{
  "best_metric": 0.23224526643753052,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 1.0,
  "eval_steps": 50,
  "global_step": 107,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009345794392523364,
      "grad_norm": 1.2118754386901855,
      "learning_rate": 1e-05,
      "loss": 0.8063,
      "step": 1
    },
    {
      "epoch": 0.009345794392523364,
      "eval_loss": 0.7730486392974854,
      "eval_runtime": 14.8906,
      "eval_samples_per_second": 12.155,
      "eval_steps_per_second": 3.089,
      "step": 1
    },
    {
      "epoch": 0.018691588785046728,
      "grad_norm": 1.7004547119140625,
      "learning_rate": 2e-05,
      "loss": 0.8924,
      "step": 2
    },
    {
      "epoch": 0.028037383177570093,
      "grad_norm": 1.4907296895980835,
      "learning_rate": 3e-05,
      "loss": 0.6562,
      "step": 3
    },
    {
      "epoch": 0.037383177570093455,
      "grad_norm": 1.358850359916687,
      "learning_rate": 4e-05,
      "loss": 0.4478,
      "step": 4
    },
    {
      "epoch": 0.04672897196261682,
      "grad_norm": 1.1591500043869019,
      "learning_rate": 5e-05,
      "loss": 0.4457,
      "step": 5
    },
    {
      "epoch": 0.056074766355140186,
      "grad_norm": 1.2124463319778442,
      "learning_rate": 6e-05,
      "loss": 0.3413,
      "step": 6
    },
    {
      "epoch": 0.06542056074766354,
      "grad_norm": 1.477152705192566,
      "learning_rate": 7e-05,
      "loss": 0.3224,
      "step": 7
    },
    {
      "epoch": 0.07476635514018691,
      "grad_norm": 1.3230681419372559,
      "learning_rate": 8e-05,
      "loss": 0.4452,
      "step": 8
    },
    {
      "epoch": 0.08411214953271028,
      "grad_norm": 1.0649213790893555,
      "learning_rate": 9e-05,
      "loss": 0.3927,
      "step": 9
    },
    {
      "epoch": 0.09345794392523364,
      "grad_norm": 1.3603013753890991,
      "learning_rate": 0.0001,
      "loss": 0.3909,
      "step": 10
    },
    {
      "epoch": 0.102803738317757,
      "grad_norm": 1.195493459701538,
      "learning_rate": 9.997377845227576e-05,
      "loss": 0.3308,
      "step": 11
    },
    {
      "epoch": 0.11214953271028037,
      "grad_norm": 0.8207054138183594,
      "learning_rate": 9.989514131188559e-05,
      "loss": 0.3578,
      "step": 12
    },
    {
      "epoch": 0.12149532710280374,
      "grad_norm": 0.8612375855445862,
      "learning_rate": 9.97641710583307e-05,
      "loss": 0.3874,
      "step": 13
    },
    {
      "epoch": 0.1308411214953271,
      "grad_norm": 0.9588674306869507,
      "learning_rate": 9.958100506132127e-05,
      "loss": 0.449,
      "step": 14
    },
    {
      "epoch": 0.14018691588785046,
      "grad_norm": 0.8636590242385864,
      "learning_rate": 9.934583543669453e-05,
      "loss": 0.3778,
      "step": 15
    },
    {
      "epoch": 0.14953271028037382,
      "grad_norm": 0.9204433560371399,
      "learning_rate": 9.905890884491195e-05,
      "loss": 0.4883,
      "step": 16
    },
    {
      "epoch": 0.1588785046728972,
      "grad_norm": 0.8820167779922485,
      "learning_rate": 9.872052623234632e-05,
      "loss": 0.443,
      "step": 17
    },
    {
      "epoch": 0.16822429906542055,
      "grad_norm": 0.7248702645301819,
      "learning_rate": 9.833104251563056e-05,
      "loss": 0.3601,
      "step": 18
    },
    {
      "epoch": 0.17757009345794392,
      "grad_norm": 0.7967797517776489,
      "learning_rate": 9.789086620939936e-05,
      "loss": 0.4402,
      "step": 19
    },
    {
      "epoch": 0.18691588785046728,
      "grad_norm": 0.9615940451622009,
      "learning_rate": 9.740045899781352e-05,
      "loss": 0.4484,
      "step": 20
    },
    {
      "epoch": 0.19626168224299065,
      "grad_norm": 1.0163406133651733,
      "learning_rate": 9.686033525031719e-05,
      "loss": 0.4522,
      "step": 21
    },
