{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.004265984109209193,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.1329920546045965e-05,
      "grad_norm": NaN,
      "learning_rate": 1.004e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 2.1329920546045965e-05,
      "eval_loss": NaN,
      "eval_runtime": 2182.7599,
      "eval_samples_per_second": 9.044,
      "eval_steps_per_second": 2.261,
      "step": 1
    },
    {
      "epoch": 4.265984109209193e-05,
      "grad_norm": NaN,
      "learning_rate": 2.008e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 6.39897616381379e-05,
      "grad_norm": NaN,
      "learning_rate": 3.012e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 8.531968218418386e-05,
      "grad_norm": NaN,
      "learning_rate": 4.016e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00010664960273022984,
      "grad_norm": NaN,
      "learning_rate": 5.02e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0001279795232762758,
      "grad_norm": NaN,
      "learning_rate": 6.024e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00014930944382232175,
      "grad_norm": NaN,
      "learning_rate": 7.028e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00017063936436836772,
      "grad_norm": NaN,
      "learning_rate": 8.032e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.00019196928491441368,
      "grad_norm": NaN,
      "learning_rate": 9.036000000000001e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00021329920546045967,
      "grad_norm": NaN,
      "learning_rate": 0.0001004,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.00023462912600650564,
      "grad_norm": NaN,
      "learning_rate": 9.987157894736842e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.0002559590465525516,
      "grad_norm": NaN,
      "learning_rate": 9.934315789473684e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.00027728896709859754,
      "grad_norm": NaN,
      "learning_rate": 9.881473684210525e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.0002986188876446435,
      "grad_norm": NaN,
      "learning_rate": 9.828631578947369e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.00031994880819068947,
      "grad_norm": NaN,
      "learning_rate": 9.77578947368421e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.00034127872873673543,
      "grad_norm": NaN,
      "learning_rate": 9.722947368421052e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.0003626086492827814,
      "grad_norm": NaN,
      "learning_rate": 9.670105263157895e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.00038393856982882736,
      "grad_norm": NaN,
      "learning_rate": 9.617263157894737e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0004052684903748733,
      "grad_norm": NaN,
      "learning_rate": 9.564421052631579e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.00042659841092091935,
      "grad_norm": NaN,
      "learning_rate": 9.511578947368421e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0004479283314669653,
      "grad_norm": NaN,
      "learning_rate": 9.458736842105264e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0004692582520130113,
      "grad_norm": NaN,
      "learning_rate": 9.405894736842106e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.0004905881725590572,
      "grad_norm": NaN,
      "learning_rate": 9.353052631578947e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.0005119180931051031,
      "grad_norm": NaN,
      "learning_rate": 9.300210526315789e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0005332480136511492,
      "grad_norm": NaN,
      "learning_rate": 9.247368421052631e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0005545779341971951,
      "grad_norm": NaN,
      "learning_rate": 9.194526315789473e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.0005759078547432411,
