{
  "best_metric": 0.13837376236915588,
  "best_model_checkpoint": "saves/psy-course-info/MentaLLaMA-chat-7B/train/fold7/checkpoint-110",
  "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": 0.8479943871498108,
      "learning_rate": 7.692307692307694e-06,
      "loss": 1.011,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.9940787553787231,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 1.13,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.8868570327758789,
      "learning_rate": 2.307692307692308e-05,
      "loss": 1.1203,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.9414767026901245,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 1.0764,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.9741135835647583,
      "learning_rate": 3.846153846153846e-05,
      "loss": 1.0518,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.9482705593109131,
      "learning_rate": 4.615384615384616e-05,
      "loss": 1.1206,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 1.1278761625289917,
      "learning_rate": 5.384615384615385e-05,
      "loss": 1.0241,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 1.162318468093872,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.9416,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 1.3868470191955566,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.8628,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 1.221936583518982,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.7247,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.6556225419044495,
      "eval_runtime": 25.2989,
      "eval_samples_per_second": 1.779,
      "eval_steps_per_second": 1.779,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 1.3224714994430542,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.6955,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.8933820724487305,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.5475,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.605753481388092,
      "learning_rate": 0.0001,
      "loss": 0.4226,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.7401834726333618,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.5387,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.5033978223800659,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.3655,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.7000488638877869,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.4049,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.5581954717636108,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.3533,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.46428707242012024,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.2976,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.43495386838912964,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.2214,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.44603559374809265,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.2682,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.2502095401287079,
      "eval_runtime": 25.3511,
      "eval_samples_per_second": 1.775,
      "eval_steps_per_second": 1.775,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.43712252378463745,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.2836,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.40741077065467834,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.1807,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.48841965198516846,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.2587,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.4851306676864624,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.2452,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.5358166098594666,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.3323,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.9471485614776611,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.4392,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.3865116536617279,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.2376,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.3768623173236847,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1953,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.3735840618610382,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.174,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.3100745975971222,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.1596,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.1874786615371704,
      "eval_runtime": 25.3055,
      "eval_samples_per_second": 1.778,
      "eval_steps_per_second": 1.778,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.4042874872684479,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.1857,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.4551032781600952,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1953,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.41698041558265686,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.1946,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.35295745730400085,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1945,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.3723732531070709,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.1621,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.4301551878452301,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.2142,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.33187252283096313,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.1482,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.31970810890197754,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.1621,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.37914833426475525,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.1839,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.36064139008522034,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.1906,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.17117930948734283,
      "eval_runtime": 25.3155,
      "eval_samples_per_second": 1.778,
      "eval_steps_per_second": 1.778,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.3406550884246826,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1638,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.4101794362068176,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.1614,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.5562009811401367,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.1717,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.4394840598106384,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.1797,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.33256176114082336,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.1546,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.35118919610977173,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.1865,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.2803776264190674,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.1433,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.39824867248535156,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.1986,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.2531840205192566,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.103,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.35376179218292236,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.1383,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.1562325656414032,
      "eval_runtime": 25.3197,
      "eval_samples_per_second": 1.777,
      "eval_steps_per_second": 1.777,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.520628035068512,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.2672,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.362133264541626,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.1441,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.2968490719795227,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.1364,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.4156266450881958,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.208,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.385905921459198,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1237,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.24312804639339447,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.1105,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.34292101860046387,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.1598,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.31784775853157043,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.1355,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.37300747632980347,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.1514,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.290574848651886,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.1166,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.15057188272476196,
      "eval_runtime": 25.3371,
      "eval_samples_per_second": 1.776,
      "eval_steps_per_second": 1.776,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.41951116919517517,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.1673,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.3957083821296692,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.1428,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.298821359872818,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.1215,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.292154997587204,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.1161,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.305836021900177,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.1174,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.3752972483634949,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.1282,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.4062899351119995,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.1208,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.2098141759634018,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.105,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.3648514747619629,
      "learning_rate": 5e-05,
      "loss": 0.1251,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.39930108189582825,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.1287,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.14558087289333344,
      "eval_runtime": 25.3493,
      "eval_samples_per_second": 1.775,
      "eval_steps_per_second": 1.775,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.42602941393852234,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.1436,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.4375516176223755,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.1213,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.3524439334869385,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.1069,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.4131127893924713,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.1284,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.3252468705177307,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.1021,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.6602956056594849,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.1609,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.2512235641479492,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0964,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.28934913873672485,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0885,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.36210256814956665,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.1038,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.31668251752853394,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.1166,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.14319542050361633,
      "eval_runtime": 25.3678,
      "eval_samples_per_second": 1.774,
      "eval_steps_per_second": 1.774,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.2889581322669983,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.1038,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.44374150037765503,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.1386,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.3132784068584442,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.1062,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.3586356043815613,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.114,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.38785675168037415,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.1029,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.3520270884037018,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0868,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.384810209274292,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.1229,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.28316593170166016,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.094,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.33476629853248596,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0991,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.3031332492828369,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.1051,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.14151525497436523,
      "eval_runtime": 25.3778,
      "eval_samples_per_second": 1.773,
      "eval_steps_per_second": 1.773,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.3278975188732147,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0812,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.4012379050254822,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.1447,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.3554513454437256,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.1122,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.38860607147216797,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.1225,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.36386922001838684,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.11,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.38789206743240356,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.1099,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.39963677525520325,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0963,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.442998468875885,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.1258,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.331474244594574,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.1097,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.3027864992618561,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0923,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.13859114050865173,
      "eval_runtime": 25.3779,
      "eval_samples_per_second": 1.773,
      "eval_steps_per_second": 1.773,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.6644110083580017,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.1523,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.4488275647163391,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.1676,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.26934486627578735,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0784,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.2813289165496826,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0755,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.3218660056591034,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0996,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.34064874053001404,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0952,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.29235410690307617,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0909,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.28724873065948486,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.1173,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.36564555764198303,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.1281,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.26742079854011536,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0944,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.13837376236915588,
      "eval_runtime": 25.3894,
      "eval_samples_per_second": 1.772,
      "eval_steps_per_second": 1.772,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.3239077031612396,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0756,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.46382710337638855,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.178,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.3255053162574768,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0991,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.43526747822761536,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.1057,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.2694756090641022,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0801,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.25986096262931824,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0633,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.43784457445144653,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0847,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.28343427181243896,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0896,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.28111532330513,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0697,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.34993672370910645,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0965,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.1385708600282669,
      "eval_runtime": 25.3827,
      "eval_samples_per_second": 1.773,
      "eval_steps_per_second": 1.773,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.32496774196624756,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0962,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.3296258747577667,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.118,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.36641067266464233,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.1131,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.3221442997455597,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.105,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.3158584237098694,
      "learning_rate": 0.0,
      "loss": 0.084,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.3685430174508646e+17,
      "train_loss": 0.23077567440271377,
      "train_runtime": 4020.9617,
      "train_samples_per_second": 0.504,
      "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": 1.3685430174508646e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}