    {
      "epoch": 0.205607476635514,
      "grad_norm": 0.9328191876411438,
      "learning_rate": 9.627106148213522e-05,
      "loss": 0.3848,
      "step": 22
    },
    {
      "epoch": 0.21495327102803738,
      "grad_norm": 1.0401077270507812,
      "learning_rate": 9.563325576007701e-05,
      "loss": 0.4394,
      "step": 23
    },
    {
      "epoch": 0.22429906542056074,
      "grad_norm": 1.1316356658935547,
      "learning_rate": 9.494758705426978e-05,
      "loss": 0.5448,
      "step": 24
    },
    {
      "epoch": 0.2336448598130841,
      "grad_norm": 1.076812505722046,
      "learning_rate": 9.421477453650118e-05,
      "loss": 0.5361,
      "step": 25
    },
    {
      "epoch": 0.24299065420560748,
      "grad_norm": 1.1580618619918823,
      "learning_rate": 9.343558682590756e-05,
      "loss": 0.4144,
      "step": 26
    },
    {
      "epoch": 0.2523364485981308,
      "grad_norm": 0.7226683497428894,
      "learning_rate": 9.261084118279847e-05,
      "loss": 0.5771,
      "step": 27
    },
    {
      "epoch": 0.2616822429906542,
      "grad_norm": 0.8558270931243896,
      "learning_rate": 9.174140265146356e-05,
      "loss": 0.4875,
      "step": 28
    },
    {
      "epoch": 0.27102803738317754,
      "grad_norm": 0.6313632726669312,
      "learning_rate": 9.082818315286055e-05,
      "loss": 0.2833,
      "step": 29
    },
    {
      "epoch": 0.2803738317757009,
      "grad_norm": 0.54814213514328,
      "learning_rate": 8.987214052813604e-05,
      "loss": 0.1784,
      "step": 30
    },
    {
      "epoch": 0.2897196261682243,
      "grad_norm": 0.5720391273498535,
      "learning_rate": 8.887427753398248e-05,
      "loss": 0.1903,
      "step": 31
    },
    {
      "epoch": 0.29906542056074764,
      "grad_norm": 0.5032756924629211,
      "learning_rate": 8.783564079088477e-05,
      "loss": 0.2295,
      "step": 32
    },
    {
      "epoch": 0.308411214953271,
      "grad_norm": 0.7864720821380615,
      "learning_rate": 8.675731968536002e-05,
      "loss": 0.3057,
      "step": 33
    },
    {
      "epoch": 0.3177570093457944,
      "grad_norm": 0.6048300266265869,
      "learning_rate": 8.564044522734147e-05,
      "loss": 0.2863,
      "step": 34
    },
    {
      "epoch": 0.32710280373831774,
      "grad_norm": 0.7044374346733093,
      "learning_rate": 8.448618886390522e-05,
      "loss": 0.2952,
      "step": 35
    },
    {
      "epoch": 0.3364485981308411,
      "grad_norm": 0.5851072072982788,
      "learning_rate": 8.329576125058406e-05,
      "loss": 0.2035,
      "step": 36
    },
    {
      "epoch": 0.34579439252336447,
      "grad_norm": 0.7135735154151917,
      "learning_rate": 8.2070410981557e-05,
      "loss": 0.312,
      "step": 37
    },
    {
      "epoch": 0.35514018691588783,
      "grad_norm": 0.6680054068565369,
      "learning_rate": 8.081142328004637e-05,
      "loss": 0.3637,
      "step": 38
    },
    {
      "epoch": 0.3644859813084112,
      "grad_norm": 0.5793293714523315,
      "learning_rate": 7.952011865029614e-05,
      "loss": 0.2209,
      "step": 39
    },
    {
      "epoch": 0.37383177570093457,
      "grad_norm": 0.7005558013916016,
      "learning_rate": 7.819785149254532e-05,
      "loss": 0.3438,
      "step": 40
    },
    {
      "epoch": 0.38317757009345793,
      "grad_norm": 0.7467755079269409,
      "learning_rate": 7.68460086824492e-05,
      "loss": 0.3601,
      "step": 41
    },
    {
      "epoch": 0.3925233644859813,
      "grad_norm": 0.7336003184318542,
      "learning_rate": 7.546600811643816e-05,
      "loss": 0.3653,
      "step": 42
    },
    {
      "epoch": 0.40186915887850466,
      "grad_norm": 0.8589034080505371,
      "learning_rate": 7.405929722454026e-05,
      "loss": 0.356,
      "step": 43
    },
    {
      "epoch": 0.411214953271028,
      "grad_norm": 0.8823071122169495,
