{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.953191489361702,
  "eval_steps": 500,
  "global_step": 440,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011347517730496455,
      "grad_norm": 42.11255056967552,
      "learning_rate": 4.999936276068748e-05,
      "loss": 2.7084,
      "num_input_tokens_seen": 262144,
      "step": 1
    },
    {
      "epoch": 0.02269503546099291,
      "grad_norm": 54.92874275677881,
      "learning_rate": 4.9997451075235834e-05,
      "loss": 3.9726,
      "num_input_tokens_seen": 524288,
      "step": 2
    },
    {
      "epoch": 0.03404255319148936,
      "grad_norm": 42.37953862248386,
      "learning_rate": 4.999426504110115e-05,
      "loss": 3.6425,
      "num_input_tokens_seen": 786432,
      "step": 3
    },
    {
      "epoch": 0.04539007092198582,
      "grad_norm": 91.1622917243015,
      "learning_rate": 4.9989804820704735e-05,
      "loss": 3.9759,
      "num_input_tokens_seen": 1048576,
      "step": 4
    },
    {
      "epoch": 0.05673758865248227,
      "grad_norm": 18.918639143868496,
      "learning_rate": 4.99840706414248e-05,
      "loss": 2.7491,
      "num_input_tokens_seen": 1310720,
      "step": 5
    },
    {
      "epoch": 0.06808510638297872,
      "grad_norm": 1015.4776658382041,
      "learning_rate": 4.9977062795584893e-05,
      "loss": 6.0462,
      "num_input_tokens_seen": 1572864,
      "step": 6
    },
    {
      "epoch": 0.07943262411347518,
      "grad_norm": 72.92199611683951,
      "learning_rate": 4.9968781640439026e-05,
      "loss": 4.8547,
      "num_input_tokens_seen": 1835008,
      "step": 7
    },
    {
      "epoch": 0.09078014184397164,
      "grad_norm": 2053.7092461560514,
      "learning_rate": 4.995922759815339e-05,
      "loss": 3.4759,
      "num_input_tokens_seen": 2097152,
      "step": 8
    },
    {
      "epoch": 0.10212765957446808,
      "grad_norm": 301.76868717065724,
      "learning_rate": 4.9948401155784904e-05,
      "loss": 5.716,
      "num_input_tokens_seen": 2359296,
      "step": 9
    },
    {
      "epoch": 0.11347517730496454,
      "grad_norm": 22.772625297554043,
      "learning_rate": 4.993630286525634e-05,
      "loss": 3.0399,
      "num_input_tokens_seen": 2621440,
      "step": 10
    },
    {
      "epoch": 0.12482269503546099,
      "grad_norm": 30.392870542185943,
      "learning_rate": 4.99229333433282e-05,
      "loss": 2.7072,
      "num_input_tokens_seen": 2883584,
      "step": 11
    },
    {
      "epoch": 0.13617021276595745,
      "grad_norm": 7.488897181026025,
      "learning_rate": 4.9908293271567286e-05,
      "loss": 2.3501,
      "num_input_tokens_seen": 3145728,
      "step": 12
    },
    {
      "epoch": 0.1475177304964539,
      "grad_norm": 7.085681299970245,
      "learning_rate": 4.9892383396311934e-05,
      "loss": 2.157,
      "num_input_tokens_seen": 3407872,
      "step": 13
    },
    {
      "epoch": 0.15886524822695036,
      "grad_norm": 8.190856615122739,
      "learning_rate": 4.987520452863399e-05,
      "loss": 2.0567,
      "num_input_tokens_seen": 3670016,
      "step": 14
    },
    {
      "epoch": 0.1702127659574468,
      "grad_norm": 10.596165600490249,
      "learning_rate": 4.985675754429744e-05,
      "loss": 2.0914,
      "num_input_tokens_seen": 3932160,
      "step": 15
    },
    {
      "epoch": 0.18156028368794327,
      "grad_norm": 4.228212579415264,
      "learning_rate": 4.9837043383713753e-05,
      "loss": 1.9227,
      "num_input_tokens_seen": 4194304,
      "step": 16
    },
    {
      "epoch": 0.19290780141843972,
      "grad_norm": 7.545954107986025,
      "learning_rate": 4.981606305189401e-05,
      "loss": 1.9327,
      "num_input_tokens_seen": 4456448,
      "step": 17
    },
    {
      "epoch": 0.20425531914893616,
      "grad_norm": 5.46892073376645,
      "learning_rate": 4.979381761839757e-05,
      "loss": 1.9021,
      "num_input_tokens_seen": 4718592,
      "step": 18
    },
    {
      "epoch": 0.21560283687943263,
      "grad_norm": 4.169344521056397,
      "learning_rate": 4.9770308217277614e-05,
      "loss": 1.8432,
      "num_input_tokens_seen": 4980736,
      "step": 19
    },
    {
      "epoch": 0.22695035460992907,
      "grad_norm": 4.236687724660673,
      "learning_rate": 4.9745536047023324e-05,
      "loss": 1.8072,
      "num_input_tokens_seen": 5242880,
      "step": 20
    },
    {
      "epoch": 0.23829787234042554,
      "grad_norm": 2.060568655336032,
      "learning_rate": 4.971950237049874e-05,
      "loss": 1.7635,
      "num_input_tokens_seen": 5505024,
      "step": 21
    },
    {
      "epoch": 0.24964539007092199,
      "grad_norm": 4.122485050689507,
      "learning_rate": 4.9692208514878444e-05,
      "loss": 1.7203,
      "num_input_tokens_seen": 5767168,
      "step": 22
    },
    {
      "epoch": 0.26099290780141843,
      "grad_norm": 2.219869083818665,
      "learning_rate": 4.966365587157986e-05,
      "loss": 1.697,
      "num_input_tokens_seen": 6029312,
      "step": 23
    },
    {
      "epoch": 0.2723404255319149,
      "grad_norm": 2.978772859366142,
      "learning_rate": 4.963384589619233e-05,
      "loss": 1.6882,
      "num_input_tokens_seen": 6291456,
      "step": 24
    },
    {
      "epoch": 0.28368794326241137,
      "grad_norm": 2.3166879594611562,
      "learning_rate": 4.96027801084029e-05,
      "loss": 1.6619,
      "num_input_tokens_seen": 6553600,
      "step": 25
    },
    {
      "epoch": 0.2950354609929078,
      "grad_norm": 2.660252399042677,
      "learning_rate": 4.957046009191889e-05,
      "loss": 1.6709,
      "num_input_tokens_seen": 6815744,
      "step": 26
    },
    {
      "epoch": 0.30638297872340425,
      "grad_norm": 1.9436043867392558,
      "learning_rate": 4.95368874943871e-05,
      "loss": 1.6295,
      "num_input_tokens_seen": 7077888,
      "step": 27
    },
    {
      "epoch": 0.3177304964539007,
      "grad_norm": 3.2367808954229056,
      "learning_rate": 4.9502064027309836e-05,
      "loss": 1.6475,
      "num_input_tokens_seen": 7340032,
      "step": 28
    },
    {
      "epoch": 0.32907801418439714,
      "grad_norm": 2.9573963451533163,
      "learning_rate": 4.946599146595769e-05,
      "loss": 1.6421,
      "num_input_tokens_seen": 7602176,
      "step": 29
    },
    {
      "epoch": 0.3404255319148936,
      "grad_norm": 2.0096985811179584,
      "learning_rate": 4.942867164927899e-05,
      "loss": 1.6335,
      "num_input_tokens_seen": 7864320,
      "step": 30
    },
    {
      "epoch": 0.3517730496453901,
      "grad_norm": 3.2248151762473904,
      "learning_rate": 4.9390106479806085e-05,
      "loss": 1.6085,
      "num_input_tokens_seen": 8126464,
      "step": 31
    },
    {
      "epoch": 0.36312056737588655,
      "grad_norm": 2.03961317414281,
      "learning_rate": 4.935029792355834e-05,
      "loss": 1.5966,
      "num_input_tokens_seen": 8388608,
      "step": 32
    },
    {
      "epoch": 0.37446808510638296,
      "grad_norm": 3.106580267812995,
      "learning_rate": 4.9309248009941914e-05,
      "loss": 1.5939,
      "num_input_tokens_seen": 8650752,
      "step": 33
    },
    {
      "epoch": 0.38581560283687943,
      "grad_norm": 2.356069611331115,
      "learning_rate": 4.9266958831646315e-05,
      "loss": 1.5713,
      "num_input_tokens_seen": 8912896,
      "step": 34
    },
    {
      "epoch": 0.3971631205673759,
      "grad_norm": 2.555281051112305,
      "learning_rate": 4.922343254453768e-05,
      "loss": 1.5476,
      "num_input_tokens_seen": 9175040,
      "step": 35
    },
    {
      "epoch": 0.4085106382978723,
      "grad_norm": 2.1382267614522377,
      "learning_rate": 4.917867136754893e-05,
      "loss": 1.5501,
      "num_input_tokens_seen": 9437184,
      "step": 36
    },
    {
      "epoch": 0.4198581560283688,
      "grad_norm": 2.182480841186189,
      "learning_rate": 4.913267758256658e-05,
      "loss": 1.5678,
      "num_input_tokens_seen": 9699328,
      "step": 37
    },
    {
      "epoch": 0.43120567375886526,
      "grad_norm": 1.9946631054615584,
      "learning_rate": 4.9085453534314476e-05,
      "loss": 1.5604,
      "num_input_tokens_seen": 9961472,
      "step": 38
    },
    {
      "epoch": 0.4425531914893617,
      "grad_norm": 2.1201916556543505,
      "learning_rate": 4.9037001630234215e-05,
      "loss": 1.5265,
      "num_input_tokens_seen": 10223616,
      "step": 39
    },
    {
      "epoch": 0.45390070921985815,
      "grad_norm": 1.9422378506921851,
      "learning_rate": 4.898732434036244e-05,
      "loss": 1.5269,
      "num_input_tokens_seen": 10485760,
      "step": 40
    },
    {
      "epoch": 0.4652482269503546,
      "grad_norm": 1.7767185160628844,
      "learning_rate": 4.893642419720491e-05,
      "loss": 1.4965,
      "num_input_tokens_seen": 10747904,
      "step": 41
    },
    {
      "epoch": 0.4765957446808511,
      "grad_norm": 1.6802879544286047,
      "learning_rate": 4.888430379560742e-05,
      "loss": 1.5254,
      "num_input_tokens_seen": 11010048,
      "step": 42
    },
    {
      "epoch": 0.4879432624113475,
      "grad_norm": 1.6860871708585086,
      "learning_rate": 4.883096579262346e-05,
      "loss": 1.4975,
      "num_input_tokens_seen": 11272192,
      "step": 43
    },
    {
      "epoch": 0.49929078014184397,
      "grad_norm": 1.7303274117706944,
      "learning_rate": 4.877641290737884e-05,
      "loss": 1.5209,
      "num_input_tokens_seen": 11534336,
      "step": 44
    },
    {
      "epoch": 0.5106382978723404,
      "grad_norm": 1.4626721944583252,
      "learning_rate": 4.872064792093299e-05,
      "loss": 1.51,
      "num_input_tokens_seen": 11796480,
      "step": 45
    },
    {
      "epoch": 0.5219858156028369,
      "grad_norm": 1.6681840945027697,
      "learning_rate": 4.866367367613725e-05,
      "loss": 1.5086,
      "num_input_tokens_seen": 12058624,
      "step": 46
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 1.5207849294270255,
      "learning_rate": 4.86054930774899e-05,
      "loss": 1.4588,
      "num_input_tokens_seen": 12320768,
      "step": 47
    },
    {
      "epoch": 0.5446808510638298,
      "grad_norm": 1.616710324729056,
      "learning_rate": 4.854610909098812e-05,
      "loss": 1.4805,
      "num_input_tokens_seen": 12582912,
      "step": 48
    },
    {
      "epoch": 0.5560283687943263,
      "grad_norm": 1.60340831300244,
      "learning_rate": 4.848552474397676e-05,
      "loss": 1.4696,
      "num_input_tokens_seen": 12845056,
      "step": 49
    },
    {
      "epoch": 0.5673758865248227,
      "grad_norm": 1.7880113956949981,
      "learning_rate": 4.842374312499405e-05,
      "loss": 1.4821,
      "num_input_tokens_seen": 13107200,
      "step": 50
    },
    {
      "epoch": 0.5787234042553191,
      "grad_norm": 1.3568656846238325,
      "learning_rate": 4.836076738361408e-05,
      "loss": 1.4884,
      "num_input_tokens_seen": 13369344,
      "step": 51
    },
    {
      "epoch": 0.5900709219858156,
      "grad_norm": 1.5552837054733266,
      "learning_rate": 4.829660073028631e-05,
      "loss": 1.4686,
      "num_input_tokens_seen": 13631488,
      "step": 52
    },
    {
      "epoch": 0.601418439716312,
      "grad_norm": 1.4041461982644978,
      "learning_rate": 4.823124643617187e-05,
      "loss": 1.4522,
      "num_input_tokens_seen": 13893632,
      "step": 53
    },
    {
      "epoch": 0.6127659574468085,
      "grad_norm": 1.475780206398884,
      "learning_rate": 4.8164707832976783e-05,
      "loss": 1.464,
      "num_input_tokens_seen": 14155776,
      "step": 54
    },
    {
      "epoch": 0.624113475177305,
      "grad_norm": 1.4112950034248575,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 1.445,
      "num_input_tokens_seen": 14417920,
      "step": 55
    },
    {