      "grad_norm": NaN,
      "learning_rate": 9.141684210526316e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.000597237775289287,
      "grad_norm": NaN,
      "learning_rate": 9.088842105263158e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.000618567695835333,
      "grad_norm": NaN,
      "learning_rate": 9.036000000000001e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.0006398976163813789,
      "grad_norm": NaN,
      "learning_rate": 8.983157894736843e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.000661227536927425,
      "grad_norm": NaN,
      "learning_rate": 8.930315789473684e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.0006825574574734709,
      "grad_norm": NaN,
      "learning_rate": 8.877473684210526e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.0007038873780195169,
      "grad_norm": NaN,
      "learning_rate": 8.824631578947368e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.0007252172985655628,
      "grad_norm": NaN,
      "learning_rate": 8.771789473684211e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.0007465472191116088,
      "grad_norm": NaN,
      "learning_rate": 8.718947368421053e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.0007678771396576547,
      "grad_norm": NaN,
      "learning_rate": 8.666105263157895e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.0007892070602037007,
      "grad_norm": NaN,
      "learning_rate": 8.613263157894737e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.0008105369807497467,
      "grad_norm": NaN,
      "learning_rate": 8.560421052631578e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.0008318669012957927,
      "grad_norm": NaN,
      "learning_rate": 8.50757894736842e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.0008531968218418387,
      "grad_norm": NaN,
      "learning_rate": 8.454736842105263e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.0008745267423878846,
      "grad_norm": NaN,
      "learning_rate": 8.401894736842106e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.0008958566629339306,
      "grad_norm": NaN,
      "learning_rate": 8.349052631578948e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.0009171865834799765,
      "grad_norm": NaN,
      "learning_rate": 8.29621052631579e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.0009385165040260225,
      "grad_norm": NaN,
      "learning_rate": 8.243368421052632e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.0009598464245720685,
      "grad_norm": NaN,
      "learning_rate": 8.190526315789474e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.0009811763451181145,
      "grad_norm": NaN,
      "learning_rate": 8.137684210526315e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.0010025062656641604,
      "grad_norm": NaN,
      "learning_rate": 8.084842105263157e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.0010238361862102063,
      "grad_norm": NaN,
      "learning_rate": 8.032e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.0010451661067562524,
      "grad_norm": NaN,
      "learning_rate": 7.979157894736842e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.0010664960273022983,
      "grad_norm": NaN,
      "learning_rate": 7.926315789473684e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.0010664960273022983,
      "eval_loss": NaN,
      "eval_runtime": 2186.1728,
      "eval_samples_per_second": 9.029,
      "eval_steps_per_second": 2.257,
      "step": 50
    },
    {
      "epoch": 0.0010878259478483442,
      "grad_norm": NaN,
      "learning_rate": 7.873473684210526e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.0011091558683943902,
      "grad_norm": NaN,
      "learning_rate": 7.820631578947369e-05,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.0011304857889404363,
      "grad_norm": NaN,
