{
  "best_metric": 1.1349619626998901,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.03266372693124286,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016331863465621427,
      "grad_norm": 1.671673059463501,
      "learning_rate": 1.001e-05,
      "loss": 1.0081,
      "step": 1
    },
    {
      "epoch": 0.00016331863465621427,
      "eval_loss": 1.9000940322875977,
      "eval_runtime": 345.3153,
      "eval_samples_per_second": 7.466,
      "eval_steps_per_second": 1.868,
      "step": 1
    },
    {
      "epoch": 0.00032663726931242854,
      "grad_norm": 2.1853973865509033,
      "learning_rate": 2.002e-05,
      "loss": 1.0249,
      "step": 2
    },
    {
      "epoch": 0.0004899559039686428,
      "grad_norm": 2.061541795730591,
      "learning_rate": 3.0029999999999995e-05,
      "loss": 1.0868,
      "step": 3
    },
    {
      "epoch": 0.0006532745386248571,
      "grad_norm": 2.0026113986968994,
      "learning_rate": 4.004e-05,
      "loss": 1.2093,
      "step": 4
    },
    {
      "epoch": 0.0008165931732810714,
      "grad_norm": 1.3478747606277466,
      "learning_rate": 5.005e-05,
      "loss": 0.9586,
      "step": 5
    },
    {
      "epoch": 0.0009799118079372856,
      "grad_norm": 1.2198477983474731,
      "learning_rate": 6.005999999999999e-05,
      "loss": 1.001,
      "step": 6
    },
    {
      "epoch": 0.0011432304425935,
      "grad_norm": 1.0008301734924316,
      "learning_rate": 7.006999999999998e-05,
      "loss": 1.0274,
      "step": 7
    },
    {
      "epoch": 0.0013065490772497142,
      "grad_norm": 0.9373151063919067,
      "learning_rate": 8.008e-05,
      "loss": 1.0383,
      "step": 8
    },
    {
      "epoch": 0.0014698677119059284,
      "grad_norm": 0.984042763710022,
      "learning_rate": 9.009e-05,
      "loss": 0.9748,
      "step": 9
    },
    {
      "epoch": 0.0016331863465621427,
      "grad_norm": 0.9123459458351135,
      "learning_rate": 0.0001001,
      "loss": 1.0147,
      "step": 10
    },
    {
      "epoch": 0.001796504981218357,
      "grad_norm": 0.941821277141571,
      "learning_rate": 9.957315789473684e-05,
      "loss": 0.8924,
      "step": 11
    },
    {
      "epoch": 0.0019598236158745713,
      "grad_norm": 0.8732932209968567,
      "learning_rate": 9.904631578947367e-05,
      "loss": 0.9978,
      "step": 12
    },
    {
      "epoch": 0.0021231422505307855,
      "grad_norm": 0.8224309086799622,
      "learning_rate": 9.851947368421052e-05,
      "loss": 1.064,
      "step": 13
    },
    {
      "epoch": 0.002286460885187,
      "grad_norm": 0.9332011342048645,
      "learning_rate": 9.799263157894736e-05,
      "loss": 1.0589,
      "step": 14
    },
    {
      "epoch": 0.002449779519843214,
      "grad_norm": 0.9349180459976196,
      "learning_rate": 9.746578947368421e-05,
      "loss": 1.1028,
      "step": 15
    },
    {
      "epoch": 0.0026130981544994283,
      "grad_norm": 0.8387799263000488,
      "learning_rate": 9.693894736842104e-05,
      "loss": 1.0083,
      "step": 16
    },
    {
      "epoch": 0.0027764167891556426,
      "grad_norm": 0.8592500686645508,
      "learning_rate": 9.641210526315789e-05,
      "loss": 1.0184,
      "step": 17
    },
    {
      "epoch": 0.002939735423811857,
      "grad_norm": 0.8980984687805176,
      "learning_rate": 9.588526315789473e-05,
      "loss": 0.937,
      "step": 18
    },
    {
      "epoch": 0.003103054058468071,
      "grad_norm": 0.8308787941932678,
      "learning_rate": 9.535842105263157e-05,
      "loss": 0.9237,
      "step": 19
    },
    {
      "epoch": 0.0032663726931242854,
      "grad_norm": 1.0007582902908325,
      "learning_rate": 9.483157894736841e-05,
      "loss": 1.0406,
      "step": 20
    },
    {
      "epoch": 0.0034296913277804997,
      "grad_norm": 1.081726312637329,
      "learning_rate": 9.430473684210526e-05,
      "loss": 1.007,
      "step": 21
    },
    {
      "epoch": 0.003593009962436714,
      "grad_norm": 0.9985299110412598,
      "learning_rate": 9.37778947368421e-05,
      "loss": 1.0914,
      "step": 22
    },
    {
      "epoch": 0.0037563285970929282,
      "grad_norm": 1.0678647756576538,
      "learning_rate": 9.325105263157894e-05,
      "loss": 1.2774,
      "step": 23
    },
    {
      "epoch": 0.0039196472317491425,
      "grad_norm": 1.0457429885864258,
      "learning_rate": 9.272421052631578e-05,
      "loss": 0.9798,
      "step": 24
    },
    {
      "epoch": 0.004082965866405357,