      "epoch": 0.6354609929078014,
      "grad_norm": 1.6206014969548581,
      "learning_rate": 4.802809132787125e-05,
      "loss": 1.45,
      "num_input_tokens_seen": 14680064,
      "step": 56
    },
    {
      "epoch": 0.6468085106382979,
      "grad_norm": 1.2999206377427606,
      "learning_rate": 4.7958020390553426e-05,
      "loss": 1.4923,
      "num_input_tokens_seen": 14942208,
      "step": 57
    },
    {
      "epoch": 0.6581560283687943,
      "grad_norm": 1.2629239809770683,
      "learning_rate": 4.7886779072985156e-05,
      "loss": 1.4459,
      "num_input_tokens_seen": 15204352,
      "step": 58
    },
    {
      "epoch": 0.6695035460992907,
      "grad_norm": 1.6115720276042818,
      "learning_rate": 4.78143710069879e-05,
      "loss": 1.4211,
      "num_input_tokens_seen": 15466496,
      "step": 59
    },
    {
      "epoch": 0.6808510638297872,
      "grad_norm": 1.3564661495186316,
      "learning_rate": 4.774079988386296e-05,
      "loss": 1.4354,
      "num_input_tokens_seen": 15728640,
      "step": 60
    },
    {
      "epoch": 0.6921985815602837,
      "grad_norm": 1.4029089027053228,
      "learning_rate": 4.766606945420329e-05,
      "loss": 1.4552,
      "num_input_tokens_seen": 15990784,
      "step": 61
    },
    {
      "epoch": 0.7035460992907802,
      "grad_norm": 1.609508929492919,
      "learning_rate": 4.759018352770229e-05,
      "loss": 1.4401,
      "num_input_tokens_seen": 16252928,
      "step": 62
    },
    {
      "epoch": 0.7148936170212766,
      "grad_norm": 1.5314498833493546,
      "learning_rate": 4.751314597295963e-05,
      "loss": 1.4717,
      "num_input_tokens_seen": 16515072,
      "step": 63
    },
    {
      "epoch": 0.7262411347517731,
      "grad_norm": 1.4584944515244869,
      "learning_rate": 4.743496071728396e-05,
      "loss": 1.4372,
      "num_input_tokens_seen": 16777216,
      "step": 64
    },
    {
      "epoch": 0.7375886524822695,
      "grad_norm": 1.3848187202296613,
      "learning_rate": 4.735563174649278e-05,
      "loss": 1.4222,
      "num_input_tokens_seen": 17039360,
      "step": 65
    },
    {
      "epoch": 0.7489361702127659,
      "grad_norm": 1.322399845197604,
      "learning_rate": 4.72751631047092e-05,
      "loss": 1.4328,
      "num_input_tokens_seen": 17301504,
      "step": 66
    },
    {
      "epoch": 0.7602836879432624,
      "grad_norm": 1.2041955676624019,
      "learning_rate": 4.719355889415576e-05,
      "loss": 1.4133,
      "num_input_tokens_seen": 17563648,
      "step": 67
    },
    {
      "epoch": 0.7716312056737589,
      "grad_norm": 1.4025507710172729,
      "learning_rate": 4.711082327494536e-05,
      "loss": 1.4239,
      "num_input_tokens_seen": 17825792,
      "step": 68
    },
    {
      "epoch": 0.7829787234042553,
      "grad_norm": 1.5777455822322792,
      "learning_rate": 4.7026960464869116e-05,
      "loss": 1.437,
      "num_input_tokens_seen": 18087936,
      "step": 69
    },
    {
      "epoch": 0.7943262411347518,
      "grad_norm": 1.3436386092926063,
      "learning_rate": 4.6941974739181395e-05,
      "loss": 1.4243,
      "num_input_tokens_seen": 18350080,
      "step": 70
    },
    {
      "epoch": 0.8056737588652483,
      "grad_norm": 1.7031338750612581,
      "learning_rate": 4.6855870430381816e-05,
      "loss": 1.4272,
      "num_input_tokens_seen": 18612224,
      "step": 71
    },
    {
      "epoch": 0.8170212765957446,
      "grad_norm": 1.3269888785525612,
      "learning_rate": 4.6768651927994434e-05,
      "loss": 1.4054,
      "num_input_tokens_seen": 18874368,
      "step": 72
    },
    {
      "epoch": 0.8283687943262411,
      "grad_norm": 1.4476048219302555,
      "learning_rate": 4.668032367834392e-05,
      "loss": 1.413,
      "num_input_tokens_seen": 19136512,
      "step": 73
    },
    {
      "epoch": 0.8397163120567376,
      "grad_norm": 1.4535317388744813,
      "learning_rate": 4.6590890184328925e-05,
      "loss": 1.4054,
      "num_input_tokens_seen": 19398656,
      "step": 74
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 1.2269074929733113,
      "learning_rate": 4.6500356005192514e-05,
      "loss": 1.3898,
      "num_input_tokens_seen": 19660800,
      "step": 75
    },
    {
      "epoch": 0.8624113475177305,
      "grad_norm": 1.3008326960072658,
      "learning_rate": 4.640872575628973e-05,
      "loss": 1.4042,
      "num_input_tokens_seen": 19922944,
      "step": 76
    },
    {
      "epoch": 0.873758865248227,
      "grad_norm": 1.2343345399913839,
      "learning_rate": 4.6316004108852305e-05,
      "loss": 1.4181,
      "num_input_tokens_seen": 20185088,
      "step": 77
    },
    {
      "epoch": 0.8851063829787233,
      "grad_norm": 1.40051458320969,
      "learning_rate": 4.622219578975057e-05,
      "loss": 1.3986,
      "num_input_tokens_seen": 20447232,
      "step": 78
    },
    {
      "epoch": 0.8964539007092198,
      "grad_norm": 1.2497430360048092,
      "learning_rate": 4.6127305581252414e-05,
      "loss": 1.3769,
      "num_input_tokens_seen": 20709376,
      "step": 79
    },
    {
      "epoch": 0.9078014184397163,
      "grad_norm": 1.2431538833258515,
      "learning_rate": 4.6031338320779534e-05,
      "loss": 1.4002,
      "num_input_tokens_seen": 20971520,
      "step": 80
    },
    {
      "epoch": 0.9191489361702128,
      "grad_norm": 1.0814373534222335,
      "learning_rate": 4.593429890066082e-05,
      "loss": 1.4156,
      "num_input_tokens_seen": 21233664,
      "step": 81
    },
    {
      "epoch": 0.9304964539007092,
      "grad_norm": 1.115346242762015,
      "learning_rate": 4.583619226788294e-05,
      "loss": 1.3867,
      "num_input_tokens_seen": 21495808,
      "step": 82
    },
    {
      "epoch": 0.9418439716312057,
      "grad_norm": 1.2127601722053167,
      "learning_rate": 4.573702342383816e-05,
      "loss": 1.3751,
      "num_input_tokens_seen": 21757952,
      "step": 83
    },
    {
      "epoch": 0.9531914893617022,
      "grad_norm": 1.1748214200248,
      "learning_rate": 4.563679742406935e-05,
      "loss": 1.3834,
      "num_input_tokens_seen": 22020096,
      "step": 84
    },
    {
      "epoch": 0.9645390070921985,
      "grad_norm": 1.1331339281580772,
      "learning_rate": 4.5535519378012295e-05,
      "loss": 1.3791,
      "num_input_tokens_seen": 22282240,
      "step": 85
    },
    {
      "epoch": 0.975886524822695,
      "grad_norm": 1.4004411805319554,
      "learning_rate": 4.543319444873517e-05,
      "loss": 1.3785,
      "num_input_tokens_seen": 22544384,
      "step": 86
    },
    {
      "epoch": 0.9872340425531915,
      "grad_norm": 1.2118340365527955,
      "learning_rate": 4.532982785267541e-05,
      "loss": 1.3635,
      "num_input_tokens_seen": 22806528,
      "step": 87
    },
    {
      "epoch": 0.9985815602836879,
      "grad_norm": 1.5899548683498645,
      "learning_rate": 4.522542485937369e-05,
      "loss": 1.3879,
      "num_input_tokens_seen": 23068672,
      "step": 88
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.5899548683498645,
      "learning_rate": 4.511999079120534e-05,
      "loss": 1.2364,
      "num_input_tokens_seen": 23101440,
      "step": 89
    },
    {
      "epoch": 1.0113475177304965,
      "grad_norm": 3.1471576605311427,
      "learning_rate": 4.5013531023109014e-05,
      "loss": 1.0204,
      "num_input_tokens_seen": 23363584,
      "step": 90
    },
    {
      "epoch": 1.022695035460993,
      "grad_norm": 1.9813456886904501,
      "learning_rate": 4.4906050982312664e-05,
      "loss": 1.0799,
      "num_input_tokens_seen": 23625728,
      "step": 91
    },
    {
      "epoch": 1.0340425531914894,
      "grad_norm": 1.7175351501466867,
      "learning_rate": 4.479755614805688e-05,
      "loss": 1.0052,
      "num_input_tokens_seen": 23887872,
      "step": 92
    },
    {
      "epoch": 1.0453900709219859,
      "grad_norm": 1.970342186079611,
      "learning_rate": 4.4688052051315545e-05,
      "loss": 1.0531,
      "num_input_tokens_seen": 24150016,
      "step": 93
    },
    {
      "epoch": 1.0567375886524824,
      "grad_norm": 1.7872662354821134,
      "learning_rate": 4.457754427451389e-05,
      "loss": 1.0159,
      "num_input_tokens_seen": 24412160,
      "step": 94
    },
    {
      "epoch": 1.0680851063829788,
      "grad_norm": 1.8666514589785563,
      "learning_rate": 4.446603845124388e-05,
      "loss": 0.9947,
      "num_input_tokens_seen": 24674304,
      "step": 95
    },
    {
      "epoch": 1.0794326241134753,
      "grad_norm": 1.5777077629921268,
      "learning_rate": 4.4353540265977064e-05,
      "loss": 0.9969,
      "num_input_tokens_seen": 24936448,
      "step": 96
    },
    {
      "epoch": 1.0907801418439715,
      "grad_norm": 1.4442562002627628,
      "learning_rate": 4.4240055453774734e-05,
      "loss": 1.02,
      "num_input_tokens_seen": 25198592,
      "step": 97
    },
    {
      "epoch": 1.102127659574468,
      "grad_norm": 1.6801959052168647,
      "learning_rate": 4.412558979999558e-05,
      "loss": 0.9789,
      "num_input_tokens_seen": 25460736,
      "step": 98
    },
    {
      "epoch": 1.1134751773049645,
      "grad_norm": 1.3983076558719154,
      "learning_rate": 4.401014914000078e-05,
      "loss": 1.0035,
      "num_input_tokens_seen": 25722880,
      "step": 99
    },
    {
      "epoch": 1.124822695035461,
      "grad_norm": 1.4068549353820048,
      "learning_rate": 4.389373935885646e-05,
      "loss": 0.9751,
      "num_input_tokens_seen": 25985024,
      "step": 100
    },
    {
      "epoch": 1.1361702127659574,
      "grad_norm": 1.4162325676250134,
      "learning_rate": 4.3776366391033746e-05,
      "loss": 0.9464,
      "num_input_tokens_seen": 26247168,
      "step": 101
    },
    {
      "epoch": 1.147517730496454,
      "grad_norm": 1.3675197337363096,
      "learning_rate": 4.365803622010618e-05,
      "loss": 0.9592,
      "num_input_tokens_seen": 26509312,
      "step": 102
    },
    {
      "epoch": 1.1588652482269504,
      "grad_norm": 1.5007646821184917,
      "learning_rate": 4.35387548784447e-05,
      "loss": 0.9709,
      "num_input_tokens_seen": 26771456,
      "step": 103
    },
    {
      "epoch": 1.1702127659574468,
      "grad_norm": 1.4773281381482295,
      "learning_rate": 4.341852844691012e-05,
      "loss": 0.9834,
      "num_input_tokens_seen": 27033600,
      "step": 104
    },
    {
      "epoch": 1.1815602836879433,
      "grad_norm": 1.933895535557616,
      "learning_rate": 4.329736305454314e-05,
      "loss": 0.9999,
      "num_input_tokens_seen": 27295744,
      "step": 105
    },
    {
      "epoch": 1.1929078014184398,
      "grad_norm": 1.6902638904380827,
      "learning_rate": 4.3175264878251845e-05,
      "loss": 0.9294,
      "num_input_tokens_seen": 27557888,
      "step": 106
    },
    {
      "epoch": 1.2042553191489362,
      "grad_norm": 1.696391072445269,
      "learning_rate": 4.305224014249688e-05,
      "loss": 0.9906,
      "num_input_tokens_seen": 27820032,
      "step": 107
    },
    {
      "epoch": 1.2156028368794327,
      "grad_norm": 1.7162350808896498,
      "learning_rate": 4.292829511897409e-05,
      "loss": 0.9731,
      "num_input_tokens_seen": 28082176,
      "step": 108
    },
    {
      "epoch": 1.226950354609929,
      "grad_norm": 1.736567992601448,
      "learning_rate": 4.280343612629479e-05,
      "loss": 0.978,
      "num_input_tokens_seen": 28344320,
      "step": 109
    },
    {
      "epoch": 1.2382978723404254,
      "grad_norm": 1.3602272146940024,
      "learning_rate": 4.267766952966369e-05,
      "loss": 0.9325,
      "num_input_tokens_seen": 28606464,
      "step": 110
    },
    {
      "epoch": 1.249645390070922,
      "grad_norm": 1.5745245166339177,
      "learning_rate": 4.255100174055434e-05,
      "loss": 0.9657,
