{
  "best_metric": 0.0005954264779575169,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.06422349777224742,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012844699554449485,
      "grad_norm": 0.4161011576652527,
      "learning_rate": 5e-05,
      "loss": 0.2276,
      "step": 1
    },
    {
      "epoch": 0.0012844699554449485,
      "eval_loss": 0.677666425704956,
      "eval_runtime": 4.3008,
      "eval_samples_per_second": 11.626,
      "eval_steps_per_second": 3.023,
      "step": 1
    },
    {
      "epoch": 0.002568939910889897,
      "grad_norm": 0.587279200553894,
      "learning_rate": 0.0001,
      "loss": 0.293,
      "step": 2
    },
    {
      "epoch": 0.0038534098663348454,
      "grad_norm": 0.6024236083030701,
      "learning_rate": 9.990365154573717e-05,
      "loss": 0.2936,
      "step": 3
    },
    {
      "epoch": 0.005137879821779794,
      "grad_norm": 0.5766181349754333,
      "learning_rate": 9.961501876182148e-05,
      "loss": 0.1895,
      "step": 4
    },
    {
      "epoch": 0.006422349777224742,
      "grad_norm": 0.7392317056655884,
      "learning_rate": 9.913533761814537e-05,
      "loss": 0.0935,
      "step": 5
    },
    {
      "epoch": 0.007706819732669691,
      "grad_norm": 0.40463578701019287,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.0339,
      "step": 6
    },
    {
      "epoch": 0.00899128968811464,
      "grad_norm": 0.11740680783987045,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.0139,
      "step": 7
    },
    {
      "epoch": 0.010275759643559588,
      "grad_norm": 0.17799319326877594,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.008,
      "step": 8
    },
    {
      "epoch": 0.011560229599004535,
      "grad_norm": 0.14940109848976135,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.0071,
      "step": 9
    },
    {
      "epoch": 0.012844699554449484,
      "grad_norm": 0.2678021192550659,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.0066,
      "step": 10
    },
    {
      "epoch": 0.014129169509894433,
      "grad_norm": 0.1295286864042282,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.0035,
      "step": 11
    },
    {
      "epoch": 0.015413639465339381,
      "grad_norm": 0.1710747331380844,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.0025,
      "step": 12
    },
    {
      "epoch": 0.01669810942078433,
      "grad_norm": 0.08956174552440643,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.0083,
      "step": 13
    },
    {
      "epoch": 0.01798257937622928,
      "grad_norm": 0.08717551827430725,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.002,
      "step": 14
    },
    {
      "epoch": 0.019267049331674228,
      "grad_norm": 0.0825677365064621,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.0018,
      "step": 15
    },
    {
      "epoch": 0.020551519287119176,
      "grad_norm": 0.09371823817491531,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.003,
      "step": 16
    },
    {
      "epoch": 0.02183598924256412,
      "grad_norm": 0.018300285562872887,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.0009,
      "step": 17
    },
    {
      "epoch": 0.02312045919800907,
      "grad_norm": 0.06318554282188416,
      "learning_rate": 7.75e-05,
      "loss": 0.001,
      "step": 18
    },
    {
      "epoch": 0.02440492915345402,
      "grad_norm": 0.035294026136398315,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.0009,
      "step": 19
    },
    {
      "epoch": 0.025689399108898968,
      "grad_norm": 0.05147477984428406,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.0023,
      "step": 20
    },
    {
      "epoch": 0.026973869064343917,
      "grad_norm": 0.027873137965798378,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.0008,
      "step": 21
    },
    {
      "epoch": 0.028258339019788865,
      "grad_norm": 0.025377586483955383,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.0002,
      "step": 22
    },
    {
      "epoch": 0.029542808975233814,
      "grad_norm": 0.026686685159802437,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.0007,
      "step": 23
    },
    {
      "epoch": 0.030827278930678763,
      "grad_norm": 0.035086534917354584,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.0012,
      "step": 24
    },
    {
      "epoch": 0.03211174888612371,
      "grad_norm": 0.03124326281249523,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.0007,
      "step": 25
    },
    {
      "epoch": 0.03211174888612371,
      "eval_loss": 0.001722008571960032,