      "grad_norm": 1.1700959205627441,
      "learning_rate": 9.219736842105263e-05,
      "loss": 1.2144,
      "step": 25
    },
    {
      "epoch": 0.004246284501061571,
      "grad_norm": 1.3236618041992188,
      "learning_rate": 9.167052631578946e-05,
      "loss": 1.1766,
      "step": 26
    },
    {
      "epoch": 0.004409603135717786,
      "grad_norm": 1.2073756456375122,
      "learning_rate": 9.114368421052632e-05,
      "loss": 0.8459,
      "step": 27
    },
    {
      "epoch": 0.004572921770374,
      "grad_norm": 1.3933292627334595,
      "learning_rate": 9.061684210526315e-05,
      "loss": 1.0467,
      "step": 28
    },
    {
      "epoch": 0.004736240405030214,
      "grad_norm": 1.4482253789901733,
      "learning_rate": 9.009e-05,
      "loss": 1.1401,
      "step": 29
    },
    {
      "epoch": 0.004899559039686428,
      "grad_norm": 1.365537405014038,
      "learning_rate": 8.956315789473683e-05,
      "loss": 0.9932,
      "step": 30
    },
    {
      "epoch": 0.005062877674342643,
      "grad_norm": 1.475220799446106,
      "learning_rate": 8.903631578947368e-05,
      "loss": 1.2499,
      "step": 31
    },
    {
      "epoch": 0.005226196308998857,
      "grad_norm": 1.531992793083191,
      "learning_rate": 8.850947368421052e-05,
      "loss": 1.0115,
      "step": 32
    },
    {
      "epoch": 0.005389514943655071,
      "grad_norm": 2.305574655532837,
      "learning_rate": 8.798263157894736e-05,
      "loss": 0.9368,
      "step": 33
    },
    {
      "epoch": 0.005552833578311285,
      "grad_norm": 1.7354161739349365,
      "learning_rate": 8.745578947368422e-05,
      "loss": 1.049,
      "step": 34
    },
    {
      "epoch": 0.0057161522129675,
      "grad_norm": 2.7026562690734863,
      "learning_rate": 8.692894736842105e-05,
      "loss": 1.3359,
      "step": 35
    },
    {
      "epoch": 0.005879470847623714,
      "grad_norm": 2.1211535930633545,
      "learning_rate": 8.64021052631579e-05,
      "loss": 1.2523,
      "step": 36
    },
    {
      "epoch": 0.0060427894822799285,
      "grad_norm": 2.5288071632385254,
      "learning_rate": 8.587526315789473e-05,
      "loss": 1.43,
      "step": 37
    },
    {
      "epoch": 0.006206108116936142,
      "grad_norm": 2.433478832244873,
      "learning_rate": 8.534842105263157e-05,
      "loss": 1.214,
      "step": 38
    },
    {
      "epoch": 0.006369426751592357,
      "grad_norm": 2.750303268432617,
      "learning_rate": 8.482157894736842e-05,
      "loss": 1.0099,
      "step": 39
    },
    {
      "epoch": 0.006532745386248571,
      "grad_norm": 2.981351375579834,
      "learning_rate": 8.429473684210525e-05,
      "loss": 1.6271,
      "step": 40
    },
    {
      "epoch": 0.0066960640209047856,
      "grad_norm": 3.7224624156951904,
      "learning_rate": 8.376789473684211e-05,
      "loss": 1.733,
      "step": 41
    },
    {
      "epoch": 0.006859382655560999,
      "grad_norm": 3.8278751373291016,
      "learning_rate": 8.324105263157894e-05,
      "loss": 1.5315,
      "step": 42
    },
    {
      "epoch": 0.007022701290217214,
      "grad_norm": 2.7715137004852295,
      "learning_rate": 8.271421052631579e-05,
      "loss": 1.103,
      "step": 43
    },
    {
      "epoch": 0.007186019924873428,
      "grad_norm": 4.1672892570495605,
      "learning_rate": 8.218736842105262e-05,
      "loss": 1.6296,
      "step": 44
    },
    {
      "epoch": 0.007349338559529643,
      "grad_norm": 4.840080261230469,
      "learning_rate": 8.166052631578947e-05,
      "loss": 1.3456,
      "step": 45
    },
    {
      "epoch": 0.0075126571941858565,
      "grad_norm": 4.377506256103516,
      "learning_rate": 8.113368421052631e-05,
      "loss": 1.6744,
      "step": 46
    },
    {
      "epoch": 0.007675975828842071,
      "grad_norm": 4.180212497711182,
      "learning_rate": 8.060684210526315e-05,
      "loss": 1.4903,
      "step": 47
    },
    {
      "epoch": 0.007839294463498285,
      "grad_norm": 4.473518371582031,
      "learning_rate": 8.008e-05,
      "loss": 2.0731,
      "step": 48
    },
    {
      "epoch": 0.008002613098154499,
      "grad_norm": 7.101559162139893,
      "learning_rate": 7.955315789473684e-05,
      "loss": 2.0784,
      "step": 49
    },
    {
      "epoch": 0.008165931732810714,
      "grad_norm": 12.615863800048828,
      "learning_rate": 7.902631578947368e-05,
      "loss": 3.4556,
      "step": 50
    },
    {
      "epoch": 0.008165931732810714,
      "eval_loss": 1.2871240377426147,