      "num_input_tokens_seen": 28868608,
      "step": 111
    },
    {
      "epoch": 1.2609929078014184,
      "grad_norm": 1.3239840597482868,
      "learning_rate": 4.242343921638234e-05,
      "loss": 0.9451,
      "num_input_tokens_seen": 29130752,
      "step": 112
    },
    {
      "epoch": 1.2723404255319148,
      "grad_norm": 1.392428377159933,
      "learning_rate": 4.22949884601761e-05,
      "loss": 0.9632,
      "num_input_tokens_seen": 29392896,
      "step": 113
    },
    {
      "epoch": 1.2836879432624113,
      "grad_norm": 1.382581854515865,
      "learning_rate": 4.2165656020245336e-05,
      "loss": 0.9483,
      "num_input_tokens_seen": 29655040,
      "step": 114
    },
    {
      "epoch": 1.2950354609929078,
      "grad_norm": 1.5462756056089444,
      "learning_rate": 4.2035448489847284e-05,
      "loss": 0.9899,
      "num_input_tokens_seen": 29917184,
      "step": 115
    },
    {
      "epoch": 1.3063829787234043,
      "grad_norm": 1.4147640794435994,
      "learning_rate": 4.1904372506850484e-05,
      "loss": 0.9092,
      "num_input_tokens_seen": 30179328,
      "step": 116
    },
    {
      "epoch": 1.3177304964539007,
      "grad_norm": 1.2432801814071204,
      "learning_rate": 4.1772434753396504e-05,
      "loss": 0.9501,
      "num_input_tokens_seen": 30441472,
      "step": 117
    },
    {
      "epoch": 1.3290780141843972,
      "grad_norm": 1.4932728466362941,
      "learning_rate": 4.1639641955559205e-05,
      "loss": 1.0093,
      "num_input_tokens_seen": 30703616,
      "step": 118
    },
    {
      "epoch": 1.3404255319148937,
      "grad_norm": 1.146394031379382,
      "learning_rate": 4.1506000883001875e-05,
      "loss": 0.95,
      "num_input_tokens_seen": 30965760,
      "step": 119
    },
    {
      "epoch": 1.3517730496453901,
      "grad_norm": 1.314570904504416,
      "learning_rate": 4.137151834863213e-05,
      "loss": 0.9733,
      "num_input_tokens_seen": 31227904,
      "step": 120
    },
    {
      "epoch": 1.3631205673758866,
      "grad_norm": 1.144532383386255,
      "learning_rate": 4.123620120825459e-05,
      "loss": 0.9503,
      "num_input_tokens_seen": 31490048,
      "step": 121
    },
    {
      "epoch": 1.374468085106383,
      "grad_norm": 1.407081639684963,
      "learning_rate": 4.1100056360221384e-05,
      "loss": 0.9787,
      "num_input_tokens_seen": 31752192,
      "step": 122
    },
    {
      "epoch": 1.3858156028368795,
      "grad_norm": 1.1478616889934938,
      "learning_rate": 4.096309074508046e-05,
      "loss": 0.9697,
      "num_input_tokens_seen": 32014336,
      "step": 123
    },
    {
      "epoch": 1.397163120567376,
      "grad_norm": 1.1798657684361409,
      "learning_rate": 4.082531134522176e-05,
      "loss": 0.9397,
      "num_input_tokens_seen": 32276480,
      "step": 124
    },
    {
      "epoch": 1.4085106382978723,
      "grad_norm": 1.1170685676293548,
      "learning_rate": 4.06867251845213e-05,
      "loss": 0.9466,
      "num_input_tokens_seen": 32538624,
      "step": 125
    },
    {
      "epoch": 1.4198581560283687,
      "grad_norm": 1.158583040981931,
      "learning_rate": 4.054733932798306e-05,
      "loss": 0.9517,
      "num_input_tokens_seen": 32800768,
      "step": 126
    },
    {
      "epoch": 1.4312056737588652,
      "grad_norm": 1.1206965982137238,
      "learning_rate": 4.0407160881378824e-05,
      "loss": 0.9299,
      "num_input_tokens_seen": 33062912,
      "step": 127
    },
    {
      "epoch": 1.4425531914893617,
      "grad_norm": 1.2166341082803098,
      "learning_rate": 4.0266196990885955e-05,
      "loss": 0.9674,
      "num_input_tokens_seen": 33325056,
      "step": 128
    },
    {
      "epoch": 1.4539007092198581,
      "grad_norm": 1.253313105155196,
      "learning_rate": 4.012445484272307e-05,
      "loss": 0.935,
      "num_input_tokens_seen": 33587200,
      "step": 129
    },
    {
      "epoch": 1.4652482269503546,
      "grad_norm": 1.1241425426902512,
      "learning_rate": 3.9981941662783674e-05,
      "loss": 0.9856,
      "num_input_tokens_seen": 33849344,
      "step": 130
    },
    {
      "epoch": 1.476595744680851,
      "grad_norm": 1.2496739496083311,
      "learning_rate": 3.9838664716267855e-05,
      "loss": 0.95,
      "num_input_tokens_seen": 34111488,
      "step": 131
    },
    {
      "epoch": 1.4879432624113476,
      "grad_norm": 1.2413295026999056,
      "learning_rate": 3.969463130731183e-05,
      "loss": 1.0095,
      "num_input_tokens_seen": 34373632,
      "step": 132
    },
    {
      "epoch": 1.499290780141844,
      "grad_norm": 1.0994149236511626,
      "learning_rate": 3.954984877861565e-05,
      "loss": 0.9711,
      "num_input_tokens_seen": 34635776,
      "step": 133
    },
    {
      "epoch": 1.5106382978723403,
      "grad_norm": 1.2204241140248873,
      "learning_rate": 3.9404324511068825e-05,
      "loss": 1.0004,
      "num_input_tokens_seen": 34897920,
      "step": 134
    },
    {
      "epoch": 1.5219858156028367,
      "grad_norm": 1.0639734593664278,
      "learning_rate": 3.92580659233741e-05,
      "loss": 0.9683,
      "num_input_tokens_seen": 35160064,
      "step": 135
    },
    {
      "epoch": 1.5333333333333332,
      "grad_norm": 1.286928460200864,
      "learning_rate": 3.911108047166924e-05,
      "loss": 0.9735,
      "num_input_tokens_seen": 35422208,
      "step": 136
    },
    {
      "epoch": 1.5446808510638297,
      "grad_norm": 1.1776256536499852,
      "learning_rate": 3.8963375649146866e-05,
      "loss": 0.9917,
      "num_input_tokens_seen": 35684352,
      "step": 137
    },
    {
      "epoch": 1.5560283687943262,
      "grad_norm": 1.1927233327599214,
      "learning_rate": 3.881495898567257e-05,
      "loss": 0.9585,
      "num_input_tokens_seen": 35946496,
      "step": 138
    },
    {
      "epoch": 1.5673758865248226,
      "grad_norm": 1.1616205054974948,
      "learning_rate": 3.866583804740095e-05,
      "loss": 0.9305,
      "num_input_tokens_seen": 36208640,
      "step": 139
    },
    {
      "epoch": 1.578723404255319,
      "grad_norm": 1.1608542297205653,
      "learning_rate": 3.851602043638994e-05,
      "loss": 0.9738,
      "num_input_tokens_seen": 36470784,
      "step": 140
    },
    {
      "epoch": 1.5900709219858156,
      "grad_norm": 1.1754828045051902,
      "learning_rate": 3.8365513790213265e-05,
      "loss": 0.9627,
      "num_input_tokens_seen": 36732928,
      "step": 141
    },
    {
      "epoch": 1.601418439716312,
      "grad_norm": 1.2412851531549465,
      "learning_rate": 3.821432578157105e-05,
      "loss": 0.9673,
      "num_input_tokens_seen": 36995072,
      "step": 142
    },
    {
      "epoch": 1.6127659574468085,
      "grad_norm": 1.1681668630687394,
      "learning_rate": 3.8062464117898724e-05,
      "loss": 0.9908,
      "num_input_tokens_seen": 37257216,
      "step": 143
    },
    {
      "epoch": 1.624113475177305,
      "grad_norm": 1.1771959095169333,
      "learning_rate": 3.790993654097405e-05,
      "loss": 0.9913,
      "num_input_tokens_seen": 37519360,
      "step": 144
    },
    {
      "epoch": 1.6354609929078014,
      "grad_norm": 1.2334490161088576,
      "learning_rate": 3.77567508265225e-05,
      "loss": 0.9911,
      "num_input_tokens_seen": 37781504,
      "step": 145
    },
    {
      "epoch": 1.646808510638298,
      "grad_norm": 1.132776925570845,
      "learning_rate": 3.76029147838208e-05,
      "loss": 0.9801,
      "num_input_tokens_seen": 38043648,
      "step": 146
    },
    {
      "epoch": 1.6581560283687944,
      "grad_norm": 1.2852017625106646,
      "learning_rate": 3.74484362552989e-05,
      "loss": 0.9725,
      "num_input_tokens_seen": 38305792,
      "step": 147
    },
    {
      "epoch": 1.6695035460992909,
      "grad_norm": 1.1423632361464884,
      "learning_rate": 3.72933231161401e-05,
      "loss": 0.961,
      "num_input_tokens_seen": 38567936,
      "step": 148
    },
    {
      "epoch": 1.6808510638297873,
      "grad_norm": 1.1887510715530398,
      "learning_rate": 3.713758327387961e-05,
      "loss": 0.944,
      "num_input_tokens_seen": 38830080,
      "step": 149
    },
    {
      "epoch": 1.6921985815602838,
      "grad_norm": 1.2005973709528561,
      "learning_rate": 3.6981224668001424e-05,
      "loss": 0.9855,
      "num_input_tokens_seen": 39092224,
      "step": 150
    },
    {
      "epoch": 1.7035460992907803,
      "grad_norm": 1.1796966769071517,
      "learning_rate": 3.682425526953359e-05,
      "loss": 0.9785,
      "num_input_tokens_seen": 39354368,
      "step": 151
    },
    {
      "epoch": 1.7148936170212767,
      "grad_norm": 1.1401769784499336,
      "learning_rate": 3.6666683080641846e-05,
      "loss": 0.9509,
      "num_input_tokens_seen": 39616512,
      "step": 152
    },
    {
      "epoch": 1.7262411347517732,
      "grad_norm": 1.2720626628857692,
      "learning_rate": 3.6508516134221635e-05,
      "loss": 0.965,
      "num_input_tokens_seen": 39878656,
      "step": 153
    },
    {
      "epoch": 1.7375886524822695,
      "grad_norm": 1.1887836841186321,
      "learning_rate": 3.634976249348867e-05,
      "loss": 0.9737,
      "num_input_tokens_seen": 40140800,
      "step": 154
    },
    {
      "epoch": 1.748936170212766,
      "grad_norm": 1.2318081552834408,
      "learning_rate": 3.619043025156782e-05,
      "loss": 0.947,
      "num_input_tokens_seen": 40402944,
      "step": 155
    },
    {
      "epoch": 1.7602836879432624,
      "grad_norm": 1.0371027068087095,
      "learning_rate": 3.603052753108053e-05,
      "loss": 0.9782,
      "num_input_tokens_seen": 40665088,
      "step": 156
    },
    {
      "epoch": 1.7716312056737589,
      "grad_norm": 1.2582450073527114,
      "learning_rate": 3.58700624837308e-05,
      "loss": 0.9852,
      "num_input_tokens_seen": 40927232,
      "step": 157
    },
    {
      "epoch": 1.7829787234042553,
      "grad_norm": 1.159400337663857,
      "learning_rate": 3.5709043289889536e-05,
      "loss": 0.9779,
      "num_input_tokens_seen": 41189376,
      "step": 158
    },
    {
      "epoch": 1.7943262411347518,
      "grad_norm": 1.1094376112354303,
      "learning_rate": 3.554747815817756e-05,
      "loss": 0.9958,
      "num_input_tokens_seen": 41451520,
      "step": 159
    },
    {
      "epoch": 1.8056737588652483,
      "grad_norm": 1.2198757703909164,
      "learning_rate": 3.5385375325047166e-05,
      "loss": 0.9784,
      "num_input_tokens_seen": 41713664,
      "step": 160
    },
    {
      "epoch": 1.8170212765957445,
      "grad_norm": 1.0480308860957073,
      "learning_rate": 3.522274305436217e-05,
      "loss": 0.9644,
      "num_input_tokens_seen": 41975808,
      "step": 161
    },
    {
      "epoch": 1.828368794326241,
      "grad_norm": 1.1883804521566375,
      "learning_rate": 3.50595896369767e-05,
      "loss": 0.9513,
      "num_input_tokens_seen": 42237952,
      "step": 162
    },
    {
      "epoch": 1.8397163120567375,
      "grad_norm": 1.1041573287946038,
      "learning_rate": 3.4895923390312466e-05,
      "loss": 0.9935,
      "num_input_tokens_seen": 42500096,
      "step": 163
    },
    {
      "epoch": 1.851063829787234,
      "grad_norm": 1.0322154463171043,
      "learning_rate": 3.4731752657934794e-05,
      "loss": 1.0127,
      "num_input_tokens_seen": 42762240,
      "step": 164
    },
    {
      "epoch": 1.8624113475177304,
      "grad_norm": 1.210272229526448,
      "learning_rate": 3.456708580912725e-05,
      "loss": 0.94,
      "num_input_tokens_seen": 43024384,
      "step": 165
    },
    {
      "epoch": 1.8737588652482269,
      "grad_norm": 1.1397057549276046,
      "learning_rate": 3.4401931238464994e-05,
      "loss": 1.0017,
      "num_input_tokens_seen": 43286528,
      "step": 166
    },
    {