      "eval_runtime": 4.3428,
      "eval_samples_per_second": 11.513,
      "eval_steps_per_second": 2.993,
      "step": 25
    },
    {
      "epoch": 0.03339621884156866,
      "grad_norm": 0.10468930006027222,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0027,
      "step": 26
    },
    {
      "epoch": 0.03468068879701361,
      "grad_norm": 0.043511610478162766,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.0003,
      "step": 27
    },
    {
      "epoch": 0.03596515875245856,
      "grad_norm": 0.047194723039865494,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.0004,
      "step": 28
    },
    {
      "epoch": 0.03724962870790351,
      "grad_norm": 0.010208461433649063,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.0002,
      "step": 29
    },
    {
      "epoch": 0.038534098663348455,
      "grad_norm": 0.004359261132776737,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.0001,
      "step": 30
    },
    {
      "epoch": 0.039818568618793404,
      "grad_norm": 0.004191869869828224,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.0001,
      "step": 31
    },
    {
      "epoch": 0.04110303857423835,
      "grad_norm": 0.00581542169675231,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.0002,
      "step": 32
    },
    {
      "epoch": 0.042387508529683295,
      "grad_norm": 0.029106365516781807,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.0006,
      "step": 33
    },
    {
      "epoch": 0.04367197848512824,
      "grad_norm": 0.012221266515552998,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.0001,
      "step": 34
    },
    {
      "epoch": 0.04495644844057319,
      "grad_norm": 0.024582967162132263,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.0003,
      "step": 35
    },
    {
      "epoch": 0.04624091839601814,
      "grad_norm": 0.002639414044097066,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.0001,
      "step": 36
    },
    {
      "epoch": 0.04752538835146309,
      "grad_norm": 0.006335746496915817,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.0001,
      "step": 37
    },
    {
      "epoch": 0.04880985830690804,
      "grad_norm": 0.05119847506284714,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.0009,
      "step": 38
    },
    {
      "epoch": 0.05009432826235299,
      "grad_norm": 0.005954067222774029,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.0002,
      "step": 39
    },
    {
      "epoch": 0.051378798217797936,
      "grad_norm": 0.018545329570770264,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.0004,
      "step": 40
    },
    {
      "epoch": 0.052663268173242885,
      "grad_norm": 0.04680047929286957,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.0005,
      "step": 41
    },
    {
      "epoch": 0.05394773812868783,
      "grad_norm": 0.030956776812672615,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.0002,
      "step": 42
    },
    {
      "epoch": 0.05523220808413278,
      "grad_norm": 0.029979685321450233,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.0009,
      "step": 43
    },
    {
      "epoch": 0.05651667803957773,
      "grad_norm": 0.05502396449446678,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.0004,
      "step": 44
    },
    {
      "epoch": 0.05780114799502268,
      "grad_norm": 0.022603997960686684,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.0003,
      "step": 45
    },
    {
      "epoch": 0.05908561795046763,
      "grad_norm": 0.06383545696735382,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.0017,
      "step": 46
    },
    {
      "epoch": 0.06037008790591258,
      "grad_norm": 0.004797203931957483,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.0001,
      "step": 47
    },
    {
      "epoch": 0.061654557861357526,
      "grad_norm": 0.001430455595254898,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.0001,
      "step": 48
    },
    {
      "epoch": 0.06293902781680247,
      "grad_norm": 0.0032753057312220335,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.0001,
      "step": 49
    },
    {
      "epoch": 0.06422349777224742,
      "grad_norm": 0.026153214275836945,
      "learning_rate": 1e-05,
      "loss": 0.0006,
      "step": 50
    },
    {
      "epoch": 0.06422349777224742,
      "eval_loss": 0.0005954264779575169,
      "eval_runtime": 4.3372,
      "eval_samples_per_second": 11.528,
      "eval_steps_per_second": 2.997,
      "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": 5.969016129878753e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}