      "learning_rate": 7.76778947368421e-05,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.0011518157094864822,
      "grad_norm": NaN,
      "learning_rate": 7.714947368421052e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.001173145630032528,
      "grad_norm": NaN,
      "learning_rate": 7.662105263157896e-05,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.001194475550578574,
      "grad_norm": NaN,
      "learning_rate": 7.609263157894737e-05,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.0012158054711246201,
      "grad_norm": NaN,
      "learning_rate": 7.556421052631579e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.001237135391670666,
      "grad_norm": NaN,
      "learning_rate": 7.503578947368421e-05,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.001258465312216712,
      "grad_norm": NaN,
      "learning_rate": 7.450736842105263e-05,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.0012797952327627579,
      "grad_norm": NaN,
      "learning_rate": 7.397894736842105e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.001301125153308804,
      "grad_norm": NaN,
      "learning_rate": 7.345052631578948e-05,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.00132245507385485,
      "grad_norm": NaN,
      "learning_rate": 7.29221052631579e-05,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.0013437849944008958,
      "grad_norm": NaN,
      "learning_rate": 7.239368421052631e-05,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.0013651149149469417,
      "grad_norm": NaN,
      "learning_rate": 7.186526315789474e-05,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.0013864448354929879,
      "grad_norm": NaN,
      "learning_rate": 7.133684210526316e-05,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.0014077747560390338,
      "grad_norm": NaN,
      "learning_rate": 7.080842105263158e-05,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.0014291046765850797,
      "grad_norm": NaN,
      "learning_rate": 7.028e-05,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.0014504345971311256,
      "grad_norm": NaN,
      "learning_rate": 6.975157894736843e-05,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.0014717645176771717,
      "grad_norm": NaN,
      "learning_rate": 6.922315789473685e-05,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.0014930944382232176,
      "grad_norm": NaN,
      "learning_rate": 6.869473684210527e-05,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.0015144243587692635,
      "grad_norm": NaN,
      "learning_rate": 6.816631578947368e-05,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.0015357542793153094,
      "grad_norm": NaN,
      "learning_rate": 6.76378947368421e-05,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.0015570841998613556,
      "grad_norm": NaN,
      "learning_rate": 6.710947368421052e-05,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.0015784141204074015,
      "grad_norm": NaN,
      "learning_rate": 6.658105263157894e-05,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.0015997440409534474,
      "grad_norm": NaN,
      "learning_rate": 6.605263157894737e-05,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.0016210739614994933,
      "grad_norm": NaN,
      "learning_rate": 6.55242105263158e-05,
      "loss": 0.0,
      "step": 76
    },
    {
      "epoch": 0.0016424038820455394,
      "grad_norm": NaN,
      "learning_rate": 6.499578947368422e-05,
      "loss": 0.0,
      "step": 77
    },
    {
      "epoch": 0.0016637338025915853,
      "grad_norm": NaN,
      "learning_rate": 6.446736842105264e-05,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.0016850637231376313,
      "grad_norm": NaN,
      "learning_rate": 6.393894736842105e-05,
      "loss": 0.0,
      "step": 79
    },
    {
      "epoch": 0.0017063936436836774,
      "grad_norm": NaN,
