{
  "best_metric": 4.016265392303467,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.6974716652136007,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013949433304272014,
      "grad_norm": 7.363111972808838,
      "learning_rate": 5e-05,
      "loss": 5.8736,
      "step": 1
    },
    {
      "epoch": 0.013949433304272014,
      "eval_loss": 9.326899528503418,
      "eval_runtime": 2.037,
      "eval_samples_per_second": 24.546,
      "eval_steps_per_second": 6.382,
      "step": 1
    },
    {
      "epoch": 0.02789886660854403,
      "grad_norm": 9.719325065612793,
      "learning_rate": 0.0001,
      "loss": 6.5754,
      "step": 2
    },
    {
      "epoch": 0.041848299912816043,
      "grad_norm": 7.773379802703857,
      "learning_rate": 9.990365154573717e-05,
      "loss": 6.3283,
      "step": 3
    },
    {
      "epoch": 0.05579773321708806,
      "grad_norm": 3.33626651763916,
      "learning_rate": 9.961501876182148e-05,
      "loss": 5.7989,
      "step": 4
    },
    {
      "epoch": 0.06974716652136007,
      "grad_norm": 3.496938705444336,
      "learning_rate": 9.913533761814537e-05,
      "loss": 5.5673,
      "step": 5
    },
    {
      "epoch": 0.08369659982563209,
      "grad_norm": 4.142089366912842,
      "learning_rate": 9.846666218300807e-05,
      "loss": 5.355,
      "step": 6
    },
    {
      "epoch": 0.0976460331299041,
      "grad_norm": 4.253803730010986,
      "learning_rate": 9.761185582727977e-05,
      "loss": 5.1066,
      "step": 7
    },
    {
      "epoch": 0.11159546643417612,
      "grad_norm": 3.290839433670044,
      "learning_rate": 9.657457896300791e-05,
      "loss": 5.0173,
      "step": 8
    },
    {
      "epoch": 0.12554489973844812,
      "grad_norm": 4.412205696105957,
      "learning_rate": 9.535927336897098e-05,
      "loss": 4.8093,
      "step": 9
    },
    {
      "epoch": 0.13949433304272013,
      "grad_norm": 4.175014495849609,
      "learning_rate": 9.397114317029975e-05,
      "loss": 4.4967,
      "step": 10
    },
    {
      "epoch": 0.15344376634699217,
      "grad_norm": 3.934361696243286,
      "learning_rate": 9.241613255361455e-05,
      "loss": 4.5042,
      "step": 11
    },
    {
      "epoch": 0.16739319965126417,
      "grad_norm": 5.009128570556641,
      "learning_rate": 9.070090031310558e-05,
      "loss": 3.7794,
      "step": 12
    },
    {
      "epoch": 0.18134263295553618,
      "grad_norm": 5.36450719833374,
      "learning_rate": 8.883279133655399e-05,
      "loss": 4.5505,
      "step": 13
    },
    {
      "epoch": 0.1952920662598082,
      "grad_norm": 5.2228899002075195,
      "learning_rate": 8.681980515339464e-05,
      "loss": 4.6535,
      "step": 14
    },
    {
      "epoch": 0.2092414995640802,
      "grad_norm": 3.968933582305908,
      "learning_rate": 8.467056167950311e-05,
      "loss": 4.6139,
      "step": 15
    },
    {
      "epoch": 0.22319093286835223,
      "grad_norm": 2.7600717544555664,
      "learning_rate": 8.239426430539243e-05,
      "loss": 4.4797,
      "step": 16
    },
    {
      "epoch": 0.23714036617262424,
      "grad_norm": 1.5951428413391113,
      "learning_rate": 8.000066048588211e-05,
      "loss": 4.376,
      "step": 17
    },
    {
      "epoch": 0.25108979947689625,
      "grad_norm": 1.9203548431396484,
      "learning_rate": 7.75e-05,
      "loss": 4.4635,
      "step": 18
    },
    {
      "epoch": 0.26503923278116825,
      "grad_norm": 2.370145559310913,
      "learning_rate": 7.490299105985507e-05,
      "loss": 4.3938,
      "step": 19
    },
    {
      "epoch": 0.27898866608544026,
      "grad_norm": 2.8391361236572266,
      "learning_rate": 7.222075445642904e-05,
      "loss": 4.4165,
      "step": 20
    },
    {
      "epoch": 0.29293809938971227,
      "grad_norm": 2.6807332038879395,
      "learning_rate": 6.946477593864228e-05,
      "loss": 4.4067,
      "step": 21
    },
    {
      "epoch": 0.30688753269398433,
      "grad_norm": 2.280893325805664,
      "learning_rate": 6.664685702961344e-05,
      "loss": 4.3394,
      "step": 22
    },
    {
      "epoch": 0.32083696599825634,
      "grad_norm": 2.4688901901245117,
      "learning_rate": 6.377906449072578e-05,
      "loss": 4.0924,
      "step": 23
    },
    {
      "epoch": 0.33478639930252835,
      "grad_norm": 2.70896577835083,
      "learning_rate": 6.087367864990233e-05,
      "loss": 3.8322,
      "step": 24
    },
    {
      "epoch": 0.34873583260680036,
      "grad_norm": 3.547678232192993,
      "learning_rate": 5.794314081535644e-05,
      "loss": 3.6481,
      "step": 25
    },
    {
      "epoch": 0.34873583260680036,