      "eval_runtime": 345.3086,
      "eval_samples_per_second": 7.466,
      "eval_steps_per_second": 1.868,
      "step": 50
    },
    {
      "epoch": 0.008329250367466928,
      "grad_norm": 1.8585017919540405,
      "learning_rate": 7.849947368421052e-05,
      "loss": 0.9102,
      "step": 51
    },
    {
      "epoch": 0.008492569002123142,
      "grad_norm": 1.3500086069107056,
      "learning_rate": 7.797263157894736e-05,
      "loss": 1.079,
      "step": 52
    },
    {
      "epoch": 0.008655887636779356,
      "grad_norm": 0.9420222043991089,
      "learning_rate": 7.744578947368421e-05,
      "loss": 0.9128,
      "step": 53
    },
    {
      "epoch": 0.008819206271435572,
      "grad_norm": 0.7498682141304016,
      "learning_rate": 7.691894736842104e-05,
      "loss": 0.9181,
      "step": 54
    },
    {
      "epoch": 0.008982524906091785,
      "grad_norm": 0.6257831454277039,
      "learning_rate": 7.63921052631579e-05,
      "loss": 0.8515,
      "step": 55
    },
    {
      "epoch": 0.009145843540748,
      "grad_norm": 0.6922722458839417,
      "learning_rate": 7.586526315789473e-05,
      "loss": 1.0347,
      "step": 56
    },
    {
      "epoch": 0.009309162175404213,
      "grad_norm": 0.6588111519813538,
      "learning_rate": 7.533842105263158e-05,
      "loss": 0.9266,
      "step": 57
    },
    {
      "epoch": 0.009472480810060429,
      "grad_norm": 0.6781211495399475,
      "learning_rate": 7.481157894736841e-05,
      "loss": 0.8475,
      "step": 58
    },
    {
      "epoch": 0.009635799444716642,
      "grad_norm": 0.7402060627937317,
      "learning_rate": 7.428473684210526e-05,
      "loss": 0.9287,
      "step": 59
    },
    {
      "epoch": 0.009799118079372856,
      "grad_norm": 0.7259023189544678,
      "learning_rate": 7.375789473684209e-05,
      "loss": 0.9206,
      "step": 60
    },
    {
      "epoch": 0.00996243671402907,
      "grad_norm": 0.7616604566574097,
      "learning_rate": 7.323105263157895e-05,
      "loss": 1.0049,
      "step": 61
    },
    {
      "epoch": 0.010125755348685286,
      "grad_norm": 0.7781885862350464,
      "learning_rate": 7.270421052631578e-05,
      "loss": 0.9962,
      "step": 62
    },
    {
      "epoch": 0.0102890739833415,
      "grad_norm": 0.7381305694580078,
      "learning_rate": 7.217736842105263e-05,
      "loss": 0.9049,
      "step": 63
    },
    {
      "epoch": 0.010452392617997713,
      "grad_norm": 0.6955409646034241,
      "learning_rate": 7.165052631578947e-05,
      "loss": 0.8963,
      "step": 64
    },
    {
      "epoch": 0.010615711252653927,
      "grad_norm": 0.8050999045372009,
      "learning_rate": 7.11236842105263e-05,
      "loss": 1.0838,
      "step": 65
    },
    {
      "epoch": 0.010779029887310143,
      "grad_norm": 0.7544150352478027,
      "learning_rate": 7.059684210526315e-05,
      "loss": 0.9493,
      "step": 66
    },
    {
      "epoch": 0.010942348521966357,
      "grad_norm": 0.8155741095542908,
      "learning_rate": 7.006999999999998e-05,
      "loss": 1.1459,
      "step": 67
    },
    {
      "epoch": 0.01110566715662257,
      "grad_norm": 0.7876653671264648,
      "learning_rate": 6.954315789473684e-05,
      "loss": 1.1572,
      "step": 68
    },
    {
      "epoch": 0.011268985791278784,
      "grad_norm": 0.7840471267700195,
      "learning_rate": 6.901631578947368e-05,
      "loss": 0.9516,
      "step": 69
    },
    {
      "epoch": 0.011432304425935,
      "grad_norm": 0.8437424302101135,
      "learning_rate": 6.848947368421052e-05,
      "loss": 1.0117,
      "step": 70
    },
    {
      "epoch": 0.011595623060591214,
      "grad_norm": 1.0028568506240845,
      "learning_rate": 6.796263157894737e-05,
      "loss": 1.0057,
      "step": 71
    },
    {
      "epoch": 0.011758941695247428,
      "grad_norm": 0.9504867792129517,
      "learning_rate": 6.74357894736842e-05,
      "loss": 0.7451,
      "step": 72
    },
    {
      "epoch": 0.011922260329903641,
      "grad_norm": 0.9289828538894653,
      "learning_rate": 6.690894736842105e-05,
      "loss": 0.9866,
      "step": 73
    },
    {
      "epoch": 0.012085578964559857,
      "grad_norm": 0.9018694758415222,
      "learning_rate": 6.638210526315788e-05,
      "loss": 0.9381,
      "step": 74
    },
    {
      "epoch": 0.01224889759921607,
      "grad_norm": 1.0793242454528809,
      "learning_rate": 6.585526315789474e-05,
      "loss": 0.8213,
      "step": 75
    },
    {