      "learning_rate": 6.341052631578947e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.0017277235642297233,
      "grad_norm": NaN,
      "learning_rate": 6.288210526315789e-05,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.0017490534847757692,
      "grad_norm": NaN,
      "learning_rate": 6.235368421052632e-05,
      "loss": 0.0,
      "step": 82
    },
    {
      "epoch": 0.0017703834053218151,
      "grad_norm": NaN,
      "learning_rate": 6.182526315789474e-05,
      "loss": 0.0,
      "step": 83
    },
    {
      "epoch": 0.0017917133258678612,
      "grad_norm": NaN,
      "learning_rate": 6.129684210526316e-05,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.0018130432464139072,
      "grad_norm": NaN,
      "learning_rate": 6.076842105263158e-05,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.001834373166959953,
      "grad_norm": NaN,
      "learning_rate": 6.024e-05,
      "loss": 0.0,
      "step": 86
    },
    {
      "epoch": 0.001855703087505999,
      "grad_norm": NaN,
      "learning_rate": 5.971157894736842e-05,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 0.001877033008052045,
      "grad_norm": NaN,
      "learning_rate": 5.9183157894736835e-05,
      "loss": 0.0,
      "step": 88
    },
    {
      "epoch": 0.001898362928598091,
      "grad_norm": NaN,
      "learning_rate": 5.8654736842105267e-05,
      "loss": 0.0,
      "step": 89
    },
    {
      "epoch": 0.001919692849144137,
      "grad_norm": NaN,
      "learning_rate": 5.8126315789473684e-05,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.0019410227696901828,
      "grad_norm": NaN,
      "learning_rate": 5.759789473684211e-05,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 0.001962352690236229,
      "grad_norm": NaN,
      "learning_rate": 5.706947368421053e-05,
      "loss": 0.0,
      "step": 92
    },
    {
      "epoch": 0.0019836826107822747,
      "grad_norm": NaN,
      "learning_rate": 5.6541052631578945e-05,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 0.0020050125313283208,
      "grad_norm": NaN,
      "learning_rate": 5.601263157894736e-05,
      "loss": 0.0,
      "step": 94
    },
    {
      "epoch": 0.002026342451874367,
      "grad_norm": NaN,
      "learning_rate": 5.5484210526315794e-05,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 0.0020476723724204126,
      "grad_norm": NaN,
      "learning_rate": 5.495578947368421e-05,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.0020690022929664587,
      "grad_norm": NaN,
      "learning_rate": 5.442736842105264e-05,
      "loss": 0.0,
      "step": 97
    },
    {
      "epoch": 0.002090332213512505,
      "grad_norm": NaN,
      "learning_rate": 5.3898947368421055e-05,
      "loss": 0.0,
      "step": 98
    },
    {
      "epoch": 0.0021116621340585505,
      "grad_norm": NaN,
      "learning_rate": 5.337052631578947e-05,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 0.0021329920546045967,
      "grad_norm": NaN,
      "learning_rate": 5.284210526315789e-05,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.0021329920546045967,
      "eval_loss": NaN,
      "eval_runtime": 2185.4878,
      "eval_samples_per_second": 9.032,
      "eval_steps_per_second": 2.258,
      "step": 100
    },
    {
      "epoch": 0.0021543219751506424,
      "grad_norm": NaN,
      "learning_rate": 5.231368421052631e-05,
      "loss": 0.0,
      "step": 101
    },
    {
      "epoch": 0.0021756518956966885,
      "grad_norm": NaN,
      "learning_rate": 5.178526315789474e-05,
      "loss": 0.0,
      "step": 102
    },
    {
      "epoch": 0.0021969818162427346,
      "grad_norm": NaN,
      "learning_rate": 5.1256842105263165e-05,
      "loss": 0.0,
      "step": 103
    },
    {
      "epoch": 0.0022183117367887803,
      "grad_norm": NaN,
      "learning_rate": 5.072842105263158e-05,
      "loss": 0.0,
      "step": 104