      "eval_loss": 4.197577953338623,
      "eval_runtime": 2.0767,
      "eval_samples_per_second": 24.077,
      "eval_steps_per_second": 6.26,
      "step": 25
    },
    {
      "epoch": 0.36268526591107236,
      "grad_norm": 3.973175048828125,
      "learning_rate": 5.500000000000001e-05,
      "loss": 4.4533,
      "step": 26
    },
    {
      "epoch": 0.37663469921534437,
      "grad_norm": 4.574081897735596,
      "learning_rate": 5.205685918464356e-05,
      "loss": 4.4782,
      "step": 27
    },
    {
      "epoch": 0.3905841325196164,
      "grad_norm": 4.432999610900879,
      "learning_rate": 4.912632135009769e-05,
      "loss": 4.6537,
      "step": 28
    },
    {
      "epoch": 0.4045335658238884,
      "grad_norm": 3.599513530731201,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 4.4924,
      "step": 29
    },
    {
      "epoch": 0.4184829991281604,
      "grad_norm": 3.2482171058654785,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 4.517,
      "step": 30
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 2.7505600452423096,
      "learning_rate": 4.053522406135775e-05,
      "loss": 4.4046,
      "step": 31
    },
    {
      "epoch": 0.44638186573670446,
      "grad_norm": 2.255084276199341,
      "learning_rate": 3.777924554357096e-05,
      "loss": 4.154,
      "step": 32
    },
    {
      "epoch": 0.46033129904097647,
      "grad_norm": 1.9739567041397095,
      "learning_rate": 3.509700894014496e-05,
      "loss": 4.3462,
      "step": 33
    },
    {
      "epoch": 0.4742807323452485,
      "grad_norm": 1.9505712985992432,
      "learning_rate": 3.250000000000001e-05,
      "loss": 4.0326,
      "step": 34
    },
    {
      "epoch": 0.4882301656495205,
      "grad_norm": 2.435300350189209,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 4.1367,
      "step": 35
    },
    {
      "epoch": 0.5021795989537925,
      "grad_norm": 3.183511257171631,
      "learning_rate": 2.760573569460757e-05,
      "loss": 3.8502,
      "step": 36
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 3.9571962356567383,
      "learning_rate": 2.53294383204969e-05,
      "loss": 3.8177,
      "step": 37
    },
    {
      "epoch": 0.5300784655623365,
      "grad_norm": 1.17935049533844,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 4.0578,
      "step": 38
    },
    {
      "epoch": 0.5440278988666085,
      "grad_norm": 1.1350454092025757,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 4.1775,
      "step": 39
    },
    {
      "epoch": 0.5579773321708805,
      "grad_norm": 1.0570968389511108,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 4.1952,
      "step": 40
    },
    {
      "epoch": 0.5719267654751525,
      "grad_norm": 1.0743228197097778,
      "learning_rate": 1.758386744638546e-05,
      "loss": 4.2512,
      "step": 41
    },
    {
      "epoch": 0.5858761987794245,
      "grad_norm": 1.1253777742385864,
      "learning_rate": 1.602885682970026e-05,
      "loss": 4.266,
      "step": 42
    },
    {
      "epoch": 0.5998256320836965,
      "grad_norm": 1.2194774150848389,
      "learning_rate": 1.464072663102903e-05,
      "loss": 4.1919,
      "step": 43
    },
    {
      "epoch": 0.6137750653879687,
      "grad_norm": 1.2656453847885132,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 4.2019,
      "step": 44
    },
    {
      "epoch": 0.6277244986922407,
      "grad_norm": 1.4768873453140259,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 4.191,
      "step": 45
    },
    {
      "epoch": 0.6416739319965127,
      "grad_norm": 1.5102301836013794,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 4.0265,
      "step": 46
    },
    {
      "epoch": 0.6556233653007847,
      "grad_norm": 1.6276775598526,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 4.0218,
      "step": 47
    },
    {
      "epoch": 0.6695727986050567,
      "grad_norm": 1.962693214416504,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 3.9513,
      "step": 48
    },
    {
      "epoch": 0.6835222319093287,
      "grad_norm": 2.404271364212036,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 3.7333,
      "step": 49
    },
    {
      "epoch": 0.6974716652136007,
      "grad_norm": 4.255843639373779,
      "learning_rate": 1e-05,
      "loss": 3.6049,
      "step": 50
    },
    {
      "epoch": 0.6974716652136007,
      "eval_loss": 4.016265392303467,
      "eval_runtime": 2.0762,
      "eval_samples_per_second": 24.082,
      "eval_steps_per_second": 6.261,
      "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": 1.62480894509056e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}