{
  "best_metric": 0.06834910064935684,
  "best_model_checkpoint": "saves/psy-course-doc/Llama-3.1-8B-Instruct/train/fold8/checkpoint-120",
  "epoch": 4.938271604938271,
  "eval_steps": 10,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03950617283950617,
      "grad_norm": 0.1671736091375351,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.1869,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.16582784056663513,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.1988,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.18888749182224274,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.1921,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.1755290925502777,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.2255,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.1657591015100479,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.2326,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.18214763700962067,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.1522,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.1790877729654312,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.2504,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.17740999162197113,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.169,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.16571664810180664,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.1995,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.15495440363883972,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.1249,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.14697352051734924,
      "eval_runtime": 22.7537,
      "eval_samples_per_second": 1.978,
      "eval_steps_per_second": 1.978,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.1573731005191803,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.1622,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.16252732276916504,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.1194,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.15282991528511047,
      "learning_rate": 0.0001,
      "loss": 0.1447,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.17091505229473114,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.125,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.1642923802137375,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.1276,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.14902353286743164,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.1298,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.14012889564037323,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.1544,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.14282411336898804,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.1652,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.12849318981170654,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.1172,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.1253332644701004,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1931,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.09536000341176987,
      "eval_runtime": 22.78,
      "eval_samples_per_second": 1.975,
      "eval_steps_per_second": 1.975,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.1180008128285408,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.0941,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.08796224743127823,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.0956,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.09806405007839203,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.1034,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.10877854377031326,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.094,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.10131094604730606,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.103,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.2585918605327606,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.2217,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.09397617727518082,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0618,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.10325226187705994,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1233,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.1052778884768486,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1252,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.10001438856124878,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.0487,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.08096157759428024,
      "eval_runtime": 22.7579,
      "eval_samples_per_second": 1.977,
      "eval_steps_per_second": 1.977,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.08254600316286087,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.0308,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.12527090311050415,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1464,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.10172444581985474,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.0471,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.09430652856826782,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0974,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.09226976335048676,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.111,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.09533911943435669,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.1197,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.10893023014068604,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0956,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.10068079084157944,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.068,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.09929613023996353,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.0875,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.09669752418994904,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.0772,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.0761091485619545,
      "eval_runtime": 22.7755,
      "eval_samples_per_second": 1.976,
      "eval_steps_per_second": 1.976,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.11060942709445953,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0974,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.08127131313085556,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.0801,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.0786014273762703,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0814,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.08632098883390427,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.1167,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.08443205058574677,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0394,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.07280303537845612,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0608,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.11312844604253769,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.1678,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.07459332048892975,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0817,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.07596450299024582,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.048,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.09002533555030823,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0882,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.07281188666820526,
      "eval_runtime": 22.7628,
      "eval_samples_per_second": 1.977,
      "eval_steps_per_second": 1.977,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.1602524220943451,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.1074,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.09179461002349854,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0721,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.07420310378074646,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0512,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.11405811458826065,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.1533,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.0900145098567009,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1113,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.09761472046375275,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.1306,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.08146359026432037,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.0972,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.08867393434047699,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0939,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.07587228715419769,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0363,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.08474782109260559,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0735,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.07060755789279938,
      "eval_runtime": 22.742,
      "eval_samples_per_second": 1.979,
      "eval_steps_per_second": 1.979,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.09078418463468552,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0871,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.08147489279508591,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0584,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.08732921630144119,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0699,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.07618939876556396,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0408,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.0927119329571724,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0676,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.09952496737241745,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0524,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.09643147885799408,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0959,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.09040112048387527,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0564,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.10234247148036957,
      "learning_rate": 5e-05,
      "loss": 0.0756,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.08778979629278183,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0446,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.06925108283758163,
      "eval_runtime": 22.7477,
      "eval_samples_per_second": 1.978,
      "eval_steps_per_second": 1.978,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.06914497166872025,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0529,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.10942385345697403,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.1181,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.0847330316901207,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0656,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.0975685864686966,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0526,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.06725738942623138,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0441,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.20020921528339386,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.1706,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.10064365714788437,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.1095,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.09107114374637604,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0583,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.09740545600652695,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0708,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.09200047701597214,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0407,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.0691196471452713,
      "eval_runtime": 22.7396,
      "eval_samples_per_second": 1.979,
      "eval_steps_per_second": 1.979,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.10005452483892441,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0891,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.08712375164031982,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0553,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.09198945015668869,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.062,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.08189446479082108,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0567,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.0884997546672821,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0945,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.08648461103439331,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.04,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.07578586786985397,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0421,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.10573717951774597,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.1189,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.0986710861325264,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0495,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.07944886386394501,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0229,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.06839077174663544,
      "eval_runtime": 22.7459,
      "eval_samples_per_second": 1.978,
      "eval_steps_per_second": 1.978,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.0837191641330719,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0402,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.08790914714336395,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0704,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.08919599652290344,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0552,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.10567336529493332,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0926,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.11058743298053741,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0681,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.0706229954957962,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0183,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.11984913051128387,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.081,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.11969496309757233,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.1307,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.11076483875513077,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0944,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.08448881655931473,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0399,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.06852899491786957,
      "eval_runtime": 22.7478,
      "eval_samples_per_second": 1.978,
      "eval_steps_per_second": 1.978,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.11652204394340515,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.1273,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.2210250198841095,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.1457,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.12247328460216522,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.111,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.09281650185585022,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0442,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.0971105620265007,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.07,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.08289182931184769,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0403,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.07124431431293488,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0155,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.0695243626832962,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0148,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.10752096027135849,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.1,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.08974195271730423,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0601,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.06844048202037811,
      "eval_runtime": 22.7544,
      "eval_samples_per_second": 1.978,
      "eval_steps_per_second": 1.978,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.09636320173740387,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0877,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.0898442342877388,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0608,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.1008099615573883,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0777,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.08709677308797836,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0485,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.08761801570653915,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0648,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.09783001989126205,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0623,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.09931576997041702,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0966,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.1376482993364334,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.1334,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.08383094519376755,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0344,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.10729902237653732,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0727,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.06834910064935684,
      "eval_runtime": 22.7513,
      "eval_samples_per_second": 1.978,
      "eval_steps_per_second": 1.978,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.08458263427019119,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0152,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.08840657770633698,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0532,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.09596497565507889,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0715,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.09176391363143921,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0623,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.11014857888221741,
      "learning_rate": 0.0,
      "loss": 0.1083,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.5208222651888435e+17,
      "train_loss": 0.09313745249807835,
      "train_runtime": 3763.0141,
      "train_samples_per_second": 0.538,
      "train_steps_per_second": 0.033
    }
  ],
  "logging_steps": 1,
  "max_steps": 125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5208222651888435e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}