      "epoch": 1.8851063829787233,
      "grad_norm": 1.052990158347976,
      "learning_rate": 3.423629736538685e-05,
      "loss": 0.9705,
      "num_input_tokens_seen": 43548672,
      "step": 167
    },
    {
      "epoch": 1.8964539007092198,
      "grad_norm": 1.247482706002507,
      "learning_rate": 3.4070192633766025e-05,
      "loss": 0.9841,
      "num_input_tokens_seen": 43810816,
      "step": 168
    },
    {
      "epoch": 1.9078014184397163,
      "grad_norm": 1.1048483913646374,
      "learning_rate": 3.390362551147974e-05,
      "loss": 0.9737,
      "num_input_tokens_seen": 44072960,
      "step": 169
    },
    {
      "epoch": 1.9191489361702128,
      "grad_norm": 1.0770863251176332,
      "learning_rate": 3.3736604489977466e-05,
      "loss": 1.0008,
      "num_input_tokens_seen": 44335104,
      "step": 170
    },
    {
      "epoch": 1.9304964539007092,
      "grad_norm": 1.130827655449932,
      "learning_rate": 3.356913808384807e-05,
      "loss": 0.9726,
      "num_input_tokens_seen": 44597248,
      "step": 171
    },
    {
      "epoch": 1.9418439716312057,
      "grad_norm": 1.0722010665917157,
      "learning_rate": 3.3401234830385756e-05,
      "loss": 0.9711,
      "num_input_tokens_seen": 44859392,
      "step": 172
    },
    {
      "epoch": 1.9531914893617022,
      "grad_norm": 1.1584145820517182,
      "learning_rate": 3.323290328915483e-05,
      "loss": 0.9989,
      "num_input_tokens_seen": 45121536,
      "step": 173
    },
    {
      "epoch": 1.9645390070921986,
      "grad_norm": 1.0846738851387514,
      "learning_rate": 3.306415204155335e-05,
      "loss": 0.9588,
      "num_input_tokens_seen": 45383680,
      "step": 174
    },
    {
      "epoch": 1.9758865248226951,
      "grad_norm": 1.102142271317201,
      "learning_rate": 3.2894989690375626e-05,
      "loss": 0.9476,
      "num_input_tokens_seen": 45645824,
      "step": 175
    },
    {
      "epoch": 1.9872340425531916,
      "grad_norm": 1.2026725696126155,
      "learning_rate": 3.272542485937369e-05,
      "loss": 0.9606,
      "num_input_tokens_seen": 45907968,
      "step": 176
    },
    {
      "epoch": 1.998581560283688,
      "grad_norm": 1.2427515943863843,
      "learning_rate": 3.255546619281765e-05,
      "loss": 1.0062,
      "num_input_tokens_seen": 46170112,
      "step": 177
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.2427515943863843,
      "learning_rate": 3.2385122355055005e-05,
      "loss": 0.7789,
      "num_input_tokens_seen": 46202880,
      "step": 178
    },
    {
      "epoch": 2.0113475177304965,
      "grad_norm": 3.9851861322995004,
      "learning_rate": 3.221440203006897e-05,
      "loss": 0.5235,
      "num_input_tokens_seen": 46465024,
      "step": 179
    },
    {
      "epoch": 2.022695035460993,
      "grad_norm": 2.782182214592954,
      "learning_rate": 3.2043313921035743e-05,
      "loss": 0.5097,
      "num_input_tokens_seen": 46727168,
      "step": 180
    },
    {
      "epoch": 2.0340425531914894,
      "grad_norm": 1.8270642765269718,
      "learning_rate": 3.1871866749880846e-05,
      "loss": 0.4839,
      "num_input_tokens_seen": 46989312,
      "step": 181
    },
    {
      "epoch": 2.045390070921986,
      "grad_norm": 3.7339811640972473,
      "learning_rate": 3.170006925683448e-05,
      "loss": 0.4825,
      "num_input_tokens_seen": 47251456,
      "step": 182
    },
    {
      "epoch": 2.0567375886524824,
      "grad_norm": 2.9941865165214754,
      "learning_rate": 3.152793019998594e-05,
      "loss": 0.4497,
      "num_input_tokens_seen": 47513600,
      "step": 183
    },
    {
      "epoch": 2.068085106382979,
      "grad_norm": 1.8964492803313993,
      "learning_rate": 3.135545835483718e-05,
      "loss": 0.4443,
      "num_input_tokens_seen": 47775744,
      "step": 184
    },
    {
      "epoch": 2.0794326241134753,
      "grad_norm": 1.6098003889750838,
      "learning_rate": 3.118266251385539e-05,
      "loss": 0.4355,
      "num_input_tokens_seen": 48037888,
      "step": 185
    },
    {
      "epoch": 2.0907801418439718,
      "grad_norm": 1.523263157923423,
      "learning_rate": 3.100955148602481e-05,
      "loss": 0.4265,
      "num_input_tokens_seen": 48300032,
      "step": 186
    },
    {
      "epoch": 2.1021276595744682,
      "grad_norm": 1.3639153937211606,
      "learning_rate": 3.083613409639764e-05,
      "loss": 0.4058,
      "num_input_tokens_seen": 48562176,
      "step": 187
    },
    {
      "epoch": 2.1134751773049647,
      "grad_norm": 1.370922535424333,
      "learning_rate": 3.0662419185644115e-05,
      "loss": 0.4004,
      "num_input_tokens_seen": 48824320,
      "step": 188
    },
    {
      "epoch": 2.124822695035461,
      "grad_norm": 1.440676408033895,
      "learning_rate": 3.0488415609601862e-05,
      "loss": 0.389,
      "num_input_tokens_seen": 49086464,
      "step": 189
    },
    {
      "epoch": 2.1361702127659576,
      "grad_norm": 1.310285355956054,
      "learning_rate": 3.0314132238824415e-05,
      "loss": 0.404,
      "num_input_tokens_seen": 49348608,
      "step": 190
    },
    {
      "epoch": 2.147517730496454,
      "grad_norm": 1.4941784665076816,
      "learning_rate": 3.013957795812902e-05,
      "loss": 0.382,
      "num_input_tokens_seen": 49610752,
      "step": 191
    },
    {
      "epoch": 2.1588652482269506,
      "grad_norm": 1.4030391388098873,
      "learning_rate": 2.996476166614364e-05,
      "loss": 0.3788,
      "num_input_tokens_seen": 49872896,
      "step": 192
    },
    {
      "epoch": 2.1702127659574466,
      "grad_norm": 1.256129131429154,
      "learning_rate": 2.9789692274853388e-05,
      "loss": 0.3925,
      "num_input_tokens_seen": 50135040,
      "step": 193
    },
    {
      "epoch": 2.181560283687943,
      "grad_norm": 1.4558080899884718,
      "learning_rate": 2.9614378709146133e-05,
      "loss": 0.3868,
      "num_input_tokens_seen": 50397184,
      "step": 194
    },
    {
      "epoch": 2.1929078014184396,
      "grad_norm": 1.250507734486578,
      "learning_rate": 2.943882990635759e-05,
      "loss": 0.3775,
      "num_input_tokens_seen": 50659328,
      "step": 195
    },
    {
      "epoch": 2.204255319148936,
      "grad_norm": 1.2741202231518605,
      "learning_rate": 2.92630548158156e-05,
      "loss": 0.3897,
      "num_input_tokens_seen": 50921472,
      "step": 196
    },
    {
      "epoch": 2.2156028368794325,
      "grad_norm": 1.2133688441052128,
      "learning_rate": 2.9087062398384e-05,
      "loss": 0.3644,
      "num_input_tokens_seen": 51183616,
      "step": 197
    },
    {
      "epoch": 2.226950354609929,
      "grad_norm": 1.1909730406616328,
      "learning_rate": 2.8910861626005776e-05,
      "loss": 0.3933,
      "num_input_tokens_seen": 51445760,
      "step": 198
    },
    {
      "epoch": 2.2382978723404254,
      "grad_norm": 1.1826769961907178,
      "learning_rate": 2.873446148124563e-05,
      "loss": 0.4031,
      "num_input_tokens_seen": 51707904,
      "step": 199
    },
    {
      "epoch": 2.249645390070922,
      "grad_norm": 1.2503503019173514,
      "learning_rate": 2.8557870956832132e-05,
      "loss": 0.3774,
      "num_input_tokens_seen": 51970048,
      "step": 200
    },
    {
      "epoch": 2.2609929078014184,
      "grad_norm": 1.1228352195116507,
      "learning_rate": 2.8381099055199222e-05,
      "loss": 0.396,
      "num_input_tokens_seen": 52232192,
      "step": 201
    },
    {
      "epoch": 2.272340425531915,
      "grad_norm": 1.2833412130464927,
      "learning_rate": 2.8204154788027325e-05,
      "loss": 0.3589,
      "num_input_tokens_seen": 52494336,
      "step": 202
    },
    {
      "epoch": 2.2836879432624113,
      "grad_norm": 1.1493157288933067,
      "learning_rate": 2.8027047175783873e-05,
      "loss": 0.36,
      "num_input_tokens_seen": 52756480,
      "step": 203
    },
    {
      "epoch": 2.295035460992908,
      "grad_norm": 1.2057679652659834,
      "learning_rate": 2.7849785247263515e-05,
      "loss": 0.3938,
      "num_input_tokens_seen": 53018624,
      "step": 204
    },
    {
      "epoch": 2.3063829787234043,
      "grad_norm": 1.2859581898852654,
      "learning_rate": 2.767237803912783e-05,
      "loss": 0.4006,
      "num_input_tokens_seen": 53280768,
      "step": 205
    },
    {
      "epoch": 2.3177304964539007,
      "grad_norm": 1.2255059859165218,
      "learning_rate": 2.7494834595444568e-05,
      "loss": 0.3798,
      "num_input_tokens_seen": 53542912,
      "step": 206
    },
    {
      "epoch": 2.329078014184397,
      "grad_norm": 1.1213649523858145,
      "learning_rate": 2.731716396722672e-05,
      "loss": 0.3806,
      "num_input_tokens_seen": 53805056,
      "step": 207
    },
    {
      "epoch": 2.3404255319148937,
      "grad_norm": 1.215408045504973,
      "learning_rate": 2.7139375211970996e-05,
      "loss": 0.3794,
      "num_input_tokens_seen": 54067200,
      "step": 208
    },
    {
      "epoch": 2.35177304964539,
      "grad_norm": 1.1823599565086842,
      "learning_rate": 2.6961477393196126e-05,
      "loss": 0.3836,
      "num_input_tokens_seen": 54329344,
      "step": 209
    },
    {
      "epoch": 2.3631205673758866,
      "grad_norm": 1.1340883173812746,
      "learning_rate": 2.6783479579980807e-05,
      "loss": 0.3769,
      "num_input_tokens_seen": 54591488,
      "step": 210
    },
    {
      "epoch": 2.374468085106383,
      "grad_norm": 1.2066922550248658,
      "learning_rate": 2.6605390846501377e-05,
      "loss": 0.3854,
      "num_input_tokens_seen": 54853632,
      "step": 211
    },
    {
      "epoch": 2.3858156028368795,
      "grad_norm": 1.2171750570169015,
      "learning_rate": 2.6427220271569203e-05,
      "loss": 0.3872,
      "num_input_tokens_seen": 55115776,
      "step": 212
    },
    {
      "epoch": 2.397163120567376,
      "grad_norm": 1.154268662146649,
      "learning_rate": 2.624897693816785e-05,
      "loss": 0.3877,
      "num_input_tokens_seen": 55377920,
      "step": 213
    },
    {
      "epoch": 2.4085106382978725,
      "grad_norm": 1.1755024157603309,
      "learning_rate": 2.6070669932990067e-05,
      "loss": 0.3839,
      "num_input_tokens_seen": 55640064,
      "step": 214
    },
    {
      "epoch": 2.419858156028369,
      "grad_norm": 1.2230171275187467,
      "learning_rate": 2.5892308345974515e-05,
      "loss": 0.3765,
      "num_input_tokens_seen": 55902208,
      "step": 215
    },
    {
      "epoch": 2.4312056737588654,
      "grad_norm": 1.1601360552600042,
      "learning_rate": 2.5713901269842404e-05,
      "loss": 0.3788,
      "num_input_tokens_seen": 56164352,
      "step": 216
    },
    {
      "epoch": 2.4425531914893615,
      "grad_norm": 1.2731492044445878,
      "learning_rate": 2.5535457799633955e-05,
      "loss": 0.3773,
      "num_input_tokens_seen": 56426496,
      "step": 217
    },
    {
      "epoch": 2.453900709219858,
      "grad_norm": 1.1913197047744846,
      "learning_rate": 2.5356987032244683e-05,
      "loss": 0.3741,
      "num_input_tokens_seen": 56688640,
      "step": 218
    },
    {
      "epoch": 2.4652482269503544,
      "grad_norm": 1.3734178315666306,
      "learning_rate": 2.5178498065961736e-05,
      "loss": 0.3959,
      "num_input_tokens_seen": 56950784,
      "step": 219
    },
    {
      "epoch": 2.476595744680851,
      "grad_norm": 1.2130341884336506,
      "learning_rate": 2.5e-05,
      "loss": 0.3795,
      "num_input_tokens_seen": 57212928,
      "step": 220
    },
    {
      "epoch": 2.4879432624113473,
      "grad_norm": 1.2201255253281913,
      "learning_rate": 2.4821501934038266e-05,
      "loss": 0.3643,
      "num_input_tokens_seen": 57475072,
      "step": 221
    },
    {
      "epoch": 2.499290780141844,
      "grad_norm": 1.215550219664517,