      "epoch": 0.012412216233872285,
      "grad_norm": 1.2196921110153198,
      "learning_rate": 6.532842105263157e-05,
      "loss": 1.2063,
      "step": 76
    },
    {
      "epoch": 0.012575534868528498,
      "grad_norm": 1.1026328802108765,
      "learning_rate": 6.480157894736842e-05,
      "loss": 0.9335,
      "step": 77
    },
    {
      "epoch": 0.012738853503184714,
      "grad_norm": 1.1513912677764893,
      "learning_rate": 6.427473684210526e-05,
      "loss": 0.8602,
      "step": 78
    },
    {
      "epoch": 0.012902172137840928,
      "grad_norm": 1.6112369298934937,
      "learning_rate": 6.37478947368421e-05,
      "loss": 0.9575,
      "step": 79
    },
    {
      "epoch": 0.013065490772497142,
      "grad_norm": 1.4818161725997925,
      "learning_rate": 6.322105263157894e-05,
      "loss": 1.0907,
      "step": 80
    },
    {
      "epoch": 0.013228809407153356,
      "grad_norm": 1.3476381301879883,
      "learning_rate": 6.269421052631577e-05,
      "loss": 1.1235,
      "step": 81
    },
    {
      "epoch": 0.013392128041809571,
      "grad_norm": 2.3844518661499023,
      "learning_rate": 6.216736842105263e-05,
      "loss": 1.5409,
      "step": 82
    },
    {
      "epoch": 0.013555446676465785,
      "grad_norm": 3.1227309703826904,
      "learning_rate": 6.164052631578947e-05,
      "loss": 1.0545,
      "step": 83
    },
    {
      "epoch": 0.013718765311121999,
      "grad_norm": 1.8032991886138916,
      "learning_rate": 6.111368421052631e-05,
      "loss": 1.458,
      "step": 84
    },
    {
      "epoch": 0.013882083945778213,
      "grad_norm": 3.0967934131622314,
      "learning_rate": 6.058684210526315e-05,
      "loss": 1.4376,
      "step": 85
    },
    {
      "epoch": 0.014045402580434428,
      "grad_norm": 1.9893653392791748,
      "learning_rate": 6.005999999999999e-05,
      "loss": 1.2981,
      "step": 86
    },
    {
      "epoch": 0.014208721215090642,
      "grad_norm": 1.9208163022994995,
      "learning_rate": 5.953315789473684e-05,
      "loss": 0.9923,
      "step": 87
    },
    {
      "epoch": 0.014372039849746856,
      "grad_norm": 2.3992538452148438,
      "learning_rate": 5.9006315789473676e-05,
      "loss": 1.1079,
      "step": 88
    },
    {
      "epoch": 0.01453535848440307,
      "grad_norm": 2.272313117980957,
      "learning_rate": 5.847947368421053e-05,
      "loss": 1.1979,
      "step": 89
    },
    {
      "epoch": 0.014698677119059285,
      "grad_norm": 2.8902785778045654,
      "learning_rate": 5.795263157894737e-05,
      "loss": 1.3671,
      "step": 90
    },
    {
      "epoch": 0.014861995753715499,
      "grad_norm": 2.847869634628296,
      "learning_rate": 5.742578947368421e-05,
      "loss": 0.7691,
      "step": 91
    },
    {
      "epoch": 0.015025314388371713,
      "grad_norm": 2.585005044937134,
      "learning_rate": 5.6898947368421046e-05,
      "loss": 1.2341,
      "step": 92
    },
    {
      "epoch": 0.015188633023027927,
      "grad_norm": 3.3812036514282227,
      "learning_rate": 5.6372105263157886e-05,
      "loss": 1.3677,
      "step": 93
    },
    {
      "epoch": 0.015351951657684142,
      "grad_norm": 4.347215175628662,
      "learning_rate": 5.584526315789473e-05,
      "loss": 1.5338,
      "step": 94
    },
    {
      "epoch": 0.015515270292340356,
      "grad_norm": 2.856776237487793,
      "learning_rate": 5.531842105263158e-05,
      "loss": 1.4113,
      "step": 95
    },
    {
      "epoch": 0.01567858892699657,
      "grad_norm": 3.887981414794922,
      "learning_rate": 5.4791578947368424e-05,
      "loss": 1.4782,
      "step": 96
    },
    {
      "epoch": 0.015841907561652786,
      "grad_norm": 3.390988826751709,
      "learning_rate": 5.426473684210526e-05,
      "loss": 2.0514,
      "step": 97
    },
    {
      "epoch": 0.016005226196308998,
      "grad_norm": 90.9446792602539,
      "learning_rate": 5.37378947368421e-05,
      "loss": 1.5698,
      "step": 98
    },
    {
      "epoch": 0.016168544830965213,
      "grad_norm": 4.8651556968688965,
      "learning_rate": 5.321105263157894e-05,
      "loss": 1.732,
      "step": 99
    },
    {
      "epoch": 0.01633186346562143,
      "grad_norm": 8.150487899780273,
      "learning_rate": 5.268421052631578e-05,
      "loss": 2.5082,
      "step": 100
    },
    {
      "epoch": 0.01633186346562143,
      "eval_loss": 1.1979554891586304,
      "eval_runtime": 345.8196,
      "eval_samples_per_second": 7.455,