    },
    {
      "epoch": 0.0022396416573348264,
      "grad_norm": NaN,
      "learning_rate": 5.02e-05,
      "loss": 0.0,
      "step": 105
    },
    {
      "epoch": 0.0022609715778808726,
      "grad_norm": NaN,
      "learning_rate": 4.967157894736842e-05,
      "loss": 0.0,
      "step": 106
    },
    {
      "epoch": 0.0022823014984269183,
      "grad_norm": NaN,
      "learning_rate": 4.914315789473684e-05,
      "loss": 0.0,
      "step": 107
    },
    {
      "epoch": 0.0023036314189729644,
      "grad_norm": NaN,
      "learning_rate": 4.861473684210526e-05,
      "loss": 0.0,
      "step": 108
    },
    {
      "epoch": 0.00232496133951901,
      "grad_norm": NaN,
      "learning_rate": 4.8086315789473686e-05,
      "loss": 0.0,
      "step": 109
    },
    {
      "epoch": 0.002346291260065056,
      "grad_norm": NaN,
      "learning_rate": 4.7557894736842104e-05,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.0023676211806111023,
      "grad_norm": NaN,
      "learning_rate": 4.702947368421053e-05,
      "loss": 0.0,
      "step": 111
    },
    {
      "epoch": 0.002388951101157148,
      "grad_norm": NaN,
      "learning_rate": 4.6501052631578946e-05,
      "loss": 0.0,
      "step": 112
    },
    {
      "epoch": 0.002410281021703194,
      "grad_norm": NaN,
      "learning_rate": 4.5972631578947364e-05,
      "loss": 0.0,
      "step": 113
    },
    {
      "epoch": 0.0024316109422492403,
      "grad_norm": NaN,
      "learning_rate": 4.544421052631579e-05,
      "loss": 0.0,
      "step": 114
    },
    {
      "epoch": 0.002452940862795286,
      "grad_norm": NaN,
      "learning_rate": 4.4915789473684213e-05,
      "loss": 0.0,
      "step": 115
    },
    {
      "epoch": 0.002474270783341332,
      "grad_norm": NaN,
      "learning_rate": 4.438736842105263e-05,
      "loss": 0.0,
      "step": 116
    },
    {
      "epoch": 0.0024956007038873782,
      "grad_norm": NaN,
      "learning_rate": 4.3858947368421056e-05,
      "loss": 0.0,
      "step": 117
    },
    {
      "epoch": 0.002516930624433424,
      "grad_norm": NaN,
      "learning_rate": 4.3330526315789474e-05,
      "loss": 0.0,
      "step": 118
    },
    {
      "epoch": 0.00253826054497947,
      "grad_norm": NaN,
      "learning_rate": 4.280210526315789e-05,
      "loss": 0.0,
      "step": 119
    },
    {
      "epoch": 0.0025595904655255157,
      "grad_norm": NaN,
      "learning_rate": 4.2273684210526317e-05,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.002580920386071562,
      "grad_norm": NaN,
      "learning_rate": 4.174526315789474e-05,
      "loss": 0.0,
      "step": 121
    },
    {
      "epoch": 0.002602250306617608,
      "grad_norm": NaN,
      "learning_rate": 4.121684210526316e-05,
      "loss": 0.0,
      "step": 122
    },
    {
      "epoch": 0.0026235802271636537,
      "grad_norm": NaN,
      "learning_rate": 4.068842105263158e-05,
      "loss": 0.0,
      "step": 123
    },
    {
      "epoch": 0.0026449101477097,
      "grad_norm": NaN,
      "learning_rate": 4.016e-05,
      "loss": 0.0,
      "step": 124
    },
    {
      "epoch": 0.002666240068255746,
      "grad_norm": NaN,
      "learning_rate": 3.963157894736842e-05,
      "loss": 0.0,
      "step": 125
    },
    {
      "epoch": 0.0026875699888017916,
      "grad_norm": NaN,
      "learning_rate": 3.9103157894736844e-05,
      "loss": 0.0,
      "step": 126
    },
    {
      "epoch": 0.0027088999093478378,
      "grad_norm": NaN,
      "learning_rate": 3.857473684210526e-05,
      "loss": 0.0,
      "step": 127
    },
    {
      "epoch": 0.0027302298298938835,
      "grad_norm": NaN,
      "learning_rate": 3.804631578947369e-05,
      "loss": 0.0,
      "step": 128
    },
    {
      "epoch": 0.0027515597504399296,
      "grad_norm": NaN,
      "learning_rate": 3.7517894736842105e-05,
      "loss": 0.0,
