{
  "best_metric": 0.12621580064296722,
  "best_model_checkpoint": "saves/psy-course-info/MentaLLaMA-chat-7B/train/fold6/checkpoint-100",
  "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": 0.983975887298584,
      "learning_rate": 7.692307692307694e-06,
      "loss": 1.2093,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 1.0252294540405273,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 1.1843,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.9572101831436157,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.9841,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.8713443875312805,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 1.0671,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.8152269721031189,
      "learning_rate": 3.846153846153846e-05,
      "loss": 1.0259,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.9589189291000366,
      "learning_rate": 4.615384615384616e-05,
      "loss": 1.0151,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 1.0678017139434814,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.9943,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 1.119783878326416,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.9902,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 1.4542350769042969,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.9647,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 1.2535679340362549,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.788,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.6942957043647766,
      "eval_runtime": 21.9934,
      "eval_samples_per_second": 2.046,
      "eval_steps_per_second": 2.046,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 1.241783618927002,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.7159,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.8711119294166565,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.5012,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.7151867151260376,
      "learning_rate": 0.0001,
      "loss": 0.4756,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.5280992388725281,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.3283,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.5277550220489502,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.3588,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.44429466128349304,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.33,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.6373321413993835,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.3544,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.4666365087032318,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.3031,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.5163149237632751,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.2309,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.43429380655288696,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.2842,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.2572690546512604,
      "eval_runtime": 21.9936,
      "eval_samples_per_second": 2.046,
      "eval_steps_per_second": 2.046,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.45612528920173645,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.2687,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.5132527351379395,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.317,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.4585282802581787,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.2416,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.4536152482032776,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.2891,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.47091439366340637,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.2645,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.9559937715530396,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.4288,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.34595897793769836,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.2119,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.32452264428138733,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.2102,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.35272103548049927,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.2251,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.3803368806838989,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.2114,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.18284356594085693,
      "eval_runtime": 22.0723,
      "eval_samples_per_second": 2.039,
      "eval_steps_per_second": 2.039,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.3909124433994293,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.1858,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.39703044295310974,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1745,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.3593040108680725,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.1497,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.3582431972026825,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1677,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.3293991684913635,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.1699,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.3170468509197235,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.1711,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.3955947160720825,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.177,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.3204350173473358,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.1458,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.34891557693481445,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.2122,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.38252586126327515,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.2531,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.15930500626564026,
      "eval_runtime": 22.0726,
      "eval_samples_per_second": 2.039,
      "eval_steps_per_second": 2.039,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.35312801599502563,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1269,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.3177107274532318,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.1336,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.3134976029396057,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.1639,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.3743612766265869,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.114,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.3452843129634857,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.1594,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.38332611322402954,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.1618,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.3207746148109436,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.1512,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.3756410479545593,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.173,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.43267396092414856,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.2125,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.3486817181110382,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.1673,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.14034511148929596,
      "eval_runtime": 22.0862,
      "eval_samples_per_second": 2.037,
      "eval_steps_per_second": 2.037,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.8317620754241943,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.2956,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.26826825737953186,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.1122,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.2549706697463989,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.1241,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.31633609533309937,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.145,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.45098891854286194,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1966,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.4581511616706848,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.1673,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.330304354429245,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.1264,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.30647796392440796,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.1686,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.2558991014957428,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.1007,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.27266135811805725,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.1253,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.13921113312244415,
      "eval_runtime": 22.0853,
      "eval_samples_per_second": 2.038,
      "eval_steps_per_second": 2.038,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.3342473804950714,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.1094,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.40066179633140564,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.1164,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.3206006586551666,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.1177,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.3142695724964142,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.102,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.3415108621120453,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.1454,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.39238694310188293,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.162,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.3579406440258026,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.1587,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.3030065894126892,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.11,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.3578912019729614,
      "learning_rate": 5e-05,
      "loss": 0.123,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.3651309013366699,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.1169,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.13557228446006775,
      "eval_runtime": 22.0871,
      "eval_samples_per_second": 2.037,
      "eval_steps_per_second": 2.037,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.42983004450798035,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.1212,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.36541497707366943,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.1266,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.3244531452655792,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.1078,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.3044168949127197,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.1058,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.33127933740615845,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.1055,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.7823874950408936,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.2554,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.2994139790534973,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.1084,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.30759984254837036,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0984,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.3504593074321747,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.1254,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.2636311650276184,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0855,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.12724395096302032,
      "eval_runtime": 22.1199,
      "eval_samples_per_second": 2.034,
      "eval_steps_per_second": 2.034,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.3199959993362427,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0899,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.32163044810295105,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.1029,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.3103608787059784,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.1203,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.3809058666229248,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.1208,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.20337730646133423,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0651,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.40271884202957153,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.1218,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.2907763123512268,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.1031,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.2965530753135681,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.1245,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.34808850288391113,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.1027,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.3923734724521637,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.1248,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.1271580159664154,
      "eval_runtime": 22.1156,
      "eval_samples_per_second": 2.035,
      "eval_steps_per_second": 2.035,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.3443357050418854,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.1191,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.32944390177726746,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.1092,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.26660656929016113,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0663,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.32605257630348206,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.1187,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.3395266830921173,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.1239,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.31612691283226013,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0774,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.3342391550540924,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.116,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.350486159324646,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.1464,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.34505361318588257,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.1226,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.29945847392082214,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.1085,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.12621580064296722,
      "eval_runtime": 22.1249,
      "eval_samples_per_second": 2.034,
      "eval_steps_per_second": 2.034,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.4904720187187195,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.131,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.6007070541381836,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.1585,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.3374367654323578,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.1075,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.32402580976486206,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0623,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.2799527943134308,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.1085,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.29464858770370483,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0914,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.34573981165885925,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0994,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.2678261995315552,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0778,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.3620866537094116,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.1141,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.30441972613334656,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.1071,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.1270829737186432,
      "eval_runtime": 22.1006,
      "eval_samples_per_second": 2.036,
      "eval_steps_per_second": 2.036,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.33899807929992676,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0798,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.37928062677383423,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.1304,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.33973997831344604,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.1144,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.30973002314567566,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.096,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.3053879737854004,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0873,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.37338632345199585,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0937,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.3185729384422302,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.097,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.3350658714771271,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.125,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.2704894542694092,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0946,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.33802467584609985,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0938,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.12657736241817474,
      "eval_runtime": 22.1011,
      "eval_samples_per_second": 2.036,
      "eval_steps_per_second": 2.036,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.3372776210308075,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.1059,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.31522753834724426,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0868,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.3324069082736969,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.1086,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.3118916451931,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.1232,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.30282673239707947,
      "learning_rate": 0.0,
      "loss": 0.0712,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.4013976186768589e+17,
      "train_loss": 0.23165440315008162,
      "train_runtime": 4080.3078,
      "train_samples_per_second": 0.496,
      "train_steps_per_second": 0.031
    }
  ],
  "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": 1.4013976186768589e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}