      "learning_rate": 7.262735145222696e-05,
      "loss": 0.3742,
      "step": 44
    },
    {
      "epoch": 0.4205607476635514,
      "grad_norm": 0.9084258675575256,
      "learning_rate": 7.117167271287453e-05,
      "loss": 0.3287,
      "step": 45
    },
    {
      "epoch": 0.42990654205607476,
      "grad_norm": 0.8384641408920288,
      "learning_rate": 6.969378781246436e-05,
      "loss": 0.3742,
      "step": 46
    },
    {
      "epoch": 0.4392523364485981,
      "grad_norm": 0.7774955034255981,
      "learning_rate": 6.819524684817438e-05,
      "loss": 0.3295,
      "step": 47
    },
    {
      "epoch": 0.4485981308411215,
      "grad_norm": 0.7413498163223267,
      "learning_rate": 6.667762158254104e-05,
      "loss": 0.3136,
      "step": 48
    },
    {
      "epoch": 0.45794392523364486,
      "grad_norm": 0.783761203289032,
      "learning_rate": 6.514250379489753e-05,
      "loss": 0.287,
      "step": 49
    },
    {
      "epoch": 0.4672897196261682,
      "grad_norm": 0.9675016403198242,
      "learning_rate": 6.359150361181715e-05,
      "loss": 0.353,
      "step": 50
    },
    {
      "epoch": 0.4672897196261682,
      "eval_loss": 0.283975750207901,
      "eval_runtime": 15.2093,
      "eval_samples_per_second": 11.901,
      "eval_steps_per_second": 3.024,
      "step": 50
    },
    {
      "epoch": 0.4766355140186916,
      "grad_norm": 1.1342438459396362,
      "learning_rate": 6.202624781831268e-05,
      "loss": 0.3326,
      "step": 51
    },
    {
      "epoch": 0.48598130841121495,
      "grad_norm": 0.9279870986938477,
      "learning_rate": 6.044837815156377e-05,
      "loss": 0.3252,
      "step": 52
    },
    {
      "epoch": 0.4953271028037383,
      "grad_norm": 0.5372065901756287,
      "learning_rate": 5.885954957896115e-05,
      "loss": 0.3693,
      "step": 53
    },
    {
      "epoch": 0.5046728971962616,
      "grad_norm": 1.0543334484100342,
      "learning_rate": 5.726142856227452e-05,
      "loss": 0.6897,
      "step": 54
    },
    {
      "epoch": 0.514018691588785,
      "grad_norm": 0.5793179869651794,
      "learning_rate": 5.565569130976422e-05,
      "loss": 0.2111,
      "step": 55
    },
    {
      "epoch": 0.5233644859813084,
      "grad_norm": 0.5614607930183411,
      "learning_rate": 5.4044022018070214e-05,
      "loss": 0.1905,
      "step": 56
    },
    {
      "epoch": 0.5327102803738317,
      "grad_norm": 0.6062226891517639,
      "learning_rate": 5.242811110572242e-05,
      "loss": 0.2007,
      "step": 57
    },
    {
      "epoch": 0.5420560747663551,
      "grad_norm": 0.5884981155395508,
      "learning_rate": 5.080965344012508e-05,
      "loss": 0.1989,
      "step": 58
    },
    {
      "epoch": 0.5514018691588785,
      "grad_norm": 0.5349563360214233,
      "learning_rate": 4.919034655987493e-05,
      "loss": 0.2204,
      "step": 59
    },
    {
      "epoch": 0.5607476635514018,
      "grad_norm": 0.5922881960868835,
      "learning_rate": 4.7571888894277604e-05,
      "loss": 0.256,
      "step": 60
    },
    {
      "epoch": 0.5700934579439252,
      "grad_norm": 0.5709701776504517,
      "learning_rate": 4.59559779819298e-05,
      "loss": 0.2065,
      "step": 61
    },
    {
      "epoch": 0.5794392523364486,
      "grad_norm": 0.5307181477546692,
      "learning_rate": 4.434430869023579e-05,
      "loss": 0.1677,
      "step": 62
    },
    {
      "epoch": 0.5887850467289719,
      "grad_norm": 0.5722399950027466,
      "learning_rate": 4.27385714377255e-05,
      "loss": 0.2411,
      "step": 63
    },
    {
      "epoch": 0.5981308411214953,
      "grad_norm": 0.489662766456604,
      "learning_rate": 4.114045042103887e-05,
      "loss": 0.1892,
      "step": 64
    },
    {
      "epoch": 0.6074766355140186,
      "grad_norm": 0.8208240270614624,