      "learning_rate": 2.4643012967755326e-05,
      "loss": 0.3926,
      "num_input_tokens_seen": 57737216,
      "step": 222
    },
    {
      "epoch": 2.5106382978723403,
      "grad_norm": 1.390476571364045,
      "learning_rate": 2.446454220036605e-05,
      "loss": 0.3904,
      "num_input_tokens_seen": 57999360,
      "step": 223
    },
    {
      "epoch": 2.5219858156028367,
      "grad_norm": 1.117871728218981,
      "learning_rate": 2.42860987301576e-05,
      "loss": 0.373,
      "num_input_tokens_seen": 58261504,
      "step": 224
    },
    {
      "epoch": 2.533333333333333,
      "grad_norm": 1.3698199224662784,
      "learning_rate": 2.410769165402549e-05,
      "loss": 0.4068,
      "num_input_tokens_seen": 58523648,
      "step": 225
    },
    {
      "epoch": 2.5446808510638297,
      "grad_norm": 1.3551110495536183,
      "learning_rate": 2.3929330067009942e-05,
      "loss": 0.3859,
      "num_input_tokens_seen": 58785792,
      "step": 226
    },
    {
      "epoch": 2.556028368794326,
      "grad_norm": 1.294001666579498,
      "learning_rate": 2.3751023061832158e-05,
      "loss": 0.3738,
      "num_input_tokens_seen": 59047936,
      "step": 227
    },
    {
      "epoch": 2.5673758865248226,
      "grad_norm": 1.2033518812521018,
      "learning_rate": 2.35727797284308e-05,
      "loss": 0.4054,
      "num_input_tokens_seen": 59310080,
      "step": 228
    },
    {
      "epoch": 2.578723404255319,
      "grad_norm": 1.3809415688054603,
      "learning_rate": 2.339460915349862e-05,
      "loss": 0.3948,
      "num_input_tokens_seen": 59572224,
      "step": 229
    },
    {
      "epoch": 2.5900709219858156,
      "grad_norm": 1.144779349719294,
      "learning_rate": 2.3216520420019195e-05,
      "loss": 0.3976,
      "num_input_tokens_seen": 59834368,
      "step": 230
    },
    {
      "epoch": 2.601418439716312,
      "grad_norm": 1.2132146253753062,
      "learning_rate": 2.303852260680388e-05,
      "loss": 0.3899,
      "num_input_tokens_seen": 60096512,
      "step": 231
    },
    {
      "epoch": 2.6127659574468085,
      "grad_norm": 1.1499252028219595,
      "learning_rate": 2.2860624788029013e-05,
      "loss": 0.4025,
      "num_input_tokens_seen": 60358656,
      "step": 232
    },
    {
      "epoch": 2.624113475177305,
      "grad_norm": 1.1403014147417394,
      "learning_rate": 2.268283603277328e-05,
      "loss": 0.3858,
      "num_input_tokens_seen": 60620800,
      "step": 233
    },
    {
      "epoch": 2.6354609929078014,
      "grad_norm": 1.13239820788593,
      "learning_rate": 2.250516540455543e-05,
      "loss": 0.3676,
      "num_input_tokens_seen": 60882944,
      "step": 234
    },
    {
      "epoch": 2.646808510638298,
      "grad_norm": 1.1982201887250508,
      "learning_rate": 2.2327621960872187e-05,
      "loss": 0.3744,
      "num_input_tokens_seen": 61145088,
      "step": 235
    },
    {
      "epoch": 2.6581560283687944,
      "grad_norm": 1.091653134615552,
      "learning_rate": 2.2150214752736488e-05,
      "loss": 0.3804,
      "num_input_tokens_seen": 61407232,
      "step": 236
    },
    {
      "epoch": 2.669503546099291,
      "grad_norm": 1.0757322285847275,
      "learning_rate": 2.197295282421613e-05,
      "loss": 0.3636,
      "num_input_tokens_seen": 61669376,
      "step": 237
    },
    {
      "epoch": 2.6808510638297873,
      "grad_norm": 1.1907618432720997,
      "learning_rate": 2.179584521197268e-05,
      "loss": 0.3836,
      "num_input_tokens_seen": 61931520,
      "step": 238
    },
    {
      "epoch": 2.692198581560284,
      "grad_norm": 1.154673483311636,
      "learning_rate": 2.1618900944800777e-05,
      "loss": 0.3797,
      "num_input_tokens_seen": 62193664,
      "step": 239
    },
    {
      "epoch": 2.7035460992907803,
      "grad_norm": 1.155175360207987,
      "learning_rate": 2.1442129043167874e-05,
      "loss": 0.3783,
      "num_input_tokens_seen": 62455808,
      "step": 240
    },
    {
      "epoch": 2.7148936170212767,
      "grad_norm": 1.2332827172317569,
      "learning_rate": 2.1265538518754374e-05,
      "loss": 0.3778,
      "num_input_tokens_seen": 62717952,
      "step": 241
    },
    {
      "epoch": 2.726241134751773,
      "grad_norm": 1.1881992350835984,
      "learning_rate": 2.1089138373994223e-05,
      "loss": 0.4034,
      "num_input_tokens_seen": 62980096,
      "step": 242
    },
    {
      "epoch": 2.7375886524822697,
      "grad_norm": 1.2274329880141919,
      "learning_rate": 2.0912937601616005e-05,
      "loss": 0.3808,
      "num_input_tokens_seen": 63242240,
      "step": 243
    },
    {
      "epoch": 2.748936170212766,
      "grad_norm": 1.1187546128405046,
      "learning_rate": 2.0736945184184405e-05,
      "loss": 0.3743,
      "num_input_tokens_seen": 63504384,
      "step": 244
    },
    {
      "epoch": 2.7602836879432626,
      "grad_norm": 1.2604037547622573,
      "learning_rate": 2.0561170093642423e-05,
      "loss": 0.4019,
      "num_input_tokens_seen": 63766528,
      "step": 245
    },
    {
      "epoch": 2.771631205673759,
      "grad_norm": 1.1558782623081498,
      "learning_rate": 2.038562129085387e-05,
      "loss": 0.3791,
      "num_input_tokens_seen": 64028672,
      "step": 246
    },
    {
      "epoch": 2.7829787234042556,
      "grad_norm": 1.1080497501880997,
      "learning_rate": 2.0210307725146615e-05,
      "loss": 0.3696,
      "num_input_tokens_seen": 64290816,
      "step": 247
    },
    {
      "epoch": 2.794326241134752,
      "grad_norm": 1.3333275378619078,
      "learning_rate": 2.003523833385637e-05,
      "loss": 0.3945,
      "num_input_tokens_seen": 64552960,
      "step": 248
    },
    {
      "epoch": 2.8056737588652485,
      "grad_norm": 1.1083885717571962,
      "learning_rate": 1.9860422041870987e-05,
      "loss": 0.3922,
      "num_input_tokens_seen": 64815104,
      "step": 249
    },
    {
      "epoch": 2.8170212765957445,
      "grad_norm": 1.2103467593229682,
      "learning_rate": 1.9685867761175584e-05,
      "loss": 0.3921,
      "num_input_tokens_seen": 65077248,
      "step": 250
    },
    {
      "epoch": 2.828368794326241,
      "grad_norm": 1.0852218255349009,
      "learning_rate": 1.9511584390398147e-05,
      "loss": 0.3846,
      "num_input_tokens_seen": 65339392,
      "step": 251
    },
    {
      "epoch": 2.8397163120567375,
      "grad_norm": 1.2112711184032858,
      "learning_rate": 1.9337580814355888e-05,
      "loss": 0.3741,
      "num_input_tokens_seen": 65601536,
      "step": 252
    },
    {
      "epoch": 2.851063829787234,
      "grad_norm": 1.1548719932949865,
      "learning_rate": 1.9163865903602374e-05,
      "loss": 0.3688,
      "num_input_tokens_seen": 65863680,
      "step": 253
    },
    {
      "epoch": 2.8624113475177304,
      "grad_norm": 1.0632108357505439,
      "learning_rate": 1.899044851397519e-05,
      "loss": 0.3809,
      "num_input_tokens_seen": 66125824,
      "step": 254
    },
    {
      "epoch": 2.873758865248227,
      "grad_norm": 1.2738307250224112,
      "learning_rate": 1.881733748614461e-05,
      "loss": 0.3861,
      "num_input_tokens_seen": 66387968,
      "step": 255
    },
    {
      "epoch": 2.8851063829787233,
      "grad_norm": 1.2665120384000739,
      "learning_rate": 1.8644541645162834e-05,
      "loss": 0.3905,
      "num_input_tokens_seen": 66650112,
      "step": 256
    },
    {
      "epoch": 2.89645390070922,
      "grad_norm": 1.1562998336132535,
      "learning_rate": 1.8472069800014068e-05,
      "loss": 0.3614,
      "num_input_tokens_seen": 66912256,
      "step": 257
    },
    {
      "epoch": 2.9078014184397163,
      "grad_norm": 1.1877334097829628,
      "learning_rate": 1.8299930743165535e-05,
      "loss": 0.383,
      "num_input_tokens_seen": 67174400,
      "step": 258
    },
    {
      "epoch": 2.9191489361702128,
      "grad_norm": 1.077396638449169,
      "learning_rate": 1.8128133250119157e-05,
      "loss": 0.3735,
      "num_input_tokens_seen": 67436544,
      "step": 259
    },
    {
      "epoch": 2.9304964539007092,
      "grad_norm": 1.1563881856425553,
      "learning_rate": 1.795668607896426e-05,
      "loss": 0.3978,
      "num_input_tokens_seen": 67698688,
      "step": 260
    },
    {
      "epoch": 2.9418439716312057,
      "grad_norm": 1.0938743557105097,
      "learning_rate": 1.778559796993104e-05,
      "loss": 0.3877,
      "num_input_tokens_seen": 67960832,
      "step": 261
    },
    {
      "epoch": 2.953191489361702,
      "grad_norm": 1.1062018663854845,
      "learning_rate": 1.7614877644945e-05,
      "loss": 0.3862,
      "num_input_tokens_seen": 68222976,
      "step": 262
    },
    {
      "epoch": 2.9645390070921986,
      "grad_norm": 1.0442669458478842,
      "learning_rate": 1.7444533807182357e-05,
      "loss": 0.3506,
      "num_input_tokens_seen": 68485120,
      "step": 263
    },
    {
      "epoch": 2.975886524822695,
      "grad_norm": 1.0755649234512432,
      "learning_rate": 1.7274575140626318e-05,
      "loss": 0.371,
      "num_input_tokens_seen": 68747264,
      "step": 264
    },
    {
      "epoch": 2.9872340425531916,
      "grad_norm": 1.0856119742333918,
      "learning_rate": 1.710501030962438e-05,
      "loss": 0.3866,
      "num_input_tokens_seen": 69009408,
      "step": 265
    },
    {
      "epoch": 2.998581560283688,
      "grad_norm": 1.0445462962582197,
      "learning_rate": 1.6935847958446657e-05,
      "loss": 0.3701,
      "num_input_tokens_seen": 69271552,
      "step": 266
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.0445462962582197,
      "learning_rate": 1.6767096710845174e-05,
      "loss": 0.2901,
      "num_input_tokens_seen": 69304320,
      "step": 267
    },
    {
      "epoch": 3.0113475177304965,
      "grad_norm": 2.74466686658697,
      "learning_rate": 1.6598765169614243e-05,
      "loss": 0.1312,
      "num_input_tokens_seen": 69566464,
      "step": 268
    },
    {
      "epoch": 3.022695035460993,
      "grad_norm": 1.5834322773598914,
      "learning_rate": 1.643086191615194e-05,
      "loss": 0.1237,
      "num_input_tokens_seen": 69828608,
      "step": 269
    },
    {
      "epoch": 3.0340425531914894,
      "grad_norm": 1.303912889019024,
      "learning_rate": 1.6263395510022543e-05,
      "loss": 0.1163,
      "num_input_tokens_seen": 70090752,
      "step": 270
    },
    {
      "epoch": 3.045390070921986,
      "grad_norm": 0.9262307477869844,
      "learning_rate": 1.6096374488520265e-05,
      "loss": 0.101,
      "num_input_tokens_seen": 70352896,
      "step": 271
    },
    {
      "epoch": 3.0567375886524824,
      "grad_norm": 0.9926400294079983,
      "learning_rate": 1.5929807366233977e-05,
      "loss": 0.1097,
      "num_input_tokens_seen": 70615040,
      "step": 272
    },
    {
      "epoch": 3.068085106382979,
      "grad_norm": 1.275115327394668,
      "learning_rate": 1.5763702634613152e-05,
      "loss": 0.1049,
      "num_input_tokens_seen": 70877184,
      "step": 273
    },
    {
      "epoch": 3.0794326241134753,
      "grad_norm": 1.5930282703149587,
      "learning_rate": 1.559806876153501e-05,
      "loss": 0.1168,
      "num_input_tokens_seen": 71139328,
      "step": 274
    },
    {
      "epoch": 3.0907801418439718,
      "grad_norm": 1.4943109059271082,
      "learning_rate": 1.5432914190872757e-05,
      "loss": 0.1063,
      "num_input_tokens_seen": 71401472,
      "step": 275
    },
    {
      "epoch": 3.1021276595744682,
      "grad_norm": 1.3224758273342347,
      "learning_rate": 1.5268247342065215e-05,
      "loss": 0.0996,
      "num_input_tokens_seen": 71663616,
      "step": 276
    },
    {
      "epoch": 3.1134751773049647,
      "grad_norm": 1.0401363088355635,
      "learning_rate": 1.5104076609687545e-05,
      "loss": 0.099,
