{
  "best_metric": 10.372812271118164,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.023454220293764108,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004690844058752822,
      "grad_norm": 0.019355913624167442,
      "learning_rate": 5e-05,
      "loss": 10.3766,
      "step": 1
    },
    {
      "epoch": 0.0004690844058752822,
      "eval_loss": 10.375811576843262,
      "eval_runtime": 0.0872,
      "eval_samples_per_second": 573.546,
      "eval_steps_per_second": 149.122,
      "step": 1
    },
    {
      "epoch": 0.0009381688117505644,
      "grad_norm": 0.01959487795829773,
      "learning_rate": 0.0001,
      "loss": 10.376,
      "step": 2
    },
    {
      "epoch": 0.0014072532176258466,
      "grad_norm": 0.019254960119724274,
      "learning_rate": 9.990365154573717e-05,
      "loss": 10.3757,
      "step": 3
    },
    {
      "epoch": 0.0018763376235011288,
      "grad_norm": 0.016795136034488678,
      "learning_rate": 9.961501876182148e-05,
      "loss": 10.3758,
      "step": 4
    },
    {
      "epoch": 0.002345422029376411,
      "grad_norm": 0.01704433374106884,
      "learning_rate": 9.913533761814537e-05,
      "loss": 10.3744,
      "step": 5
    },
    {
      "epoch": 0.0028145064352516932,
      "grad_norm": 0.01669495552778244,
      "learning_rate": 9.846666218300807e-05,
      "loss": 10.3749,
      "step": 6
    },
    {
      "epoch": 0.0032835908411269752,
      "grad_norm": 0.017888028174638748,
      "learning_rate": 9.761185582727977e-05,
      "loss": 10.3745,
      "step": 7
    },
    {
      "epoch": 0.0037526752470022576,
      "grad_norm": 0.016524380072951317,
      "learning_rate": 9.657457896300791e-05,
      "loss": 10.3746,
      "step": 8
    },
    {
      "epoch": 0.00422175965287754,
      "grad_norm": 0.017360864207148552,
      "learning_rate": 9.535927336897098e-05,
      "loss": 10.374,
      "step": 9
    },
    {
      "epoch": 0.004690844058752822,
      "grad_norm": 0.017124928534030914,
      "learning_rate": 9.397114317029975e-05,
      "loss": 10.3736,
      "step": 10
    },
    {
      "epoch": 0.005159928464628104,
      "grad_norm": 0.01649409532546997,
      "learning_rate": 9.241613255361455e-05,
      "loss": 10.3736,
      "step": 11
    },
    {
      "epoch": 0.0056290128705033865,
      "grad_norm": 0.018352489918470383,
      "learning_rate": 9.070090031310558e-05,
      "loss": 10.3735,
      "step": 12
    },
    {
      "epoch": 0.0060980972763786685,
      "grad_norm": 0.018697958439588547,
      "learning_rate": 8.883279133655399e-05,
      "loss": 10.3739,
      "step": 13
    },
    {
      "epoch": 0.0065671816822539504,
      "grad_norm": 0.01770050823688507,
      "learning_rate": 8.681980515339464e-05,
      "loss": 10.3754,
      "step": 14
    },
    {
      "epoch": 0.007036266088129232,
      "grad_norm": 0.0220442246645689,
      "learning_rate": 8.467056167950311e-05,
      "loss": 10.3739,
      "step": 15
    },
    {
      "epoch": 0.007505350494004515,
      "grad_norm": 0.018395403400063515,
      "learning_rate": 8.239426430539243e-05,
      "loss": 10.3732,
      "step": 16
    },
    {
      "epoch": 0.007974434899879796,
      "grad_norm": 0.018865734338760376,
      "learning_rate": 8.000066048588211e-05,
      "loss": 10.3759,
      "step": 17
    },
    {
      "epoch": 0.00844351930575508,
      "grad_norm": 0.01738630421459675,
      "learning_rate": 7.75e-05,
      "loss": 10.3728,
      "step": 18
    },
    {
      "epoch": 0.008912603711630362,
      "grad_norm": 0.017076440155506134,
      "learning_rate": 7.490299105985507e-05,
      "loss": 10.3739,
      "step": 19
    },
    {
      "epoch": 0.009381688117505643,
      "grad_norm": 0.01879049837589264,
      "learning_rate": 7.222075445642904e-05,
      "loss": 10.3728,
      "step": 20
    },
    {
      "epoch": 0.009850772523380926,
      "grad_norm": 0.019032716751098633,
      "learning_rate": 6.946477593864228e-05,
      "loss": 10.3731,
      "step": 21
    },
    {
      "epoch": 0.010319856929256207,
      "grad_norm": 0.017903704196214676,
      "learning_rate": 6.664685702961344e-05,
      "loss": 10.373,
      "step": 22
    },
    {
      "epoch": 0.01078894133513149,
      "grad_norm": 0.020931022241711617,
      "learning_rate": 6.377906449072578e-05,
      "loss": 10.3722,
      "step": 23
    },
    {
      "epoch": 0.011258025741006773,
      "grad_norm": 0.0221738051623106,
      "learning_rate": 6.087367864990233e-05,
      "loss": 10.3704,
      "step": 24
    },
    {
      "epoch": 0.011727110146882054,
      "grad_norm": 0.019214561209082603,
      "learning_rate": 5.794314081535644e-05,
      "loss": 10.3695,
      "step": 25
    },
    {
      "epoch": 0.011727110146882054,