      "eval_steps_per_second": 1.865,
      "step": 100
    },
    {
      "epoch": 0.01649518210027764,
      "grad_norm": 0.7058354020118713,
      "learning_rate": 5.2157368421052626e-05,
      "loss": 0.7955,
      "step": 101
    },
    {
      "epoch": 0.016658500734933857,
      "grad_norm": 0.7873735427856445,
      "learning_rate": 5.163052631578947e-05,
      "loss": 0.9298,
      "step": 102
    },
    {
      "epoch": 0.01682181936959007,
      "grad_norm": 0.6918278336524963,
      "learning_rate": 5.110368421052632e-05,
      "loss": 0.941,
      "step": 103
    },
    {
      "epoch": 0.016985138004246284,
      "grad_norm": 0.6960136294364929,
      "learning_rate": 5.057684210526316e-05,
      "loss": 0.8583,
      "step": 104
    },
    {
      "epoch": 0.0171484566389025,
      "grad_norm": 0.6780745983123779,
      "learning_rate": 5.005e-05,
      "loss": 0.8733,
      "step": 105
    },
    {
      "epoch": 0.017311775273558712,
      "grad_norm": 0.6429307460784912,
      "learning_rate": 4.9523157894736836e-05,
      "loss": 0.9417,
      "step": 106
    },
    {
      "epoch": 0.017475093908214927,
      "grad_norm": 0.6558470726013184,
      "learning_rate": 4.899631578947368e-05,
      "loss": 0.8916,
      "step": 107
    },
    {
      "epoch": 0.017638412542871143,
      "grad_norm": 0.6242132186889648,
      "learning_rate": 4.846947368421052e-05,
      "loss": 1.0048,
      "step": 108
    },
    {
      "epoch": 0.017801731177527355,
      "grad_norm": 0.5471253991127014,
      "learning_rate": 4.794263157894737e-05,
      "loss": 0.8926,
      "step": 109
    },
    {
      "epoch": 0.01796504981218357,
      "grad_norm": 0.5996319055557251,
      "learning_rate": 4.7415789473684206e-05,
      "loss": 1.032,
      "step": 110
    },
    {
      "epoch": 0.018128368446839783,
      "grad_norm": 0.6278873682022095,
      "learning_rate": 4.688894736842105e-05,
      "loss": 1.0255,
      "step": 111
    },
    {
      "epoch": 0.018291687081496,
      "grad_norm": 0.622478723526001,
      "learning_rate": 4.636210526315789e-05,
      "loss": 0.9705,
      "step": 112
    },
    {
      "epoch": 0.018455005716152214,
      "grad_norm": 0.6352484226226807,
      "learning_rate": 4.583526315789473e-05,
      "loss": 0.7911,
      "step": 113
    },
    {
      "epoch": 0.018618324350808426,
      "grad_norm": 0.681956946849823,
      "learning_rate": 4.530842105263158e-05,
      "loss": 1.0143,
      "step": 114
    },
    {
      "epoch": 0.01878164298546464,
      "grad_norm": 0.7090697288513184,
      "learning_rate": 4.4781578947368416e-05,
      "loss": 0.9628,
      "step": 115
    },
    {
      "epoch": 0.018944961620120857,
      "grad_norm": 0.7363274097442627,
      "learning_rate": 4.425473684210526e-05,
      "loss": 1.0271,
      "step": 116
    },
    {
      "epoch": 0.01910828025477707,
      "grad_norm": 0.7926649451255798,
      "learning_rate": 4.372789473684211e-05,
      "loss": 1.124,
      "step": 117
    },
    {
      "epoch": 0.019271598889433285,
      "grad_norm": 0.7625167369842529,
      "learning_rate": 4.320105263157895e-05,
      "loss": 1.1374,
      "step": 118
    },
    {
      "epoch": 0.019434917524089497,
      "grad_norm": 0.8049649000167847,
      "learning_rate": 4.2674210526315786e-05,
      "loss": 0.9706,
      "step": 119
    },
    {
      "epoch": 0.019598236158745713,
      "grad_norm": 0.7378389239311218,
      "learning_rate": 4.2147368421052626e-05,
      "loss": 0.8136,
      "step": 120
    },
    {
      "epoch": 0.019761554793401928,
      "grad_norm": 0.8343645930290222,
      "learning_rate": 4.162052631578947e-05,
      "loss": 0.9652,
      "step": 121
    },
    {
      "epoch": 0.01992487342805814,
      "grad_norm": 1.196692705154419,
      "learning_rate": 4.109368421052631e-05,
      "loss": 0.9455,
      "step": 122
    },
    {
      "epoch": 0.020088192062714356,
      "grad_norm": 0.9792311787605286,
      "learning_rate": 4.056684210526316e-05,
      "loss": 1.0111,
      "step": 123
    },
    {
      "epoch": 0.02025151069737057,
      "grad_norm": 0.9197056889533997,
      "learning_rate": 4.004e-05,
      "loss": 0.975,
      "step": 124
    },
    {
      "epoch": 0.020414829332026783,
      "grad_norm": 1.0094839334487915,
      "learning_rate": 3.951315789473684e-05,
      "loss": 1.1968,
      "step": 125
    },
    {
      "epoch": 0.020578147966683,
      "grad_norm": 1.0122300386428833,
      "learning_rate": 3.898631578947368e-05,