      "learning_rate": 3.955162184843625e-05,
      "loss": 0.3509,
      "step": 65
    },
    {
      "epoch": 0.616822429906542,
      "grad_norm": 0.7339255213737488,
      "learning_rate": 3.7973752181687335e-05,
      "loss": 0.2853,
      "step": 66
    },
    {
      "epoch": 0.6261682242990654,
      "grad_norm": 0.7878158092498779,
      "learning_rate": 3.640849638818286e-05,
      "loss": 0.3666,
      "step": 67
    },
    {
      "epoch": 0.6355140186915887,
      "grad_norm": 0.600767195224762,
      "learning_rate": 3.4857496205102474e-05,
      "loss": 0.279,
      "step": 68
    },
    {
      "epoch": 0.6448598130841121,
      "grad_norm": 0.7032753825187683,
      "learning_rate": 3.332237841745898e-05,
      "loss": 0.3348,
      "step": 69
    },
    {
      "epoch": 0.6542056074766355,
      "grad_norm": 0.7657633423805237,
      "learning_rate": 3.180475315182563e-05,
      "loss": 0.3218,
      "step": 70
    },
    {
      "epoch": 0.6635514018691588,
      "grad_norm": 0.6951287388801575,
      "learning_rate": 3.0306212187535653e-05,
      "loss": 0.3108,
      "step": 71
    },
    {
      "epoch": 0.6728971962616822,
      "grad_norm": 0.7856379151344299,
      "learning_rate": 2.882832728712551e-05,
      "loss": 0.3201,
      "step": 72
    },
    {
      "epoch": 0.6822429906542056,
      "grad_norm": 0.7768362760543823,
      "learning_rate": 2.737264854777306e-05,
      "loss": 0.2302,
      "step": 73
    },
    {
      "epoch": 0.6915887850467289,
      "grad_norm": 0.7495273947715759,
      "learning_rate": 2.5940702775459747e-05,
      "loss": 0.2837,
      "step": 74
    },
    {
      "epoch": 0.7009345794392523,
      "grad_norm": 0.6833620667457581,
      "learning_rate": 2.4533991883561868e-05,
      "loss": 0.288,
      "step": 75
    },
    {
      "epoch": 0.7102803738317757,
      "grad_norm": 0.9326289296150208,
      "learning_rate": 2.315399131755081e-05,
      "loss": 0.2953,
      "step": 76
    },
    {
      "epoch": 0.719626168224299,
      "grad_norm": 0.7127006649971008,
      "learning_rate": 2.180214850745467e-05,
      "loss": 0.2908,
      "step": 77
    },
    {
      "epoch": 0.7289719626168224,
      "grad_norm": 1.0180916786193848,
      "learning_rate": 2.0479881349703883e-05,
      "loss": 0.3716,
      "step": 78
    },
    {
      "epoch": 0.7383177570093458,
      "grad_norm": 0.583429753780365,
      "learning_rate": 1.9188576719953633e-05,
      "loss": 0.5111,
      "step": 79
    },
    {
      "epoch": 0.7476635514018691,
      "grad_norm": 0.9300647377967834,
      "learning_rate": 1.7929589018443016e-05,
      "loss": 0.4941,
      "step": 80
    },
    {
      "epoch": 0.7570093457943925,
      "grad_norm": 0.5266556143760681,
      "learning_rate": 1.6704238749415957e-05,
      "loss": 0.2014,
      "step": 81
    },
    {
      "epoch": 0.7663551401869159,
      "grad_norm": 0.3937390446662903,
      "learning_rate": 1.5513811136094787e-05,
      "loss": 0.1134,
      "step": 82
    },
    {
      "epoch": 0.7757009345794392,
      "grad_norm": 0.5176160931587219,
      "learning_rate": 1.4359554772658552e-05,
      "loss": 0.2048,
      "step": 83
    },
    {
      "epoch": 0.7850467289719626,
      "grad_norm": 0.49737098813056946,
      "learning_rate": 1.3242680314639993e-05,
      "loss": 0.1656,
      "step": 84
    },
    {
      "epoch": 0.794392523364486,
      "grad_norm": 0.7320502996444702,
      "learning_rate": 1.2164359209115234e-05,
      "loss": 0.3223,
      "step": 85
    },
    {
      "epoch": 0.8037383177570093,
      "grad_norm": 0.5976892709732056,
      "learning_rate": 1.1125722466017547e-05,
      "loss": 0.2132,
      "step": 86
    },
    {
      "epoch": 0.8130841121495327,
      "grad_norm": 0.6687475442886353,
      "learning_rate": 1.012785947186397e-05,