      "eval_loss": 10.37377643585205,
      "eval_runtime": 0.0875,
      "eval_samples_per_second": 571.655,
      "eval_steps_per_second": 148.63,
      "step": 25
    },
    {
      "epoch": 0.012196194552757337,
      "grad_norm": 0.021041052415966988,
      "learning_rate": 5.500000000000001e-05,
      "loss": 10.3734,
      "step": 26
    },
    {
      "epoch": 0.01266527895863262,
      "grad_norm": 0.02031891979277134,
      "learning_rate": 5.205685918464356e-05,
      "loss": 10.3741,
      "step": 27
    },
    {
      "epoch": 0.013134363364507901,
      "grad_norm": 0.02011536993086338,
      "learning_rate": 4.912632135009769e-05,
      "loss": 10.3737,
      "step": 28
    },
    {
      "epoch": 0.013603447770383184,
      "grad_norm": 0.021063942462205887,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 10.372,
      "step": 29
    },
    {
      "epoch": 0.014072532176258465,
      "grad_norm": 0.020221510902047157,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 10.3736,
      "step": 30
    },
    {
      "epoch": 0.014541616582133748,
      "grad_norm": 0.019827982410788536,
      "learning_rate": 4.053522406135775e-05,
      "loss": 10.3722,
      "step": 31
    },
    {
      "epoch": 0.01501070098800903,
      "grad_norm": 0.022068917751312256,
      "learning_rate": 3.777924554357096e-05,
      "loss": 10.3729,
      "step": 32
    },
    {
      "epoch": 0.015479785393884312,
      "grad_norm": 0.02005210891366005,
      "learning_rate": 3.509700894014496e-05,
      "loss": 10.3723,
      "step": 33
    },
    {
      "epoch": 0.015948869799759593,
      "grad_norm": 0.021499594673514366,
      "learning_rate": 3.250000000000001e-05,
      "loss": 10.3741,
      "step": 34
    },
    {
      "epoch": 0.016417954205634876,
      "grad_norm": 0.02275359071791172,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 10.3708,
      "step": 35
    },
    {
      "epoch": 0.01688703861151016,
      "grad_norm": 0.02215169370174408,
      "learning_rate": 2.760573569460757e-05,
      "loss": 10.3718,
      "step": 36
    },
    {
      "epoch": 0.01735612301738544,
      "grad_norm": 0.025299865752458572,
      "learning_rate": 2.53294383204969e-05,
      "loss": 10.3707,
      "step": 37
    },
    {
      "epoch": 0.017825207423260724,
      "grad_norm": 0.02483261004090309,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 10.373,
      "step": 38
    },
    {
      "epoch": 0.018294291829136004,
      "grad_norm": 0.022907955572009087,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 10.3737,
      "step": 39
    },
    {
      "epoch": 0.018763376235011286,
      "grad_norm": 0.02221311815083027,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 10.3733,
      "step": 40
    },
    {
      "epoch": 0.01923246064088657,
      "grad_norm": 0.02572779916226864,
      "learning_rate": 1.758386744638546e-05,
      "loss": 10.3716,
      "step": 41
    },
    {
      "epoch": 0.019701545046761852,
      "grad_norm": 0.023600785061717033,
      "learning_rate": 1.602885682970026e-05,
      "loss": 10.3732,
      "step": 42
    },
    {
      "epoch": 0.020170629452637135,
      "grad_norm": 0.022225745022296906,
      "learning_rate": 1.464072663102903e-05,
      "loss": 10.373,
      "step": 43
    },
    {
      "epoch": 0.020639713858512414,
      "grad_norm": 0.023699507117271423,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 10.3711,
      "step": 44
    },
    {
      "epoch": 0.021108798264387697,
      "grad_norm": 0.025384273380041122,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 10.3736,
      "step": 45
    },
    {
      "epoch": 0.02157788267026298,
      "grad_norm": 0.025175515562295914,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 10.3727,
      "step": 46
    },
    {
      "epoch": 0.022046967076138263,
      "grad_norm": 0.02010641247034073,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 10.3712,
      "step": 47
    },
    {
      "epoch": 0.022516051482013546,
      "grad_norm": 0.02617836184799671,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 10.3704,
      "step": 48
    },
    {
      "epoch": 0.02298513588788883,
      "grad_norm": 0.025789782404899597,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 10.3732,
      "step": 49
    },
    {
      "epoch": 0.023454220293764108,
      "grad_norm": 0.023422811180353165,
      "learning_rate": 1e-05,
      "loss": 10.3715,
      "step": 50
    },
    {
      "epoch": 0.023454220293764108,
      "eval_loss": 10.372812271118164,
      "eval_runtime": 0.0841,
      "eval_samples_per_second": 594.394,
      "eval_steps_per_second": 154.542,
      "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": 42768059596800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}