      "loss": 0.9602,
      "step": 126
    },
    {
      "epoch": 0.02074146660133921,
      "grad_norm": 1.0537972450256348,
      "learning_rate": 3.845947368421052e-05,
      "loss": 0.9842,
      "step": 127
    },
    {
      "epoch": 0.020904785235995427,
      "grad_norm": 1.1098566055297852,
      "learning_rate": 3.7932631578947367e-05,
      "loss": 0.6929,
      "step": 128
    },
    {
      "epoch": 0.021068103870651642,
      "grad_norm": 1.246183156967163,
      "learning_rate": 3.7405789473684206e-05,
      "loss": 1.0037,
      "step": 129
    },
    {
      "epoch": 0.021231422505307854,
      "grad_norm": 1.2114588022232056,
      "learning_rate": 3.6878947368421045e-05,
      "loss": 0.9154,
      "step": 130
    },
    {
      "epoch": 0.02139474113996407,
      "grad_norm": 1.2241871356964111,
      "learning_rate": 3.635210526315789e-05,
      "loss": 1.0221,
      "step": 131
    },
    {
      "epoch": 0.021558059774620286,
      "grad_norm": 1.3580658435821533,
      "learning_rate": 3.582526315789474e-05,
      "loss": 1.0275,
      "step": 132
    },
    {
      "epoch": 0.021721378409276498,
      "grad_norm": 1.6600242853164673,
      "learning_rate": 3.5298421052631576e-05,
      "loss": 1.1471,
      "step": 133
    },
    {
      "epoch": 0.021884697043932713,
      "grad_norm": 1.9517477750778198,
      "learning_rate": 3.477157894736842e-05,
      "loss": 1.21,
      "step": 134
    },
    {
      "epoch": 0.022048015678588925,
      "grad_norm": 2.107109308242798,
      "learning_rate": 3.424473684210526e-05,
      "loss": 1.4034,
      "step": 135
    },
    {
      "epoch": 0.02221133431324514,
      "grad_norm": 3.42795991897583,
      "learning_rate": 3.37178947368421e-05,
      "loss": 1.2696,
      "step": 136
    },
    {
      "epoch": 0.022374652947901356,
      "grad_norm": 2.0616705417633057,
      "learning_rate": 3.319105263157894e-05,
      "loss": 1.1452,
      "step": 137
    },
    {
      "epoch": 0.02253797158255757,
      "grad_norm": 2.5637259483337402,
      "learning_rate": 3.2664210526315786e-05,
      "loss": 1.1689,
      "step": 138
    },
    {
      "epoch": 0.022701290217213784,
      "grad_norm": 3.1429243087768555,
      "learning_rate": 3.213736842105263e-05,
      "loss": 1.4649,
      "step": 139
    },
    {
      "epoch": 0.02286460885187,
      "grad_norm": 3.0663323402404785,
      "learning_rate": 3.161052631578947e-05,
      "loss": 1.4323,
      "step": 140
    },
    {
      "epoch": 0.023027927486526212,
      "grad_norm": 3.1458401679992676,
      "learning_rate": 3.108368421052632e-05,
      "loss": 0.9673,
      "step": 141
    },
    {
      "epoch": 0.023191246121182427,
      "grad_norm": 3.3782215118408203,
      "learning_rate": 3.0556842105263156e-05,
      "loss": 1.3108,
      "step": 142
    },
    {
      "epoch": 0.02335456475583864,
      "grad_norm": 3.1077187061309814,
      "learning_rate": 3.0029999999999995e-05,
      "loss": 1.6808,
      "step": 143
    },
    {
      "epoch": 0.023517883390494855,
      "grad_norm": 3.3202567100524902,
      "learning_rate": 2.9503157894736838e-05,
      "loss": 1.6597,
      "step": 144
    },
    {
      "epoch": 0.02368120202515107,
      "grad_norm": 2.8775930404663086,
      "learning_rate": 2.8976315789473684e-05,
      "loss": 0.9313,
      "step": 145
    },
    {
      "epoch": 0.023844520659807283,
      "grad_norm": 3.3522984981536865,
      "learning_rate": 2.8449473684210523e-05,
      "loss": 1.8898,
      "step": 146
    },
    {
      "epoch": 0.0240078392944635,
      "grad_norm": 4.523774147033691,
      "learning_rate": 2.7922631578947366e-05,
      "loss": 1.1704,
      "step": 147
    },
    {
      "epoch": 0.024171157929119714,
      "grad_norm": 5.291178226470947,
      "learning_rate": 2.7395789473684212e-05,
      "loss": 2.2631,
      "step": 148
    },
    {
      "epoch": 0.024334476563775926,
      "grad_norm": 5.7989959716796875,
      "learning_rate": 2.686894736842105e-05,
      "loss": 2.0457,
      "step": 149
    },
    {
      "epoch": 0.02449779519843214,
      "grad_norm": 10.409539222717285,
      "learning_rate": 2.634210526315789e-05,
      "loss": 1.8767,
      "step": 150
    },
    {
      "epoch": 0.02449779519843214,
      "eval_loss": 1.1476330757141113,
      "eval_runtime": 345.8578,
      "eval_samples_per_second": 7.454,
      "eval_steps_per_second": 1.865,
      "step": 150
    },
    {