      "step": 129
    },
    {
      "epoch": 0.0027728896709859757,
      "grad_norm": NaN,
      "learning_rate": 3.698947368421052e-05,
      "loss": 0.0,
      "step": 130
    },
    {
      "epoch": 0.0027942195915320214,
      "grad_norm": NaN,
      "learning_rate": 3.646105263157895e-05,
      "loss": 0.0,
      "step": 131
    },
    {
      "epoch": 0.0028155495120780675,
      "grad_norm": NaN,
      "learning_rate": 3.593263157894737e-05,
      "loss": 0.0,
      "step": 132
    },
    {
      "epoch": 0.0028368794326241137,
      "grad_norm": NaN,
      "learning_rate": 3.540421052631579e-05,
      "loss": 0.0,
      "step": 133
    },
    {
      "epoch": 0.0028582093531701594,
      "grad_norm": NaN,
      "learning_rate": 3.4875789473684215e-05,
      "loss": 0.0,
      "step": 134
    },
    {
      "epoch": 0.0028795392737162055,
      "grad_norm": NaN,
      "learning_rate": 3.434736842105263e-05,
      "loss": 0.0,
      "step": 135
    },
    {
      "epoch": 0.002900869194262251,
      "grad_norm": NaN,
      "learning_rate": 3.381894736842105e-05,
      "loss": 0.0,
      "step": 136
    },
    {
      "epoch": 0.0029221991148082973,
      "grad_norm": NaN,
      "learning_rate": 3.329052631578947e-05,
      "loss": 0.0,
      "step": 137
    },
    {
      "epoch": 0.0029435290353543434,
      "grad_norm": NaN,
      "learning_rate": 3.27621052631579e-05,
      "loss": 0.0,
      "step": 138
    },
    {
      "epoch": 0.002964858955900389,
      "grad_norm": NaN,
      "learning_rate": 3.223368421052632e-05,
      "loss": 0.0,
      "step": 139
    },
    {
      "epoch": 0.0029861888764464353,
      "grad_norm": NaN,
      "learning_rate": 3.1705263157894736e-05,
      "loss": 0.0,
      "step": 140
    },
    {
      "epoch": 0.0030075187969924814,
      "grad_norm": NaN,
      "learning_rate": 3.117684210526316e-05,
      "loss": 0.0,
      "step": 141
    },
    {
      "epoch": 0.003028848717538527,
      "grad_norm": NaN,
      "learning_rate": 3.064842105263158e-05,
      "loss": 0.0,
      "step": 142
    },
    {
      "epoch": 0.003050178638084573,
      "grad_norm": NaN,
      "learning_rate": 3.012e-05,
      "loss": 0.0,
      "step": 143
    },
    {
      "epoch": 0.003071508558630619,
      "grad_norm": NaN,
      "learning_rate": 2.9591578947368418e-05,
      "loss": 0.0,
      "step": 144
    },
    {
      "epoch": 0.003092838479176665,
      "grad_norm": NaN,
      "learning_rate": 2.9063157894736842e-05,
      "loss": 0.0,
      "step": 145
    },
    {
      "epoch": 0.003114168399722711,
      "grad_norm": NaN,
      "learning_rate": 2.8534736842105264e-05,
      "loss": 0.0,
      "step": 146
    },
    {
      "epoch": 0.003135498320268757,
      "grad_norm": NaN,
      "learning_rate": 2.800631578947368e-05,
      "loss": 0.0,
      "step": 147
    },
    {
      "epoch": 0.003156828240814803,
      "grad_norm": NaN,
      "learning_rate": 2.7477894736842106e-05,
      "loss": 0.0,
      "step": 148
    },
    {
      "epoch": 0.003178158161360849,
      "grad_norm": NaN,
      "learning_rate": 2.6949473684210527e-05,
      "loss": 0.0,
      "step": 149
    },
    {
      "epoch": 0.003199488081906895,
      "grad_norm": NaN,
      "learning_rate": 2.6421052631578945e-05,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 0.003199488081906895,
      "eval_loss": NaN,
      "eval_runtime": 2181.6867,
      "eval_samples_per_second": 9.048,
      "eval_steps_per_second": 2.262,
      "step": 150
    },
    {
      "epoch": 0.003220818002452941,
      "grad_norm": NaN,
      "learning_rate": 2.589263157894737e-05,
      "loss": 0.0,
      "step": 151
    },
    {
      "epoch": 0.0032421479229989866,
      "grad_norm": NaN,
      "learning_rate": 2.536421052631579e-05,
      "loss": 0.0,
      "step": 152
    },
    {
      "epoch": 0.0032634778435450327,
