{
  "best_metric": 0.058020543307065964,
  "best_model_checkpoint": "saves/psy-course-doc-info/Llama3-OpenBioLLM-8B/train/fold4/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": 0.4638867974281311,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.3713,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.4821414649486542,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.37,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.5608348846435547,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.3844,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.5530951023101807,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.4015,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.4940834641456604,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.3693,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.6329977512359619,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.3921,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.5599556565284729,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.3774,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.5469794869422913,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.3239,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.44517746567726135,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.3047,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.43796947598457336,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.3021,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.24682341516017914,
      "eval_runtime": 35.4059,
      "eval_samples_per_second": 1.271,
      "eval_steps_per_second": 1.271,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.41293635964393616,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.2484,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.4468001425266266,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.2484,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.4013810455799103,
      "learning_rate": 0.0001,
      "loss": 0.2216,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.4886457026004791,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.2275,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.4329957664012909,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.2029,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.405582070350647,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.1762,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.29763320088386536,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.1618,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.28251710534095764,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.1561,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.33685508370399475,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.1448,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.2987128496170044,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1477,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.13725502789020538,
      "eval_runtime": 35.2222,
      "eval_samples_per_second": 1.278,
      "eval_steps_per_second": 1.278,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.28806787729263306,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.1332,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.4197094142436981,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.1386,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.3084244728088379,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.1285,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.28486713767051697,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.1225,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.2846381664276123,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.113,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.6588493585586548,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.1907,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.41859519481658936,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1112,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.29821687936782837,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.0978,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.3721534013748169,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1047,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.295568585395813,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.1027,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.10148195922374725,
      "eval_runtime": 35.2519,
      "eval_samples_per_second": 1.277,
      "eval_steps_per_second": 1.277,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.37280380725860596,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.1053,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.29705044627189636,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.0979,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.390874445438385,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.079,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.4962455928325653,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1021,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.2066134214401245,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.0681,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.4505881369113922,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.0967,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.28927117586135864,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0995,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.285239577293396,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.0866,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.25073498487472534,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.0818,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.21558529138565063,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.0804,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.08040741831064224,
      "eval_runtime": 35.5176,
      "eval_samples_per_second": 1.267,
      "eval_steps_per_second": 1.267,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.5238478183746338,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0848,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.2577255964279175,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.0731,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.3455292284488678,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0873,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.25119680166244507,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.0739,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.17176544666290283,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0578,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.36899155378341675,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0834,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.2408820241689682,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0733,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.24833346903324127,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0772,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.25498002767562866,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.0687,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.31733331084251404,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0652,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.0701562911272049,
      "eval_runtime": 35.5183,
      "eval_samples_per_second": 1.267,
      "eval_steps_per_second": 1.267,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.4405730068683624,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.1111,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.2709929943084717,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0697,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.31525176763534546,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0632,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.19860970973968506,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0533,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.34792959690093994,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0606,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.2259582281112671,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.0594,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.2794646918773651,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.0749,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.3805646300315857,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0629,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.2377537041902542,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0566,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.22594037652015686,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0535,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.06407535076141357,
      "eval_runtime": 35.6828,
      "eval_samples_per_second": 1.261,
      "eval_steps_per_second": 1.261,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.2200620025396347,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0471,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.20087377727031708,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0416,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.20504744350910187,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0623,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.23730678856372833,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0615,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.30150505900382996,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0626,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.2200329303741455,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0481,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.2834266424179077,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0609,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.25412729382514954,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0612,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.2710444927215576,
      "learning_rate": 5e-05,
      "loss": 0.0615,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.23093774914741516,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0527,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.061717890202999115,
      "eval_runtime": 35.6413,
      "eval_samples_per_second": 1.263,
      "eval_steps_per_second": 1.263,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.2726534903049469,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0485,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.23765787482261658,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.052,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.21393992006778717,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0547,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.18586590886116028,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0521,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.26771366596221924,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0645,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.35347089171409607,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0906,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.19805759191513062,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0427,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.16392390429973602,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0467,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.18066729605197906,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0454,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.23595546185970306,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0527,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.06027219071984291,
      "eval_runtime": 35.5112,
      "eval_samples_per_second": 1.267,
      "eval_steps_per_second": 1.267,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.16897614300251007,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0457,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.1508565992116928,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0391,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.1834251880645752,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0373,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.23272886872291565,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0462,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.1923082023859024,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0429,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.18391279876232147,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0462,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.2546493411064148,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0485,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.1945538967847824,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0455,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.17795157432556152,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0446,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.21831755340099335,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0495,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.06012333184480667,
      "eval_runtime": 35.4141,
      "eval_samples_per_second": 1.271,
      "eval_steps_per_second": 1.271,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.28131040930747986,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0487,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.19438546895980835,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0462,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.2516339123249054,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.056,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.2355310171842575,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0427,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.19418130815029144,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0445,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.18322020769119263,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0419,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.2013123780488968,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0511,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.3566814959049225,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0471,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.2764089107513428,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0498,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.2172444462776184,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0489,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.05820522829890251,
      "eval_runtime": 35.6855,
      "eval_samples_per_second": 1.261,
      "eval_steps_per_second": 1.261,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.22188064455986023,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0483,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.4332502484321594,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0805,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.2032834142446518,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0412,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.184401735663414,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.033,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.23300878703594208,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0504,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.16200785338878632,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0291,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.2412651777267456,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0524,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.20250767469406128,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0409,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.2015630453824997,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0414,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.163670614361763,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0451,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.05846065282821655,
      "eval_runtime": 35.6581,
      "eval_samples_per_second": 1.262,
      "eval_steps_per_second": 1.262,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.2007477581501007,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0397,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.2314813733100891,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0442,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.18710993230342865,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0446,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.21665048599243164,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0501,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.16084714233875275,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0352,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.23745127022266388,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0526,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.195063516497612,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.05,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.14845800399780273,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0341,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.1935877501964569,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0514,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.20079275965690613,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0406,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.058020543307065964,
      "eval_runtime": 35.6844,
      "eval_samples_per_second": 1.261,
      "eval_steps_per_second": 1.261,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.1628788709640503,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0412,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.21814164519309998,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0414,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.17843757569789886,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0363,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.181738018989563,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0344,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.17482848465442657,
      "learning_rate": 0.0,
      "loss": 0.0389,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.6936048003232563e+17,
      "train_loss": 0.097686646386981,
      "train_runtime": 6025.7019,
      "train_samples_per_second": 0.336,
      "train_steps_per_second": 0.021
    }
  ],
  "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": 1.6936048003232563e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}