      "epoch": 0.024661113833088357,
      "grad_norm": 0.5229954719543457,
      "learning_rate": 2.5815263157894736e-05,
      "loss": 0.9078,
      "step": 151
    },
    {
      "epoch": 0.02482443246774457,
      "grad_norm": 0.4165619909763336,
      "learning_rate": 2.528842105263158e-05,
      "loss": 0.7202,
      "step": 152
    },
    {
      "epoch": 0.024987751102400785,
      "grad_norm": 0.4411524832248688,
      "learning_rate": 2.4761578947368418e-05,
      "loss": 0.7657,
      "step": 153
    },
    {
      "epoch": 0.025151069737056997,
      "grad_norm": 0.5870716571807861,
      "learning_rate": 2.423473684210526e-05,
      "loss": 0.9064,
      "step": 154
    },
    {
      "epoch": 0.025314388371713212,
      "grad_norm": 0.5716325044631958,
      "learning_rate": 2.3707894736842103e-05,
      "loss": 0.7211,
      "step": 155
    },
    {
      "epoch": 0.025477707006369428,
      "grad_norm": 0.5912550091743469,
      "learning_rate": 2.3181052631578946e-05,
      "loss": 0.9137,
      "step": 156
    },
    {
      "epoch": 0.02564102564102564,
      "grad_norm": 0.49093204736709595,
      "learning_rate": 2.265421052631579e-05,
      "loss": 0.9175,
      "step": 157
    },
    {
      "epoch": 0.025804344275681856,
      "grad_norm": 0.5379444360733032,
      "learning_rate": 2.212736842105263e-05,
      "loss": 1.0109,
      "step": 158
    },
    {
      "epoch": 0.02596766291033807,
      "grad_norm": 0.5582550764083862,
      "learning_rate": 2.1600526315789474e-05,
      "loss": 0.9187,
      "step": 159
    },
    {
      "epoch": 0.026130981544994283,
      "grad_norm": 0.5776020288467407,
      "learning_rate": 2.1073684210526313e-05,
      "loss": 0.8756,
      "step": 160
    },
    {
      "epoch": 0.0262943001796505,
      "grad_norm": 0.6320648789405823,
      "learning_rate": 2.0546842105263155e-05,
      "loss": 1.002,
      "step": 161
    },
    {
      "epoch": 0.02645761881430671,
      "grad_norm": 0.5884015560150146,
      "learning_rate": 2.002e-05,
      "loss": 0.82,
      "step": 162
    },
    {
      "epoch": 0.026620937448962927,
      "grad_norm": 0.6072445511817932,
      "learning_rate": 1.949315789473684e-05,
      "loss": 0.9141,
      "step": 163
    },
    {
      "epoch": 0.026784256083619142,
      "grad_norm": 0.578770637512207,
      "learning_rate": 1.8966315789473683e-05,
      "loss": 0.8936,
      "step": 164
    },
    {
      "epoch": 0.026947574718275354,
      "grad_norm": 0.7762899994850159,
      "learning_rate": 1.8439473684210522e-05,
      "loss": 0.67,
      "step": 165
    },
    {
      "epoch": 0.02711089335293157,
      "grad_norm": 0.7052147388458252,
      "learning_rate": 1.791263157894737e-05,
      "loss": 0.7984,
      "step": 166
    },
    {
      "epoch": 0.027274211987587785,
      "grad_norm": 0.6481052041053772,
      "learning_rate": 1.738578947368421e-05,
      "loss": 0.9779,
      "step": 167
    },
    {
      "epoch": 0.027437530622243998,
      "grad_norm": 0.6853712201118469,
      "learning_rate": 1.685894736842105e-05,
      "loss": 0.8923,
      "step": 168
    },
    {
      "epoch": 0.027600849256900213,
      "grad_norm": 0.7015615105628967,
      "learning_rate": 1.6332105263157893e-05,
      "loss": 0.8661,
      "step": 169
    },
    {
      "epoch": 0.027764167891556425,
      "grad_norm": 0.8164605498313904,
      "learning_rate": 1.5805263157894735e-05,
      "loss": 0.8789,
      "step": 170
    },
    {
      "epoch": 0.02792748652621264,
      "grad_norm": 0.8073320984840393,
      "learning_rate": 1.5278421052631578e-05,
      "loss": 1.0431,
      "step": 171
    },
    {
      "epoch": 0.028090805160868856,
      "grad_norm": 0.9141411185264587,
      "learning_rate": 1.4751578947368419e-05,
      "loss": 1.069,
      "step": 172
    },
    {
      "epoch": 0.02825412379552507,
      "grad_norm": 1.0805171728134155,
      "learning_rate": 1.4224736842105262e-05,
      "loss": 1.0579,
      "step": 173
    },
    {
      "epoch": 0.028417442430181284,
      "grad_norm": 0.8766102194786072,
      "learning_rate": 1.3697894736842106e-05,
      "loss": 0.7755,
      "step": 174
    },
    {
      "epoch": 0.0285807610648375,
      "grad_norm": 0.9655460715293884,
      "learning_rate": 1.3171052631578945e-05,
      "loss": 0.967,
      "step": 175
    },
    {
      "epoch": 0.02874407969949371,
      "grad_norm": 0.9592732787132263,
      "learning_rate": 1.264421052631579e-05,
      "loss": 0.9174,
