 10.3742,
      "step": 17
    },
    {
      "epoch": 0.10066410346032856,
      "grad_norm": 0.12414400279521942,
      "learning_rate": 7.75e-05,
      "loss": 10.375,
      "step": 18
    },
    {
      "epoch": 0.10625655365256903,
      "grad_norm": 0.1243206188082695,
      "learning_rate": 7.490299105985507e-05,
      "loss": 10.374,
      "step": 19
    },
    {
      "epoch": 0.1118490038448095,
      "grad_norm": 0.12306420505046844,
      "learning_rate": 7.222075445642904e-05,
      "loss": 10.3756,
      "step": 20
    },
    {
      "epoch": 0.11744145403704999,
      "grad_norm": 0.12505832314491272,
      "learning_rate": 6.946477593864228e-05,
      "loss": 10.3745,
      "step": 21
    },
    {
      "epoch": 0.12303390422929046,
      "grad_norm": 0.12902094423770905,
      "learning_rate": 6.664685702961344e-05,
      "loss": 10.3725,
      "step": 22
    },
    {
      "epoch": 0.12862635442153092,
      "grad_norm": 0.12437836825847626,
      "learning_rate": 6.377906449072578e-05,
      "loss": 10.3711,
      "step": 23
    },
    {
      "epoch": 0.13421880461377142,
      "grad_norm": 0.13075384497642517,
      "learning_rate": 6.087367864990233e-05,
      "loss": 10.3668,
      "step": 24
    },
    {
      "epoch": 0.1398112548060119,
      "grad_norm": 0.14323678612709045,
      "learning_rate": 5.794314081535644e-05,
      "loss": 10.3651,
      "step": 25
    },
    {
      "epoch": 0.1398112548060119,
      "eval_loss": 10.369172096252441,
      "eval_runtime": 0.0935,
      "eval_samples_per_second": 534.565,
      "eval_steps_per_second": 138.987,
      "step": 25
    },
    {
      "epoch": 0.14540370499825236,
      "grad_norm": 0.18515342473983765,
      "learning_rate": 5.500000000000001e-05,
      "loss": 10.3706,
      "step": 26
    },
    {
      "epoch": 0.15099615519049284,
      "grad_norm": 0.17940200865268707,
      "learning_rate": 5.205685918464356e-05,
      "loss": 10.3699,
      "step": 27
    },
    {
      "epoch": 0.1565886053827333,
      "grad_norm": 0.17424097657203674,
      "learning_rate": 4.912632135009769e-05,
      "loss": 10.3697,
      "step": 28
    },
    {
      "epoch": 0.16218105557497378,
      "grad_norm": 0.16775143146514893,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 10.3678,
      "step": 29
    },
    {
      "epoch": 0.16777350576721425,
      "grad_norm": 0.16442053020000458,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 10.3684,
      "step": 30
    },
    {
      "epoch": 0.17336595595945473,
      "grad_norm": 0.15736381709575653,
      "learning_rate": 4.053522406135775e-05,
      "loss": 10.3697,
      "step": 31
    },
    {
      "epoch": 0.1789584061516952,
      "grad_norm": 0.15212076902389526,
      "learning_rate": 3.777924554357096e-05,
      "loss": 10.3699,
      "step": 32
    },
    {
      "epoch": 0.1845508563439357,
      "grad_norm": 0.15667906403541565,
      "learning_rate": 3.509700894014496e-05,
      "loss": 10.37,
      "step": 33
    },
    {
      "epoch": 0.19014330653617617,
      "grad_norm": 0.15856710076332092,
      "learning_rate": 3.250000000000001e-05,
      "loss": 10.369,
      "step": 34
    },
    {
      "epoch": 0.19573575672841664,
      "grad_norm": 0.15956778824329376,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 10.3678,
      "step": 35
    },
    {
      "epoch": 0.20132820692065712,
      "grad_norm": 0.15860746800899506,
      "learning_rate": 2.760573569460757e-05,
      "loss": 10.3644,
      "step": 36
    },
    {
      "epoch": 0.2069206571128976,
      "grad_norm": 0.16222454607486725,
      "learning_rate": 2.53294383204969e-05,
      "loss": 10.3621,
      "step": 37
    },
    {
      "epoch": 0.21251310730513806,
      "grad_norm": 0.21722282469272614,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 10.3658,
      "step": 38
    },
    {
      "epoch": 0.21810555749737853,
      "grad_norm": 0.21604430675506592,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 10.3655,
      "step": 39
    },
    {
      "epoch": 0.223698007689619,
      "grad_norm": 0.20557966828346252,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 10.3654,
      "step": 40
    },
    {
      "epoch": 0.22929045788185948,
      "grad_norm": 0.20266205072402954,
      "learning_rate": 1.758386744638546e-05,
      "loss": 10.3643,
      "step": 41
    },
    {
      "epoch": 0.23488290807409998,
      "grad_norm": 0.18894320726394653,
      "learning_rate": 1.602885682970026e-05,
      "loss": 10.3643,
      "step": 42
    },
    {
      "epoch": 0.24047535826634045,
      "grad_norm": 0.18438370525836945,
      "learning_rate": 1.464072663102903e-05,
      "loss": 10.3655,
      "step": 43
    },
    {
      "epoch": 0.24606780845858092,
      "grad_norm": 0.18429425358772278,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 10.3658,
      "step": 44
    },
    {
      "epoch": 0.25166025865082137,
      "grad_norm": 0.1751224398612976,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 10.366,
      "step": 45
    },
    {
      "epoch": 0.25725270884306184,
      "grad_norm": 0.17902234196662903,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 10.3659,
      "step": 46
    },
    {
      "epoch": 0.26284515903530237,
      "grad_norm": 0.17663754522800446,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 10.365,
      "step": 47
    },
    {
      "epoch": 0.26843760922754284,
      "grad_norm": 0.17328204214572906,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 10.3631,
      "step": 48
    },
    {
      "epoch": 0.2740300594197833,
      "grad_norm": 0.1784089356660843,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 10.3607,
      "step": 49
    },
    {
      "epoch": 0.2796225096120238,
      "grad_norm": 0.19091790914535522,
      "learning_rate": 1e-05,
      "loss": 10.3588,
      "step": 50
    },
    {
      "epoch": 0.2796225096120238,
      "eval_loss": 10.362602233886719,
      "eval_runtime": 0.0947,
      "eval_samples_per_second": 527.983,
      "eval_steps_per_second": 137.275,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 43075455025152.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}