      "num_input_tokens_seen": 71925760,
      "step": 277
    },
    {
      "epoch": 3.124822695035461,
      "grad_norm": 0.9168634985756315,
      "learning_rate": 1.4940410363023306e-05,
      "loss": 0.0904,
      "num_input_tokens_seen": 72187904,
      "step": 278
    },
    {
      "epoch": 3.1361702127659576,
      "grad_norm": 0.8236578810199936,
      "learning_rate": 1.4777256945637834e-05,
      "loss": 0.0986,
      "num_input_tokens_seen": 72450048,
      "step": 279
    },
    {
      "epoch": 3.147517730496454,
      "grad_norm": 0.7819456617953726,
      "learning_rate": 1.4614624674952842e-05,
      "loss": 0.0922,
      "num_input_tokens_seen": 72712192,
      "step": 280
    },
    {
      "epoch": 3.1588652482269506,
      "grad_norm": 0.811675121286178,
      "learning_rate": 1.4452521841822436e-05,
      "loss": 0.0981,
      "num_input_tokens_seen": 72974336,
      "step": 281
    },
    {
      "epoch": 3.1702127659574466,
      "grad_norm": 0.7976686044001465,
      "learning_rate": 1.4290956710110475e-05,
      "loss": 0.0924,
      "num_input_tokens_seen": 73236480,
      "step": 282
    },
    {
      "epoch": 3.181560283687943,
      "grad_norm": 0.751816526314869,
      "learning_rate": 1.4129937516269203e-05,
      "loss": 0.0947,
      "num_input_tokens_seen": 73498624,
      "step": 283
    },
    {
      "epoch": 3.1929078014184396,
      "grad_norm": 0.8177754717456022,
      "learning_rate": 1.3969472468919461e-05,
      "loss": 0.0921,
      "num_input_tokens_seen": 73760768,
      "step": 284
    },
    {
      "epoch": 3.204255319148936,
      "grad_norm": 0.7571785449155486,
      "learning_rate": 1.3809569748432189e-05,
      "loss": 0.0906,
      "num_input_tokens_seen": 74022912,
      "step": 285
    },
    {
      "epoch": 3.2156028368794325,
      "grad_norm": 0.747961359332696,
      "learning_rate": 1.3650237506511331e-05,
      "loss": 0.0872,
      "num_input_tokens_seen": 74285056,
      "step": 286
    },
    {
      "epoch": 3.226950354609929,
      "grad_norm": 0.792288904094197,
      "learning_rate": 1.3491483865778365e-05,
      "loss": 0.0884,
      "num_input_tokens_seen": 74547200,
      "step": 287
    },
    {
      "epoch": 3.2382978723404254,
      "grad_norm": 0.8907746700880744,
      "learning_rate": 1.3333316919358157e-05,
      "loss": 0.0967,
      "num_input_tokens_seen": 74809344,
      "step": 288
    },
    {
      "epoch": 3.249645390070922,
      "grad_norm": 0.7775009871286768,
      "learning_rate": 1.3175744730466408e-05,
      "loss": 0.0818,
      "num_input_tokens_seen": 75071488,
      "step": 289
    },
    {
      "epoch": 3.2609929078014184,
      "grad_norm": 0.7695449735932754,
      "learning_rate": 1.301877533199859e-05,
      "loss": 0.0888,
      "num_input_tokens_seen": 75333632,
      "step": 290
    },
    {
      "epoch": 3.272340425531915,
      "grad_norm": 0.8110072874482183,
      "learning_rate": 1.2862416726120396e-05,
      "loss": 0.0906,
      "num_input_tokens_seen": 75595776,
      "step": 291
    },
    {
      "epoch": 3.2836879432624113,
      "grad_norm": 0.7766644179424415,
      "learning_rate": 1.2706676883859903e-05,
      "loss": 0.0872,
      "num_input_tokens_seen": 75857920,
      "step": 292
    },
    {
      "epoch": 3.295035460992908,
      "grad_norm": 0.7189275332544894,
      "learning_rate": 1.2551563744701109e-05,
      "loss": 0.087,
      "num_input_tokens_seen": 76120064,
      "step": 293
    },
    {
      "epoch": 3.3063829787234043,
      "grad_norm": 0.711512593628328,
      "learning_rate": 1.2397085216179208e-05,
      "loss": 0.0852,
      "num_input_tokens_seen": 76382208,
      "step": 294
    },
    {
      "epoch": 3.3177304964539007,
      "grad_norm": 0.7338724262748597,
      "learning_rate": 1.2243249173477513e-05,
      "loss": 0.0877,
      "num_input_tokens_seen": 76644352,
      "step": 295
    },
    {
      "epoch": 3.329078014184397,
      "grad_norm": 0.7269268914811858,
      "learning_rate": 1.2090063459025955e-05,
      "loss": 0.086,
      "num_input_tokens_seen": 76906496,
      "step": 296
    },
    {
      "epoch": 3.3404255319148937,
      "grad_norm": 0.7772637508360701,
      "learning_rate": 1.1937535882101281e-05,
      "loss": 0.0898,
      "num_input_tokens_seen": 77168640,
      "step": 297
    },
    {
      "epoch": 3.35177304964539,
      "grad_norm": 0.7412964391797219,
      "learning_rate": 1.1785674218428952e-05,
      "loss": 0.0936,
      "num_input_tokens_seen": 77430784,
      "step": 298
    },
    {
      "epoch": 3.3631205673758866,
      "grad_norm": 0.717507466030445,
      "learning_rate": 1.163448620978674e-05,
      "loss": 0.0837,
      "num_input_tokens_seen": 77692928,
      "step": 299
    },
    {
      "epoch": 3.374468085106383,
      "grad_norm": 0.7491045281676182,
      "learning_rate": 1.148397956361007e-05,
      "loss": 0.0902,
      "num_input_tokens_seen": 77955072,
      "step": 300
    },
    {
      "epoch": 3.3858156028368795,
      "grad_norm": 0.7816973300591532,
      "learning_rate": 1.1334161952599054e-05,
      "loss": 0.085,
      "num_input_tokens_seen": 78217216,
      "step": 301
    },
    {
      "epoch": 3.397163120567376,
      "grad_norm": 0.7754872404477443,
      "learning_rate": 1.1185041014327433e-05,
      "loss": 0.0967,
      "num_input_tokens_seen": 78479360,
      "step": 302
    },
    {
      "epoch": 3.4085106382978725,
      "grad_norm": 0.7562220941293399,
      "learning_rate": 1.1036624350853145e-05,
      "loss": 0.0861,
      "num_input_tokens_seen": 78741504,
      "step": 303
    },
    {
      "epoch": 3.419858156028369,
      "grad_norm": 0.7446834922212843,
      "learning_rate": 1.0888919528330777e-05,
      "loss": 0.0866,
      "num_input_tokens_seen": 79003648,
      "step": 304
    },
    {
      "epoch": 3.4312056737588654,
      "grad_norm": 0.7368714630650928,
      "learning_rate": 1.0741934076625895e-05,
      "loss": 0.0909,
      "num_input_tokens_seen": 79265792,
      "step": 305
    },
    {
      "epoch": 3.4425531914893615,
      "grad_norm": 0.7586993943731002,
      "learning_rate": 1.059567548893118e-05,
      "loss": 0.0864,
      "num_input_tokens_seen": 79527936,
      "step": 306
    },
    {
      "epoch": 3.453900709219858,
      "grad_norm": 0.7026395743924377,
      "learning_rate": 1.0450151221384358e-05,
      "loss": 0.0907,
      "num_input_tokens_seen": 79790080,
      "step": 307
    },
    {
      "epoch": 3.4652482269503544,
      "grad_norm": 0.7698549183761029,
      "learning_rate": 1.0305368692688174e-05,
      "loss": 0.0875,
      "num_input_tokens_seen": 80052224,
      "step": 308
    },
    {
      "epoch": 3.476595744680851,
      "grad_norm": 0.7275021764735461,
      "learning_rate": 1.016133528373215e-05,
      "loss": 0.0876,
      "num_input_tokens_seen": 80314368,
      "step": 309
    },
    {
      "epoch": 3.4879432624113473,
      "grad_norm": 0.6801616141816872,
      "learning_rate": 1.0018058337216327e-05,
      "loss": 0.0757,
      "num_input_tokens_seen": 80576512,
      "step": 310
    },
    {
      "epoch": 3.499290780141844,
      "grad_norm": 0.7242637394130332,
      "learning_rate": 9.875545157276939e-06,
      "loss": 0.0805,
      "num_input_tokens_seen": 80838656,
      "step": 311
    },
    {
      "epoch": 3.5106382978723403,
      "grad_norm": 0.695464243410679,
      "learning_rate": 9.733803009114045e-06,
      "loss": 0.0853,
      "num_input_tokens_seen": 81100800,
      "step": 312
    },
    {
      "epoch": 3.5219858156028367,
      "grad_norm": 0.7091878866235037,
      "learning_rate": 9.592839118621187e-06,
      "loss": 0.0871,
      "num_input_tokens_seen": 81362944,
      "step": 313
    },
    {
      "epoch": 3.533333333333333,
      "grad_norm": 0.7211061205609051,
      "learning_rate": 9.452660672016949e-06,
      "loss": 0.0787,
      "num_input_tokens_seen": 81625088,
      "step": 314
    },
    {
      "epoch": 3.5446808510638297,
      "grad_norm": 0.7222949726436061,
      "learning_rate": 9.313274815478698e-06,
      "loss": 0.0862,
      "num_input_tokens_seen": 81887232,
      "step": 315
    },
    {
      "epoch": 3.556028368794326,
      "grad_norm": 0.7838259636406755,
      "learning_rate": 9.174688654778243e-06,
      "loss": 0.0936,
      "num_input_tokens_seen": 82149376,
      "step": 316
    },
    {
      "epoch": 3.5673758865248226,
      "grad_norm": 0.7463416558404256,
      "learning_rate": 9.036909254919549e-06,
      "loss": 0.0802,
      "num_input_tokens_seen": 82411520,
      "step": 317
    },
    {
      "epoch": 3.578723404255319,
      "grad_norm": 0.7081806282392477,
      "learning_rate": 8.899943639778619e-06,
      "loss": 0.0889,
      "num_input_tokens_seen": 82673664,
      "step": 318
    },
    {
      "epoch": 3.5900709219858156,
      "grad_norm": 0.725305882992691,
      "learning_rate": 8.763798791745411e-06,
      "loss": 0.0787,
      "num_input_tokens_seen": 82935808,
      "step": 319
    },
    {
      "epoch": 3.601418439716312,
      "grad_norm": 0.6909525153125249,
      "learning_rate": 8.628481651367876e-06,
      "loss": 0.084,
      "num_input_tokens_seen": 83197952,
      "step": 320
    },
    {
      "epoch": 3.6127659574468085,
      "grad_norm": 0.8073887823074956,
      "learning_rate": 8.49399911699814e-06,
      "loss": 0.0897,
      "num_input_tokens_seen": 83460096,
      "step": 321
    },
    {
      "epoch": 3.624113475177305,
      "grad_norm": 0.7270215654465839,
      "learning_rate": 8.360358044440797e-06,
      "loss": 0.0876,
      "num_input_tokens_seen": 83722240,
      "step": 322
    },
    {
      "epoch": 3.6354609929078014,
      "grad_norm": 0.7664259700341645,
      "learning_rate": 8.227565246603493e-06,
      "loss": 0.0815,
      "num_input_tokens_seen": 83984384,
      "step": 323
    },
    {
      "epoch": 3.646808510638298,
      "grad_norm": 0.6912127705169636,
      "learning_rate": 8.09562749314952e-06,
      "loss": 0.0855,
      "num_input_tokens_seen": 84246528,
      "step": 324
    },
    {
      "epoch": 3.6581560283687944,
      "grad_norm": 0.7391846111163392,
      "learning_rate": 7.96455151015272e-06,
      "loss": 0.086,
      "num_input_tokens_seen": 84508672,
      "step": 325
    },
    {
      "epoch": 3.669503546099291,
      "grad_norm": 0.7040432780957079,
      "learning_rate": 7.83434397975466e-06,
      "loss": 0.0869,
      "num_input_tokens_seen": 84770816,
      "step": 326
    },
    {
      "epoch": 3.6808510638297873,
      "grad_norm": 0.7049978471337497,
      "learning_rate": 7.705011539823911e-06,
      "loss": 0.0791,
      "num_input_tokens_seen": 85032960,
      "step": 327
    },
    {
      "epoch": 3.692198581560284,
      "grad_norm": 0.6773004765686385,
      "learning_rate": 7.576560783617668e-06,
      "loss": 0.0807,
      "num_input_tokens_seen": 85295104,
      "step": 328
    },
    {
      "epoch": 3.7035460992907803,
      "grad_norm": 0.7205733650917361,
      "learning_rate": 7.448998259445664e-06,
      "loss": 0.0846,
      "num_input_tokens_seen": 85557248,
      "step": 329
    },
    {
      "epoch": 3.7148936170212767,
      "grad_norm": 0.7090150829436532,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 0.0755,
      "num_input_tokens_seen": 85819392,
      "step": 330
    },
    {
      "epoch": 3.726241134751773,
      "grad_norm": 0.7317047711785631,
      "learning_rate": 7.196563873705209e-06,
      "loss": 0.0897,
      "num_input_tokens_seen": 86081536,
      "step": 331
    },
    {
      "epoch": 3.7375886524822697,
      "grad_norm": 0.7593361249228872,
      "learning_rate": 7.071704881025915e-06,
      "loss": 0.0807,
      "num_input_tokens_seen": 86343680,
      "step": 332
    },
    {
