{
  "best_metric": 0.15265125036239624,
  "best_model_checkpoint": "saves/psy-course-info/Llama-3.1-8B-Instruct/train/fold3/checkpoint-80",
  "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": 2.13401460647583,
      "learning_rate": 7.692307692307694e-06,
      "loss": 1.079,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 2.2135112285614014,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 1.116,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 2.2829487323760986,
      "learning_rate": 2.307692307692308e-05,
      "loss": 1.0734,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 2.3121910095214844,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.9877,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 2.4777026176452637,
      "learning_rate": 3.846153846153846e-05,
      "loss": 1.1372,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 2.5937418937683105,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.8862,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 2.625771999359131,
      "learning_rate": 5.384615384615385e-05,
      "loss": 1.0212,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 2.2809154987335205,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.8012,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 2.193075656890869,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.662,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 1.5392875671386719,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.5514,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.4828187823295593,
      "eval_runtime": 20.4233,
      "eval_samples_per_second": 2.203,
      "eval_steps_per_second": 2.203,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 1.2312418222427368,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.4695,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.9729057550430298,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.4421,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.9885647892951965,
      "learning_rate": 0.0001,
      "loss": 0.3303,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 1.1908000707626343,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.4115,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 1.1558841466903687,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.35,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 1.0113270282745361,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.3743,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.8379513025283813,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.2822,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.6096362471580505,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.2587,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.7930107116699219,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.2563,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.773169219493866,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.2484,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.2628766596317291,
      "eval_runtime": 20.3107,
      "eval_samples_per_second": 2.216,
      "eval_steps_per_second": 2.216,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.6929939389228821,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.2972,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.6238391995429993,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.2266,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.6686587333679199,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.2141,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.6161268353462219,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.2397,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.7046502828598022,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.3039,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 1.0601948499679565,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.43,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.42058736085891724,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1639,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.5214003920555115,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.2276,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.6271799206733704,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.2438,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.6046462059020996,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.203,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.2002571076154709,
      "eval_runtime": 20.3262,
      "eval_samples_per_second": 2.214,
      "eval_steps_per_second": 2.214,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.5208979249000549,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.1605,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.4603351950645447,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1679,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.554080605506897,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.1612,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.6689148545265198,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.214,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.6904860138893127,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.1624,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.6609926819801331,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.1981,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.5136111378669739,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.1891,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.46436357498168945,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.1285,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.5467451214790344,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.143,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.5636103749275208,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.1931,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.17744499444961548,
      "eval_runtime": 20.322,
      "eval_samples_per_second": 2.214,
      "eval_steps_per_second": 2.214,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.47177210450172424,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1328,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.7334060072898865,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.1721,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.47152650356292725,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.1309,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.41765502095222473,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.1509,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.43671277165412903,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.1511,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.6516591310501099,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.1771,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.5264871120452881,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.1842,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.6639788746833801,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.2003,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.4319416284561157,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.1235,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.5767079591751099,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.1294,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.16798457503318787,
      "eval_runtime": 20.3219,
      "eval_samples_per_second": 2.214,
      "eval_steps_per_second": 2.214,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 1.38614022731781,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.3271,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.46833160519599915,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0896,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.4942617416381836,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.1268,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.5808762907981873,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.1239,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.5379523038864136,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1341,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.998986542224884,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.1611,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.4738816022872925,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.111,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.5661807656288147,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.1326,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.6213648915290833,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.1545,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.4949955344200134,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.1138,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.16169141232967377,
      "eval_runtime": 20.3256,
      "eval_samples_per_second": 2.214,
      "eval_steps_per_second": 2.214,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.5869258642196655,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.1276,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.6416803598403931,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.1274,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.6484302282333374,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.1092,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.5458757281303406,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0882,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.5555431842803955,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0728,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.6846579909324646,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.1568,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.6784289479255676,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.1371,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.4825720191001892,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0907,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.6633433103561401,
      "learning_rate": 5e-05,
      "loss": 0.127,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.6380341053009033,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0836,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.1631079763174057,
      "eval_runtime": 20.3207,
      "eval_samples_per_second": 2.214,
      "eval_steps_per_second": 2.214,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.6956302523612976,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.1648,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.5919461250305176,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.0928,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.6532953381538391,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.1256,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.6162728667259216,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.1099,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.7895723581314087,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.1607,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.987082839012146,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.1792,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.5934836268424988,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.1048,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.5125874280929565,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.1052,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.5343924164772034,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0964,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.5786824822425842,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0823,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.15265125036239624,
      "eval_runtime": 20.3286,
      "eval_samples_per_second": 2.214,
      "eval_steps_per_second": 2.214,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.65896075963974,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0998,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.7420127987861633,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.132,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.7413497567176819,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0917,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.5590284466743469,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0945,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.5833249688148499,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0934,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.5945806503295898,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0712,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.5270406603813171,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0743,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.6235726475715637,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0663,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.5442896485328674,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0584,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.6221958994865417,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0872,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.1559033989906311,
      "eval_runtime": 20.3257,
      "eval_samples_per_second": 2.214,
      "eval_steps_per_second": 2.214,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.5928692817687988,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0891,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.6080653667449951,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0624,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.6735369563102722,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.073,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.8934256434440613,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.1292,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 1.1011497974395752,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.1328,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.6627883315086365,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0798,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.6367733478546143,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0897,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.6472126841545105,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0905,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.6218619346618652,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0768,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.6205220222473145,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0765,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.15494132041931152,
      "eval_runtime": 20.3292,
      "eval_samples_per_second": 2.214,
      "eval_steps_per_second": 2.214,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.8869872689247131,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0907,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 1.1068443059921265,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.1378,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.699768602848053,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0806,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.49976956844329834,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0628,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.4237731397151947,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0411,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.5244402885437012,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0742,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.5490588545799255,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0595,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.5422118306159973,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.077,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.5524388551712036,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0775,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.5293675065040588,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0892,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.15509049594402313,
      "eval_runtime": 20.3357,
      "eval_samples_per_second": 2.213,
      "eval_steps_per_second": 2.213,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.5813242197036743,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.07,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.6725654602050781,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0891,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.5070009231567383,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0689,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.5164303779602051,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0611,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.6196990013122559,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0711,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.5869881510734558,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.049,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.6818193197250366,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.1038,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.7266791462898254,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0963,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.5797473192214966,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0671,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.6365640759468079,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0854,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.154866561293602,
      "eval_runtime": 20.334,
      "eval_samples_per_second": 2.213,
      "eval_steps_per_second": 2.213,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.5267232060432434,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0648,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.5596231818199158,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0726,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.5757695436477661,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0763,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.7604299783706665,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0684,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.676563560962677,
      "learning_rate": 0.0,
      "loss": 0.0808,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.279295183878226e+17,
      "train_loss": 0.20847544202208518,
      "train_runtime": 3549.5947,
      "train_samples_per_second": 0.57,
      "train_steps_per_second": 0.035
    }
  ],
  "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": 1.279295183878226e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}