{
  "best_metric": 0.2622641623020172,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.44692737430167595,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008938547486033519,
      "grad_norm": 30.159088134765625,
      "learning_rate": 5e-05,
      "loss": 9.9592,
      "step": 1
    },
    {
      "epoch": 0.008938547486033519,
      "eval_loss": 7.915379047393799,
      "eval_runtime": 4.311,
      "eval_samples_per_second": 11.598,
      "eval_steps_per_second": 3.016,
      "step": 1
    },
    {
      "epoch": 0.017877094972067038,
      "grad_norm": 34.4140510559082,
      "learning_rate": 0.0001,
      "loss": 10.4724,
      "step": 2
    },
    {
      "epoch": 0.026815642458100558,
      "grad_norm": 60.468650817871094,
      "learning_rate": 9.990365154573717e-05,
      "loss": 8.0167,
      "step": 3
    },
    {
      "epoch": 0.035754189944134075,
      "grad_norm": 20.849802017211914,
      "learning_rate": 9.961501876182148e-05,
      "loss": 2.8984,
      "step": 4
    },
    {
      "epoch": 0.0446927374301676,
      "grad_norm": 6.434566020965576,
      "learning_rate": 9.913533761814537e-05,
      "loss": 0.9473,
      "step": 5
    },
    {
      "epoch": 0.053631284916201116,
      "grad_norm": 5.556005001068115,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.7651,
      "step": 6
    },
    {
      "epoch": 0.06256983240223464,
      "grad_norm": 4.144664764404297,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.563,
      "step": 7
    },
    {
      "epoch": 0.07150837988826815,
      "grad_norm": 4.028663158416748,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.51,
      "step": 8
    },
    {
      "epoch": 0.08044692737430167,
      "grad_norm": 2.8934309482574463,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.4736,
      "step": 9
    },
    {
      "epoch": 0.0893854748603352,
      "grad_norm": 29.83458709716797,
      "learning_rate": 9.397114317029975e-05,
      "loss": 2.5204,
      "step": 10
    },
    {
      "epoch": 0.09832402234636871,
      "grad_norm": 18.27935791015625,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.8818,
      "step": 11
    },
    {
      "epoch": 0.10726256983240223,
      "grad_norm": 4.780270099639893,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.3139,
      "step": 12
    },
    {
      "epoch": 0.11620111731843576,
      "grad_norm": 3.9073874950408936,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.6551,
      "step": 13
    },
    {
      "epoch": 0.12513966480446928,
      "grad_norm": 5.21215295791626,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.6272,
      "step": 14
    },
    {
      "epoch": 0.1340782122905028,
      "grad_norm": 3.4546008110046387,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.5018,
      "step": 15
    },
    {
      "epoch": 0.1430167597765363,
      "grad_norm": 2.792327880859375,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.406,
      "step": 16
    },
    {
      "epoch": 0.15195530726256984,
      "grad_norm": 3.277977705001831,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.3482,
      "step": 17
    },
    {
      "epoch": 0.16089385474860335,
      "grad_norm": 3.2941317558288574,
      "learning_rate": 7.75e-05,
      "loss": 0.3875,
      "step": 18
    },
    {
      "epoch": 0.16983240223463686,
      "grad_norm": 3.6186130046844482,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.357,
      "step": 19
    },
    {
      "epoch": 0.1787709497206704,
      "grad_norm": 3.676929473876953,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.3528,
      "step": 20
    },
    {
      "epoch": 0.1877094972067039,
      "grad_norm": 2.185427188873291,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.437,
      "step": 21
    },
    {
      "epoch": 0.19664804469273742,
      "grad_norm": 2.945129632949829,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.5698,
      "step": 22
    },
    {
      "epoch": 0.20558659217877095,
      "grad_norm": 2.8894119262695312,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.4833,
      "step": 23
    },
    {
      "epoch": 0.21452513966480447,
      "grad_norm": 1.2547894716262817,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.1897,
      "step": 24
    },
    {
      "epoch": 0.22346368715083798,
      "grad_norm": 0.21161526441574097,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.0436,
      "step": 25
    },
    {
      "epoch": 0.22346368715083798,
      "eval_loss": 0.4165439307689667,