      "epoch": 3.748936170212766,
      "grad_norm": 0.7235635799774105,
      "learning_rate": 6.947759857503119e-06,
      "loss": 0.0839,
      "num_input_tokens_seen": 86605824,
      "step": 333
    },
    {
      "epoch": 3.7602836879432626,
      "grad_norm": 0.7456576507189918,
      "learning_rate": 6.824735121748163e-06,
      "loss": 0.0811,
      "num_input_tokens_seen": 86867968,
      "step": 334
    },
    {
      "epoch": 3.771631205673759,
      "grad_norm": 0.693061575666079,
      "learning_rate": 6.70263694545687e-06,
      "loss": 0.0759,
      "num_input_tokens_seen": 87130112,
      "step": 335
    },
    {
      "epoch": 3.7829787234042556,
      "grad_norm": 0.6702503675155104,
      "learning_rate": 6.5814715530898745e-06,
      "loss": 0.0764,
      "num_input_tokens_seen": 87392256,
      "step": 336
    },
    {
      "epoch": 3.794326241134752,
      "grad_norm": 0.7321643097852675,
      "learning_rate": 6.461245121555307e-06,
      "loss": 0.0855,
      "num_input_tokens_seen": 87654400,
      "step": 337
    },
    {
      "epoch": 3.8056737588652485,
      "grad_norm": 0.7231929761648604,
      "learning_rate": 6.341963779893828e-06,
      "loss": 0.0789,
      "num_input_tokens_seen": 87916544,
      "step": 338
    },
    {
      "epoch": 3.8170212765957445,
      "grad_norm": 0.6959508065425039,
      "learning_rate": 6.223633608966254e-06,
      "loss": 0.0804,
      "num_input_tokens_seen": 88178688,
      "step": 339
    },
    {
      "epoch": 3.828368794326241,
      "grad_norm": 0.6689396318017862,
      "learning_rate": 6.106260641143546e-06,
      "loss": 0.0846,
      "num_input_tokens_seen": 88440832,
      "step": 340
    },
    {
      "epoch": 3.8397163120567375,
      "grad_norm": 0.7000335984216709,
      "learning_rate": 5.989850859999227e-06,
      "loss": 0.0768,
      "num_input_tokens_seen": 88702976,
      "step": 341
    },
    {
      "epoch": 3.851063829787234,
      "grad_norm": 0.6819366248376687,
      "learning_rate": 5.874410200004421e-06,
      "loss": 0.073,
      "num_input_tokens_seen": 88965120,
      "step": 342
    },
    {
      "epoch": 3.8624113475177304,
      "grad_norm": 0.6970883337622755,
      "learning_rate": 5.759944546225271e-06,
      "loss": 0.0826,
      "num_input_tokens_seen": 89227264,
      "step": 343
    },
    {
      "epoch": 3.873758865248227,
      "grad_norm": 0.6874281419558664,
      "learning_rate": 5.646459734022938e-06,
      "loss": 0.0697,
      "num_input_tokens_seen": 89489408,
      "step": 344
    },
    {
      "epoch": 3.8851063829787233,
      "grad_norm": 0.7106888911769208,
      "learning_rate": 5.533961548756128e-06,
      "loss": 0.0812,
      "num_input_tokens_seen": 89751552,
      "step": 345
    },
    {
      "epoch": 3.89645390070922,
      "grad_norm": 0.7331620079344322,
      "learning_rate": 5.422455725486114e-06,
      "loss": 0.0836,
      "num_input_tokens_seen": 90013696,
      "step": 346
    },
    {
      "epoch": 3.9078014184397163,
      "grad_norm": 0.7035598390060888,
      "learning_rate": 5.311947948684457e-06,
      "loss": 0.0815,
      "num_input_tokens_seen": 90275840,
      "step": 347
    },
    {
      "epoch": 3.9191489361702128,
      "grad_norm": 0.7060132556751886,
      "learning_rate": 5.202443851943126e-06,
      "loss": 0.0806,
      "num_input_tokens_seen": 90537984,
      "step": 348
    },
    {
      "epoch": 3.9304964539007092,
      "grad_norm": 0.6788669783816418,
      "learning_rate": 5.093949017687341e-06,
      "loss": 0.0794,
      "num_input_tokens_seen": 90800128,
      "step": 349
    },
    {
      "epoch": 3.9418439716312057,
      "grad_norm": 0.6687951756948881,
      "learning_rate": 4.986468976890993e-06,
      "loss": 0.0734,
      "num_input_tokens_seen": 91062272,
      "step": 350
    },
    {
      "epoch": 3.953191489361702,
      "grad_norm": 0.691944078100738,
      "learning_rate": 4.880009208794667e-06,
      "loss": 0.0814,
      "num_input_tokens_seen": 91324416,
      "step": 351
    },
    {
      "epoch": 3.9645390070921986,
      "grad_norm": 0.6500781762399683,
      "learning_rate": 4.7745751406263165e-06,
      "loss": 0.0726,
      "num_input_tokens_seen": 91586560,
      "step": 352
    },
    {
      "epoch": 3.975886524822695,
      "grad_norm": 0.671905484958583,
      "learning_rate": 4.670172147324592e-06,
      "loss": 0.077,
      "num_input_tokens_seen": 91848704,
      "step": 353
    },
    {
      "epoch": 3.9872340425531916,
      "grad_norm": 0.6796917288094408,
      "learning_rate": 4.566805551264827e-06,
      "loss": 0.0796,
      "num_input_tokens_seen": 92110848,
      "step": 354
    },
    {
      "epoch": 3.998581560283688,
      "grad_norm": 0.6833947734522067,
      "learning_rate": 4.4644806219877184e-06,
      "loss": 0.0723,
      "num_input_tokens_seen": 92372992,
      "step": 355
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.6833947734522067,
      "learning_rate": 4.36320257593065e-06,
      "loss": 0.045,
      "num_input_tokens_seen": 92405760,
      "step": 356
    },
    {
      "epoch": 4.0113475177304965,
      "grad_norm": 1.477142079845877,
      "learning_rate": 4.262976576161842e-06,
      "loss": 0.0244,
      "num_input_tokens_seen": 92667904,
      "step": 357
    },
    {
      "epoch": 4.022695035460993,
      "grad_norm": 0.5476807803856774,
      "learning_rate": 4.1638077321170646e-06,
      "loss": 0.0227,
      "num_input_tokens_seen": 92930048,
      "step": 358
    },
    {
      "epoch": 4.034042553191489,
      "grad_norm": 0.48697982739940027,
      "learning_rate": 4.0657010993391865e-06,
      "loss": 0.0213,
      "num_input_tokens_seen": 93192192,
      "step": 359
    },
    {
      "epoch": 4.045390070921986,
      "grad_norm": 0.44199476911249697,
      "learning_rate": 3.968661679220468e-06,
      "loss": 0.0196,
      "num_input_tokens_seen": 93454336,
      "step": 360
    },
    {
      "epoch": 4.056737588652482,
      "grad_norm": 0.40308653677545786,
      "learning_rate": 3.872694418747594e-06,
      "loss": 0.018,
      "num_input_tokens_seen": 93716480,
      "step": 361
    },
    {
      "epoch": 4.068085106382979,
      "grad_norm": 0.37702562689636665,
      "learning_rate": 3.777804210249436e-06,
      "loss": 0.0176,
      "num_input_tokens_seen": 93978624,
      "step": 362
    },
    {
      "epoch": 4.079432624113475,
      "grad_norm": 0.36421639955022134,
      "learning_rate": 3.6839958911476957e-06,
      "loss": 0.0193,
      "num_input_tokens_seen": 94240768,
      "step": 363
    },
    {
      "epoch": 4.090780141843972,
      "grad_norm": 0.3805365338343004,
      "learning_rate": 3.591274243710277e-06,
      "loss": 0.0176,
      "num_input_tokens_seen": 94502912,
      "step": 364
    },
    {
      "epoch": 4.102127659574468,
      "grad_norm": 0.3382957037488846,
      "learning_rate": 3.499643994807486e-06,
      "loss": 0.0163,
      "num_input_tokens_seen": 94765056,
      "step": 365
    },
    {
      "epoch": 4.113475177304965,
      "grad_norm": 0.32506441384380935,
      "learning_rate": 3.4091098156710744e-06,
      "loss": 0.0159,
      "num_input_tokens_seen": 95027200,
      "step": 366
    },
    {
      "epoch": 4.124822695035461,
      "grad_norm": 0.3165720865193881,
      "learning_rate": 3.319676321656082e-06,
      "loss": 0.0164,
      "num_input_tokens_seen": 95289344,
      "step": 367
    },
    {
      "epoch": 4.136170212765958,
      "grad_norm": 0.35920729686783553,
      "learning_rate": 3.2313480720055745e-06,
      "loss": 0.0159,
      "num_input_tokens_seen": 95551488,
      "step": 368
    },
    {
      "epoch": 4.147517730496454,
      "grad_norm": 0.35575880232588847,
      "learning_rate": 3.1441295696181897e-06,
      "loss": 0.0161,
      "num_input_tokens_seen": 95813632,
      "step": 369
    },
    {
      "epoch": 4.158865248226951,
      "grad_norm": 0.35269152277096033,
      "learning_rate": 3.058025260818609e-06,
      "loss": 0.0149,
      "num_input_tokens_seen": 96075776,
      "step": 370
    },
    {
      "epoch": 4.170212765957447,
      "grad_norm": 0.38681949998462883,
      "learning_rate": 2.9730395351308866e-06,
      "loss": 0.0147,
      "num_input_tokens_seen": 96337920,
      "step": 371
    },
    {
      "epoch": 4.1815602836879435,
      "grad_norm": 0.34874854085333057,
      "learning_rate": 2.889176725054643e-06,
      "loss": 0.0164,
      "num_input_tokens_seen": 96600064,
      "step": 372
    },
    {
      "epoch": 4.19290780141844,
      "grad_norm": 0.42993916416930195,
      "learning_rate": 2.80644110584424e-06,
      "loss": 0.0149,
      "num_input_tokens_seen": 96862208,
      "step": 373
    },
    {
      "epoch": 4.2042553191489365,
      "grad_norm": 0.3819874015881562,
      "learning_rate": 2.7248368952908053e-06,
      "loss": 0.0162,
      "num_input_tokens_seen": 97124352,
      "step": 374
    },
    {
      "epoch": 4.215602836879433,
      "grad_norm": 0.39897276144640115,
      "learning_rate": 2.6443682535072177e-06,
      "loss": 0.0144,
      "num_input_tokens_seen": 97386496,
      "step": 375
    },
    {
      "epoch": 4.226950354609929,
      "grad_norm": 0.3570885820962534,
      "learning_rate": 2.565039282716045e-06,
      "loss": 0.0143,
      "num_input_tokens_seen": 97648640,
      "step": 376
    },
    {
      "epoch": 4.238297872340426,
      "grad_norm": 0.36959919713875067,
      "learning_rate": 2.486854027040375e-06,
      "loss": 0.0147,
      "num_input_tokens_seen": 97910784,
      "step": 377
    },
    {
      "epoch": 4.249645390070922,
      "grad_norm": 0.3387567156073276,
      "learning_rate": 2.4098164722977073e-06,
      "loss": 0.0142,
      "num_input_tokens_seen": 98172928,
      "step": 378
    },
    {
      "epoch": 4.260992907801419,
      "grad_norm": 0.35273580349206224,
      "learning_rate": 2.333930545796717e-06,
      "loss": 0.0162,
      "num_input_tokens_seen": 98435072,
      "step": 379
    },
    {
      "epoch": 4.272340425531915,
      "grad_norm": 0.41537674406100333,
      "learning_rate": 2.2592001161370392e-06,
      "loss": 0.0163,
      "num_input_tokens_seen": 98697216,
      "step": 380
    },
    {
      "epoch": 4.283687943262412,
      "grad_norm": 0.3722991986523798,
      "learning_rate": 2.185628993012101e-06,
      "loss": 0.0146,
      "num_input_tokens_seen": 98959360,
      "step": 381
    },
    {
      "epoch": 4.295035460992908,
      "grad_norm": 0.34823793557474586,
      "learning_rate": 2.11322092701485e-06,
      "loss": 0.0155,
      "num_input_tokens_seen": 99221504,
      "step": 382
    },
    {
      "epoch": 4.306382978723404,
      "grad_norm": 0.36284584139761145,
      "learning_rate": 2.0419796094465788e-06,
      "loss": 0.014,
      "num_input_tokens_seen": 99483648,
      "step": 383
    },
    {
      "epoch": 4.317730496453901,
      "grad_norm": 0.33330741537946007,
      "learning_rate": 1.97190867212875e-06,
      "loss": 0.0158,
      "num_input_tokens_seen": 99745792,
      "step": 384
    },
    {
      "epoch": 4.329078014184397,
      "grad_norm": 0.3678153199936105,
      "learning_rate": 1.9030116872178316e-06,
      "loss": 0.0145,
      "num_input_tokens_seen": 100007936,
      "step": 385
    },
    {
      "epoch": 4.340425531914893,
      "grad_norm": 0.3179402575720803,
      "learning_rate": 1.8352921670232143e-06,
      "loss": 0.0142,
      "num_input_tokens_seen": 100270080,
      "step": 386
    },
    {
      "epoch": 4.35177304964539,
      "grad_norm": 0.3139410780519724,
      "learning_rate": 1.768753563828135e-06,
      "loss": 0.0145,
      "num_input_tokens_seen": 100532224,
      "step": 387
    },
    {
      "epoch": 4.363120567375886,
      "grad_norm": 0.3543527103722898,