      "loss": 0.2055,
      "step": 87
    },
    {
      "epoch": 0.822429906542056,
      "grad_norm": 0.603065013885498,
      "learning_rate": 9.171816847139448e-06,
      "loss": 0.186,
      "step": 88
    },
    {
      "epoch": 0.8317757009345794,
      "grad_norm": 0.5435901880264282,
      "learning_rate": 8.25859734853645e-06,
      "loss": 0.2109,
      "step": 89
    },
    {
      "epoch": 0.8411214953271028,
      "grad_norm": 0.6504529714584351,
      "learning_rate": 7.389158817201542e-06,
      "loss": 0.2328,
      "step": 90
    },
    {
      "epoch": 0.8504672897196262,
      "grad_norm": 0.7861918210983276,
      "learning_rate": 6.564413174092443e-06,
      "loss": 0.2692,
      "step": 91
    },
    {
      "epoch": 0.8598130841121495,
      "grad_norm": 0.5888051390647888,
      "learning_rate": 5.785225463498828e-06,
      "loss": 0.2117,
      "step": 92
    },
    {
      "epoch": 0.8691588785046729,
      "grad_norm": 0.5872686505317688,
      "learning_rate": 5.05241294573024e-06,
      "loss": 0.2273,
      "step": 93
    },
    {
      "epoch": 0.8785046728971962,
      "grad_norm": 0.7006099224090576,
      "learning_rate": 4.366744239922998e-06,
      "loss": 0.2502,
      "step": 94
    },
    {
      "epoch": 0.8878504672897196,
      "grad_norm": 0.6123574376106262,
      "learning_rate": 3.728938517864794e-06,
      "loss": 0.2465,
      "step": 95
    },
    {
      "epoch": 0.897196261682243,
      "grad_norm": 0.5895901918411255,
      "learning_rate": 3.1396647496828247e-06,
      "loss": 0.2473,
      "step": 96
    },
    {
      "epoch": 0.9065420560747663,
      "grad_norm": 0.513577938079834,
      "learning_rate": 2.5995410021864787e-06,
      "loss": 0.1811,
      "step": 97
    },
    {
      "epoch": 0.9158878504672897,
      "grad_norm": 0.5878252983093262,
      "learning_rate": 2.1091337906006482e-06,
      "loss": 0.2349,
      "step": 98
    },
    {
      "epoch": 0.9252336448598131,
      "grad_norm": 0.5837914943695068,
      "learning_rate": 1.6689574843694433e-06,
      "loss": 0.2317,
      "step": 99
    },
    {
      "epoch": 0.9345794392523364,
      "grad_norm": 0.5625414848327637,
      "learning_rate": 1.2794737676536994e-06,
      "loss": 0.1619,
      "step": 100
    },
    {
      "epoch": 0.9345794392523364,
      "eval_loss": 0.23224526643753052,
      "eval_runtime": 14.9082,
      "eval_samples_per_second": 12.141,
      "eval_steps_per_second": 3.086,
      "step": 100
    },
    {
      "epoch": 0.9439252336448598,
      "grad_norm": 0.7002161741256714,
      "learning_rate": 9.410911550880475e-07,
      "loss": 0.2533,
      "step": 101
    },
    {
      "epoch": 0.9532710280373832,
      "grad_norm": 0.6093440651893616,
      "learning_rate": 6.54164563305465e-07,
      "loss": 0.1811,
      "step": 102
    },
    {
      "epoch": 0.9626168224299065,
      "grad_norm": 0.7323504686355591,
      "learning_rate": 4.189949386787462e-07,
      "loss": 0.2834,
      "step": 103
    },
    {
      "epoch": 0.9719626168224299,
      "grad_norm": 0.701038122177124,
      "learning_rate": 2.3582894166930268e-07,
      "loss": 0.2602,
      "step": 104
    },
    {
      "epoch": 0.9813084112149533,
      "grad_norm": 0.44046589732170105,
      "learning_rate": 1.0485868811441757e-07,
      "loss": 0.2167,
      "step": 105
    },
    {
      "epoch": 0.9906542056074766,
      "grad_norm": 0.6788187026977539,
      "learning_rate": 2.6221547724253337e-08,
      "loss": 0.3156,
      "step": 106
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.561313807964325,
      "learning_rate": 0.0,
      "loss": 0.2182,
      "step": 107
    }
  ],
  "logging_steps": 1,
  "max_steps": 107,
  "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": 1.7536470352920576e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}