      "step": 176
    },
    {
      "epoch": 0.028907398334149927,
      "grad_norm": 1.3226499557495117,
      "learning_rate": 1.211736842105263e-05,
      "loss": 1.2512,
      "step": 177
    },
    {
      "epoch": 0.02907071696880614,
      "grad_norm": 1.1680970191955566,
      "learning_rate": 1.1590526315789473e-05,
      "loss": 0.948,
      "step": 178
    },
    {
      "epoch": 0.029234035603462355,
      "grad_norm": 1.0348116159439087,
      "learning_rate": 1.1063684210526316e-05,
      "loss": 0.8562,
      "step": 179
    },
    {
      "epoch": 0.02939735423811857,
      "grad_norm": 1.6529384851455688,
      "learning_rate": 1.0536842105263156e-05,
      "loss": 1.1671,
      "step": 180
    },
    {
      "epoch": 0.029560672872774783,
      "grad_norm": 1.5153594017028809,
      "learning_rate": 1.001e-05,
      "loss": 1.0921,
      "step": 181
    },
    {
      "epoch": 0.029723991507430998,
      "grad_norm": 1.3825584650039673,
      "learning_rate": 9.483157894736842e-06,
      "loss": 1.1131,
      "step": 182
    },
    {
      "epoch": 0.029887310142087214,
      "grad_norm": 2.2654531002044678,
      "learning_rate": 8.956315789473684e-06,
      "loss": 1.129,
      "step": 183
    },
    {
      "epoch": 0.030050628776743426,
      "grad_norm": 1.8482561111450195,
      "learning_rate": 8.429473684210525e-06,
      "loss": 1.1118,
      "step": 184
    },
    {
      "epoch": 0.03021394741139964,
      "grad_norm": 2.0934503078460693,
      "learning_rate": 7.902631578947368e-06,
      "loss": 1.0566,
      "step": 185
    },
    {
      "epoch": 0.030377266046055854,
      "grad_norm": 2.0610568523406982,
      "learning_rate": 7.3757894736842095e-06,
      "loss": 1.5909,
      "step": 186
    },
    {
      "epoch": 0.03054058468071207,
      "grad_norm": 2.510016918182373,
      "learning_rate": 6.848947368421053e-06,
      "loss": 1.1805,
      "step": 187
    },
    {
      "epoch": 0.030703903315368285,
      "grad_norm": 2.6841964721679688,
      "learning_rate": 6.322105263157895e-06,
      "loss": 1.2795,
      "step": 188
    },
    {
      "epoch": 0.030867221950024497,
      "grad_norm": 2.3344948291778564,
      "learning_rate": 5.7952631578947365e-06,
      "loss": 1.2345,
      "step": 189
    },
    {
      "epoch": 0.031030540584680712,
      "grad_norm": 2.7954304218292236,
      "learning_rate": 5.268421052631578e-06,
      "loss": 1.2223,
      "step": 190
    },
    {
      "epoch": 0.031193859219336928,
      "grad_norm": 2.858825922012329,
      "learning_rate": 4.741578947368421e-06,
      "loss": 1.7338,
      "step": 191
    },
    {
      "epoch": 0.03135717785399314,
      "grad_norm": 3.322049856185913,
      "learning_rate": 4.2147368421052626e-06,
      "loss": 1.4427,
      "step": 192
    },
    {
      "epoch": 0.03152049648864935,
      "grad_norm": 2.922865152359009,
      "learning_rate": 3.6878947368421047e-06,
      "loss": 1.5083,
      "step": 193
    },
    {
      "epoch": 0.03168381512330557,
      "grad_norm": 4.792754173278809,
      "learning_rate": 3.1610526315789474e-06,
      "loss": 1.614,
      "step": 194
    },
    {
      "epoch": 0.03184713375796178,
      "grad_norm": 2.5056612491607666,
      "learning_rate": 2.634210526315789e-06,
      "loss": 1.0081,
      "step": 195
    },
    {
      "epoch": 0.032010452392617995,
      "grad_norm": 3.5326714515686035,
      "learning_rate": 2.1073684210526313e-06,
      "loss": 0.9609,
      "step": 196
    },
    {
      "epoch": 0.032173771027274214,
      "grad_norm": 5.468371868133545,
      "learning_rate": 1.5805263157894737e-06,
      "loss": 2.8999,
      "step": 197
    },
    {
      "epoch": 0.03233708966193043,
      "grad_norm": 5.357850074768066,
      "learning_rate": 1.0536842105263156e-06,
      "loss": 2.4673,
      "step": 198
    },
    {
      "epoch": 0.03250040829658664,
      "grad_norm": 5.674871444702148,
      "learning_rate": 5.268421052631578e-07,
      "loss": 2.0768,
      "step": 199
    },
    {
      "epoch": 0.03266372693124286,
      "grad_norm": 5.8404860496521,
      "learning_rate": 0.0,
      "loss": 1.6252,
      "step": 200
    },
    {
      "epoch": 0.03266372693124286,
      "eval_loss": 1.1349619626998901,
      "eval_runtime": 346.0024,
      "eval_samples_per_second": 7.451,
      "eval_steps_per_second": 1.864,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 8.65769979075625e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}