      "learning_rate": 1.703399269713693e-06,
      "loss": 0.0139,
      "num_input_tokens_seen": 100794368,
      "step": 388
    },
    {
      "epoch": 4.374468085106383,
      "grad_norm": 0.335580074515755,
      "learning_rate": 1.6392326163859273e-06,
      "loss": 0.0165,
      "num_input_tokens_seen": 101056512,
      "step": 389
    },
    {
      "epoch": 4.385815602836879,
      "grad_norm": 0.34683584517312804,
      "learning_rate": 1.5762568750059604e-06,
      "loss": 0.0152,
      "num_input_tokens_seen": 101318656,
      "step": 390
    },
    {
      "epoch": 4.397163120567376,
      "grad_norm": 0.3626865573265347,
      "learning_rate": 1.5144752560232372e-06,
      "loss": 0.016,
      "num_input_tokens_seen": 101580800,
      "step": 391
    },
    {
      "epoch": 4.408510638297872,
      "grad_norm": 0.3038959732006494,
      "learning_rate": 1.4538909090118846e-06,
      "loss": 0.0135,
      "num_input_tokens_seen": 101842944,
      "step": 392
    },
    {
      "epoch": 4.4198581560283685,
      "grad_norm": 0.33499076540774964,
      "learning_rate": 1.3945069225101026e-06,
      "loss": 0.0152,
      "num_input_tokens_seen": 102105088,
      "step": 393
    },
    {
      "epoch": 4.431205673758865,
      "grad_norm": 0.3607028863228608,
      "learning_rate": 1.3363263238627493e-06,
      "loss": 0.0161,
      "num_input_tokens_seen": 102367232,
      "step": 394
    },
    {
      "epoch": 4.4425531914893615,
      "grad_norm": 0.33049646901291296,
      "learning_rate": 1.2793520790670116e-06,
      "loss": 0.0153,
      "num_input_tokens_seen": 102629376,
      "step": 395
    },
    {
      "epoch": 4.453900709219858,
      "grad_norm": 0.3409835608306395,
      "learning_rate": 1.2235870926211619e-06,
      "loss": 0.0147,
      "num_input_tokens_seen": 102891520,
      "step": 396
    },
    {
      "epoch": 4.465248226950354,
      "grad_norm": 0.3426495926722642,
      "learning_rate": 1.1690342073765375e-06,
      "loss": 0.0148,
      "num_input_tokens_seen": 103153664,
      "step": 397
    },
    {
      "epoch": 4.476595744680851,
      "grad_norm": 0.3385258820673031,
      "learning_rate": 1.1156962043925828e-06,
      "loss": 0.0158,
      "num_input_tokens_seen": 103415808,
      "step": 398
    },
    {
      "epoch": 4.487943262411347,
      "grad_norm": 0.3366041472428315,
      "learning_rate": 1.0635758027950888e-06,
      "loss": 0.0135,
      "num_input_tokens_seen": 103677952,
      "step": 399
    },
    {
      "epoch": 4.499290780141844,
      "grad_norm": 0.3580533391262604,
      "learning_rate": 1.0126756596375686e-06,
      "loss": 0.0153,
      "num_input_tokens_seen": 103940096,
      "step": 400
    },
    {
      "epoch": 4.51063829787234,
      "grad_norm": 0.32986746041795145,
      "learning_rate": 9.629983697657886e-07,
      "loss": 0.0148,
      "num_input_tokens_seen": 104202240,
      "step": 401
    },
    {
      "epoch": 4.521985815602837,
      "grad_norm": 0.32413763896921793,
      "learning_rate": 9.145464656855257e-07,
      "loss": 0.0137,
      "num_input_tokens_seen": 104464384,
      "step": 402
    },
    {
      "epoch": 4.533333333333333,
      "grad_norm": 0.2817637969270016,
      "learning_rate": 8.673224174334221e-07,
      "loss": 0.0134,
      "num_input_tokens_seen": 104726528,
      "step": 403
    },
    {
      "epoch": 4.54468085106383,
      "grad_norm": 0.348191153365174,
      "learning_rate": 8.213286324510738e-07,
      "loss": 0.0147,
      "num_input_tokens_seen": 104988672,
      "step": 404
    },
    {
      "epoch": 4.556028368794326,
      "grad_norm": 0.3602776848534372,
      "learning_rate": 7.765674554623181e-07,
      "loss": 0.0168,
      "num_input_tokens_seen": 105250816,
      "step": 405
    },
    {
      "epoch": 4.567375886524823,
      "grad_norm": 0.31058750754194875,
      "learning_rate": 7.330411683536876e-07,
      "loss": 0.0147,
      "num_input_tokens_seen": 105512960,
      "step": 406
    },
    {
      "epoch": 4.578723404255319,
      "grad_norm": 0.3075632948113939,
      "learning_rate": 6.907519900580861e-07,
      "loss": 0.0155,
      "num_input_tokens_seen": 105775104,
      "step": 407
    },
    {
      "epoch": 4.590070921985816,
      "grad_norm": 0.3413483582876884,
      "learning_rate": 6.497020764416633e-07,
      "loss": 0.0153,
      "num_input_tokens_seen": 106037248,
      "step": 408
    },
    {
      "epoch": 4.601418439716312,
      "grad_norm": 0.3299810205766221,
      "learning_rate": 6.098935201939187e-07,
      "loss": 0.0139,
      "num_input_tokens_seen": 106299392,
      "step": 409
    },
    {
      "epoch": 4.6127659574468085,
      "grad_norm": 0.3045488270246865,
      "learning_rate": 5.713283507210148e-07,
      "loss": 0.0137,
      "num_input_tokens_seen": 106561536,
      "step": 410
    },
    {
      "epoch": 4.624113475177305,
      "grad_norm": 0.30919394459980154,
      "learning_rate": 5.340085340423129e-07,
      "loss": 0.0136,
      "num_input_tokens_seen": 106823680,
      "step": 411
    },
    {
      "epoch": 4.6354609929078014,
      "grad_norm": 0.3317176085043783,
      "learning_rate": 4.979359726901639e-07,
      "loss": 0.0145,
      "num_input_tokens_seen": 107085824,
      "step": 412
    },
    {
      "epoch": 4.646808510638298,
      "grad_norm": 0.3157192290221517,
      "learning_rate": 4.63112505612906e-07,
      "loss": 0.0137,
      "num_input_tokens_seen": 107347968,
      "step": 413
    },
    {
      "epoch": 4.658156028368794,
      "grad_norm": 0.304631562860152,
      "learning_rate": 4.2953990808111135e-07,
      "loss": 0.015,
      "num_input_tokens_seen": 107610112,
      "step": 414
    },
    {
      "epoch": 4.669503546099291,
      "grad_norm": 0.3526905412516224,
      "learning_rate": 3.972198915970976e-07,
      "loss": 0.0152,
      "num_input_tokens_seen": 107872256,
      "step": 415
    },
    {
      "epoch": 4.680851063829787,
      "grad_norm": 0.33679224274071523,
      "learning_rate": 3.6615410380767544e-07,
      "loss": 0.0147,
      "num_input_tokens_seen": 108134400,
      "step": 416
    },
    {
      "epoch": 4.692198581560284,
      "grad_norm": 0.32343102481646735,
      "learning_rate": 3.3634412842014353e-07,
      "loss": 0.0139,
      "num_input_tokens_seen": 108396544,
      "step": 417
    },
    {
      "epoch": 4.70354609929078,
      "grad_norm": 0.2946484230167598,
      "learning_rate": 3.077914851215585e-07,
      "loss": 0.0142,
      "num_input_tokens_seen": 108658688,
      "step": 418
    },
    {
      "epoch": 4.714893617021277,
      "grad_norm": 0.30378846194550047,
      "learning_rate": 2.804976295012612e-07,
      "loss": 0.0139,
      "num_input_tokens_seen": 108920832,
      "step": 419
    },
    {
      "epoch": 4.726241134751773,
      "grad_norm": 0.33144732440436586,
      "learning_rate": 2.544639529766829e-07,
      "loss": 0.0136,
      "num_input_tokens_seen": 109182976,
      "step": 420
    },
    {
      "epoch": 4.73758865248227,
      "grad_norm": 0.3360054980469322,
      "learning_rate": 2.2969178272238545e-07,
      "loss": 0.0143,
      "num_input_tokens_seen": 109445120,
      "step": 421
    },
    {
      "epoch": 4.748936170212766,
      "grad_norm": 0.3119829984354626,
      "learning_rate": 2.061823816024322e-07,
      "loss": 0.0132,
      "num_input_tokens_seen": 109707264,
      "step": 422
    },
    {
      "epoch": 4.760283687943263,
      "grad_norm": 0.3182968779470437,
      "learning_rate": 1.8393694810599493e-07,
      "loss": 0.0153,
      "num_input_tokens_seen": 109969408,
      "step": 423
    },
    {
      "epoch": 4.771631205673759,
      "grad_norm": 0.2823020931727126,
      "learning_rate": 1.6295661628624447e-07,
      "loss": 0.0139,
      "num_input_tokens_seen": 110231552,
      "step": 424
    },
    {
      "epoch": 4.782978723404256,
      "grad_norm": 0.33810487516657384,
      "learning_rate": 1.4324245570256633e-07,
      "loss": 0.0167,
      "num_input_tokens_seen": 110493696,
      "step": 425
    },
    {
      "epoch": 4.794326241134752,
      "grad_norm": 0.33893844406644097,
      "learning_rate": 1.2479547136600989e-07,
      "loss": 0.0135,
      "num_input_tokens_seen": 110755840,
      "step": 426
    },
    {
      "epoch": 4.8056737588652485,
      "grad_norm": 0.3356203471174735,
      "learning_rate": 1.0761660368806548e-07,
      "loss": 0.0151,
      "num_input_tokens_seen": 111017984,
      "step": 427
    },
    {
      "epoch": 4.817021276595745,
      "grad_norm": 0.3334523590081176,
      "learning_rate": 9.170672843271666e-08,
      "loss": 0.0143,
      "num_input_tokens_seen": 111280128,
      "step": 428
    },
    {
      "epoch": 4.828368794326241,
      "grad_norm": 0.32060335064770346,
      "learning_rate": 7.706665667180091e-08,
      "loss": 0.013,
      "num_input_tokens_seen": 111542272,
      "step": 429
    },
    {
      "epoch": 4.839716312056738,
      "grad_norm": 0.30209084334682806,
      "learning_rate": 6.369713474366212e-08,
      "loss": 0.0141,
      "num_input_tokens_seen": 111804416,
      "step": 430
    },
    {
      "epoch": 4.851063829787234,
      "grad_norm": 0.35524870224084554,
      "learning_rate": 5.159884421509498e-08,
      "loss": 0.0144,
      "num_input_tokens_seen": 112066560,
      "step": 431
    },
    {
      "epoch": 4.862411347517731,
      "grad_norm": 0.3137882300233803,
      "learning_rate": 4.07724018466088e-08,
      "loss": 0.0162,
      "num_input_tokens_seen": 112328704,
      "step": 432
    },
    {
      "epoch": 4.873758865248227,
      "grad_norm": 0.31600464447069954,
      "learning_rate": 3.1218359560974966e-08,
      "loss": 0.0145,
      "num_input_tokens_seen": 112590848,
      "step": 433
    },
    {
      "epoch": 4.885106382978723,
      "grad_norm": 0.36130384891727935,
      "learning_rate": 2.2937204415107717e-08,
      "loss": 0.0149,
      "num_input_tokens_seen": 112852992,
      "step": 434
    },
    {
      "epoch": 4.89645390070922,
      "grad_norm": 0.28210880961362844,
      "learning_rate": 1.5929358575206275e-08,
      "loss": 0.014,
      "num_input_tokens_seen": 113115136,
      "step": 435
    },
    {
      "epoch": 4.907801418439716,
      "grad_norm": 0.3370034082905995,
      "learning_rate": 1.0195179295269252e-08,
      "loss": 0.0145,
      "num_input_tokens_seen": 113377280,
      "step": 436
    },
    {
      "epoch": 4.919148936170213,
      "grad_norm": 0.34659397478326986,
      "learning_rate": 5.7349588988481194e-09,
      "loss": 0.0131,
      "num_input_tokens_seen": 113639424,
      "step": 437
    },
    {
      "epoch": 4.930496453900709,
      "grad_norm": 0.3388609291955605,
      "learning_rate": 2.5489247641674596e-09,
      "loss": 0.0133,
      "num_input_tokens_seen": 113901568,
      "step": 438
    },
    {
      "epoch": 4.941843971631206,
      "grad_norm": 0.32782899822451794,
      "learning_rate": 6.372393125203546e-10,
      "loss": 0.0147,
      "num_input_tokens_seen": 114163712,
      "step": 439
    },
    {
      "epoch": 4.953191489361702,
      "grad_norm": 0.340643949367228,
      "learning_rate": 0.0,
      "loss": 0.0166,
      "num_input_tokens_seen": 114425856,
      "step": 440
    },
    {
      "epoch": 4.953191489361702,
      "num_input_tokens_seen": 114425856,
      "step": 440,
      "total_flos": 182736094494720.0,
      "train_loss": 0.6679792516632006,
      "train_runtime": 10942.5374,
      "train_samples_per_second": 10.298,
      "train_steps_per_second": 0.04
    }
  ],
  "logging_steps": 1,
  "max_steps": 440,
  "num_input_tokens_seen": 114425856,
  "num_train_epochs": 5,
  "save_steps": 5000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 182736094494720.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}