      "grad_norm": NaN,
      "learning_rate": 2.483578947368421e-05,
      "loss": 0.0,
      "step": 153
    },
    {
      "epoch": 0.003284807764091079,
      "grad_norm": NaN,
      "learning_rate": 2.430736842105263e-05,
      "loss": 0.0,
      "step": 154
    },
    {
      "epoch": 0.0033061376846371246,
      "grad_norm": NaN,
      "learning_rate": 2.3778947368421052e-05,
      "loss": 0.0,
      "step": 155
    },
    {
      "epoch": 0.0033274676051831707,
      "grad_norm": NaN,
      "learning_rate": 2.3250526315789473e-05,
      "loss": 0.0,
      "step": 156
    },
    {
      "epoch": 0.003348797525729217,
      "grad_norm": NaN,
      "learning_rate": 2.2722105263157894e-05,
      "loss": 0.0,
      "step": 157
    },
    {
      "epoch": 0.0033701274462752625,
      "grad_norm": NaN,
      "learning_rate": 2.2193684210526316e-05,
      "loss": 0.0,
      "step": 158
    },
    {
      "epoch": 0.0033914573668213086,
      "grad_norm": NaN,
      "learning_rate": 2.1665263157894737e-05,
      "loss": 0.0,
      "step": 159
    },
    {
      "epoch": 0.0034127872873673548,
      "grad_norm": NaN,
      "learning_rate": 2.1136842105263158e-05,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.0034341172079134005,
      "grad_norm": NaN,
      "learning_rate": 2.060842105263158e-05,
      "loss": 0.0,
      "step": 161
    },
    {
      "epoch": 0.0034554471284594466,
      "grad_norm": NaN,
      "learning_rate": 2.008e-05,
      "loss": 0.0,
      "step": 162
    },
    {
      "epoch": 0.0034767770490054923,
      "grad_norm": NaN,
      "learning_rate": 1.9551578947368422e-05,
      "loss": 0.0,
      "step": 163
    },
    {
      "epoch": 0.0034981069695515384,
      "grad_norm": NaN,
      "learning_rate": 1.9023157894736843e-05,
      "loss": 0.0,
      "step": 164
    },
    {
      "epoch": 0.0035194368900975845,
      "grad_norm": NaN,
      "learning_rate": 1.849473684210526e-05,
      "loss": 0.0,
      "step": 165
    },
    {
      "epoch": 0.0035407668106436302,
      "grad_norm": NaN,
      "learning_rate": 1.7966315789473686e-05,
      "loss": 0.0,
      "step": 166
    },
    {
      "epoch": 0.0035620967311896764,
      "grad_norm": NaN,
      "learning_rate": 1.7437894736842107e-05,
      "loss": 0.0,
      "step": 167
    },
    {
      "epoch": 0.0035834266517357225,
      "grad_norm": NaN,
      "learning_rate": 1.6909473684210525e-05,
      "loss": 0.0,
      "step": 168
    },
    {
      "epoch": 0.003604756572281768,
      "grad_norm": NaN,
      "learning_rate": 1.638105263157895e-05,
      "loss": 0.0,
      "step": 169
    },
    {
      "epoch": 0.0036260864928278143,
      "grad_norm": NaN,
      "learning_rate": 1.5852631578947368e-05,
      "loss": 0.0,
      "step": 170
    },
    {
      "epoch": 0.00364741641337386,
      "grad_norm": NaN,
      "learning_rate": 1.532421052631579e-05,
      "loss": 0.0,
      "step": 171
    },
    {
      "epoch": 0.003668746333919906,
      "grad_norm": NaN,
      "learning_rate": 1.4795789473684209e-05,
      "loss": 0.0,
      "step": 172
    },
    {
      "epoch": 0.0036900762544659522,
      "grad_norm": NaN,
      "learning_rate": 1.4267368421052632e-05,
      "loss": 0.0,
      "step": 173
    },
    {
      "epoch": 0.003711406175011998,
      "grad_norm": NaN,
      "learning_rate": 1.3738947368421053e-05,
      "loss": 0.0,
      "step": 174
    },
    {
      "epoch": 0.003732736095558044,
      "grad_norm": NaN,
      "learning_rate": 1.3210526315789473e-05,
      "loss": 0.0,
      "step": 175
    },
    {
      "epoch": 0.00375406601610409,
      "grad_norm": NaN,
      "learning_rate": 1.2682105263157896e-05,
      "loss": 0.0,
      "step": 176
    },
    {
      "epoch": 0.003775395936650136,
      "grad_norm": NaN,
      "learning_rate": 1.2153684210526315e-05,
      "loss": 0.0,
      "step": 177
    },
    {