      "eval_runtime": 4.3527,
      "eval_samples_per_second": 11.487,
      "eval_steps_per_second": 2.987,
      "step": 25
    },
    {
      "epoch": 0.2324022346368715,
      "grad_norm": 3.016798496246338,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.707,
      "step": 26
    },
    {
      "epoch": 0.24134078212290502,
      "grad_norm": 2.214432716369629,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.4435,
      "step": 27
    },
    {
      "epoch": 0.25027932960893856,
      "grad_norm": 1.871042013168335,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.3622,
      "step": 28
    },
    {
      "epoch": 0.25921787709497207,
      "grad_norm": 1.3092725276947021,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.3011,
      "step": 29
    },
    {
      "epoch": 0.2681564245810056,
      "grad_norm": 1.4508849382400513,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.257,
      "step": 30
    },
    {
      "epoch": 0.2770949720670391,
      "grad_norm": 1.6570039987564087,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.324,
      "step": 31
    },
    {
      "epoch": 0.2860335195530726,
      "grad_norm": 1.6880950927734375,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.2753,
      "step": 32
    },
    {
      "epoch": 0.29497206703910617,
      "grad_norm": 2.029897451400757,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.3435,
      "step": 33
    },
    {
      "epoch": 0.3039106145251397,
      "grad_norm": 2.708217144012451,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.403,
      "step": 34
    },
    {
      "epoch": 0.3128491620111732,
      "grad_norm": 14.175328254699707,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.5983,
      "step": 35
    },
    {
      "epoch": 0.3217877094972067,
      "grad_norm": 6.837980270385742,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.4558,
      "step": 36
    },
    {
      "epoch": 0.3307262569832402,
      "grad_norm": 4.484794616699219,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.3205,
      "step": 37
    },
    {
      "epoch": 0.3396648044692737,
      "grad_norm": 2.619335889816284,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.3569,
      "step": 38
    },
    {
      "epoch": 0.3486033519553073,
      "grad_norm": 2.7390358448028564,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.381,
      "step": 39
    },
    {
      "epoch": 0.3575418994413408,
      "grad_norm": 2.364455223083496,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.3319,
      "step": 40
    },
    {
      "epoch": 0.3664804469273743,
      "grad_norm": 2.2109696865081787,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.3197,
      "step": 41
    },
    {
      "epoch": 0.3754189944134078,
      "grad_norm": 1.8548595905303955,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.2718,
      "step": 42
    },
    {
      "epoch": 0.3843575418994413,
      "grad_norm": 2.3461661338806152,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.3907,
      "step": 43
    },
    {
      "epoch": 0.39329608938547483,
      "grad_norm": 1.327548861503601,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.2497,
      "step": 44
    },
    {
      "epoch": 0.4022346368715084,
      "grad_norm": 1.4733893871307373,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.3123,
      "step": 45
    },
    {
      "epoch": 0.4111731843575419,
      "grad_norm": 1.3677797317504883,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.3053,
      "step": 46
    },
    {
      "epoch": 0.4201117318435754,
      "grad_norm": 1.656186580657959,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.3297,
      "step": 47
    },
    {
      "epoch": 0.42905027932960893,
      "grad_norm": 1.1715149879455566,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.3077,
      "step": 48
    },
    {
      "epoch": 0.43798882681564244,
      "grad_norm": 0.7847478985786438,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.1393,
      "step": 49
    },
    {
      "epoch": 0.44692737430167595,
      "grad_norm": 0.5844078660011292,
      "learning_rate": 1e-05,
      "loss": 0.056,
      "step": 50
    },
    {
      "epoch": 0.44692737430167595,
      "eval_loss": 0.2622641623020172,
      "eval_runtime": 4.3702,
      "eval_samples_per_second": 11.441,
      "eval_steps_per_second": 2.975,
      "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": 5.991396431364096e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}