      "epoch": 0.003796725857196182,
      "grad_norm": NaN,
      "learning_rate": 1.1625263157894737e-05,
      "loss": 0.0,
      "step": 178
    },
    {
      "epoch": 0.0038180557777422277,
      "grad_norm": NaN,
      "learning_rate": 1.1096842105263158e-05,
      "loss": 0.0,
      "step": 179
    },
    {
      "epoch": 0.003839385698288274,
      "grad_norm": NaN,
      "learning_rate": 1.0568421052631579e-05,
      "loss": 0.0,
      "step": 180
    },
    {
      "epoch": 0.00386071561883432,
      "grad_norm": NaN,
      "learning_rate": 1.004e-05,
      "loss": 0.0,
      "step": 181
    },
    {
      "epoch": 0.0038820455393803657,
      "grad_norm": NaN,
      "learning_rate": 9.511578947368422e-06,
      "loss": 0.0,
      "step": 182
    },
    {
      "epoch": 0.003903375459926412,
      "grad_norm": NaN,
      "learning_rate": 8.983157894736843e-06,
      "loss": 0.0,
      "step": 183
    },
    {
      "epoch": 0.003924705380472458,
      "grad_norm": NaN,
      "learning_rate": 8.454736842105263e-06,
      "loss": 0.0,
      "step": 184
    },
    {
      "epoch": 0.003946035301018504,
      "grad_norm": NaN,
      "learning_rate": 7.926315789473684e-06,
      "loss": 0.0,
      "step": 185
    },
    {
      "epoch": 0.003967365221564549,
      "grad_norm": NaN,
      "learning_rate": 7.397894736842104e-06,
      "loss": 0.0,
      "step": 186
    },
    {
      "epoch": 0.003988695142110595,
      "grad_norm": NaN,
      "learning_rate": 6.8694736842105265e-06,
      "loss": 0.0,
      "step": 187
    },
    {
      "epoch": 0.0040100250626566416,
      "grad_norm": NaN,
      "learning_rate": 6.341052631578948e-06,
      "loss": 0.0,
      "step": 188
    },
    {
      "epoch": 0.004031354983202688,
      "grad_norm": NaN,
      "learning_rate": 5.812631578947368e-06,
      "loss": 0.0,
      "step": 189
    },
    {
      "epoch": 0.004052684903748734,
      "grad_norm": NaN,
      "learning_rate": 5.2842105263157896e-06,
      "loss": 0.0,
      "step": 190
    },
    {
      "epoch": 0.004074014824294779,
      "grad_norm": NaN,
      "learning_rate": 4.755789473684211e-06,
      "loss": 0.0,
      "step": 191
    },
    {
      "epoch": 0.004095344744840825,
      "grad_norm": NaN,
      "learning_rate": 4.227368421052631e-06,
      "loss": 0.0,
      "step": 192
    },
    {
      "epoch": 0.004116674665386871,
      "grad_norm": NaN,
      "learning_rate": 3.698947368421052e-06,
      "loss": 0.0,
      "step": 193
    },
    {
      "epoch": 0.0041380045859329175,
      "grad_norm": NaN,
      "learning_rate": 3.170526315789474e-06,
      "loss": 0.0,
      "step": 194
    },
    {
      "epoch": 0.004159334506478964,
      "grad_norm": NaN,
      "learning_rate": 2.6421052631578948e-06,
      "loss": 0.0,
      "step": 195
    },
    {
      "epoch": 0.00418066442702501,
      "grad_norm": NaN,
      "learning_rate": 2.1136842105263157e-06,
      "loss": 0.0,
      "step": 196
    },
    {
      "epoch": 0.004201994347571055,
      "grad_norm": NaN,
      "learning_rate": 1.585263157894737e-06,
      "loss": 0.0,
      "step": 197
    },
    {
      "epoch": 0.004223324268117101,
      "grad_norm": NaN,
      "learning_rate": 1.0568421052631578e-06,
      "loss": 0.0,
      "step": 198
    },
    {
      "epoch": 0.004244654188663147,
      "grad_norm": NaN,
      "learning_rate": 5.284210526315789e-07,
      "loss": 0.0,
      "step": 199
    },
    {
      "epoch": 0.004265984109209193,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.004265984109209193,
      "eval_loss": NaN,
      "eval_runtime": 2181.8889,
      "eval_samples_per_second": 9.047,
      "eval_steps_per_second": 2.262,
      "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": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.208656527006106e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}