{
  "best_metric": 0.09626130014657974,
  "best_model_checkpoint": "saves/psy-course-doc-info/MentaLLaMA-chat-7B/train/fold5/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": 0.2797722816467285,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.4233,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.2699245512485504,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.4136,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.29221561551094055,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.4493,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 1.1821656227111816,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 1.5172,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.7919411659240723,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.9146,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.30220136046409607,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.4228,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.2929950952529907,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.4116,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.2747914791107178,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.3752,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.6147556900978088,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.7206,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.3122808039188385,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.3583,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.5169880986213684,
      "eval_runtime": 37.124,
      "eval_samples_per_second": 1.212,
      "eval_steps_per_second": 1.212,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.3133391737937927,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.376,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.2512494921684265,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.3506,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.2629973888397217,
      "learning_rate": 0.0001,
      "loss": 0.3427,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.3682570457458496,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.4078,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.5087336897850037,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.4707,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.278699666261673,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.2887,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.16112303733825684,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.2318,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 1.049189567565918,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.74,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.19688378274440765,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.2367,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.260367751121521,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.2785,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.3201766312122345,
      "eval_runtime": 37.3341,
      "eval_samples_per_second": 1.205,
      "eval_steps_per_second": 1.205,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 1.34794020652771,
      "learning_rate": 9.874639560909117e-05,
      "loss": 1.0318,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.25978657603263855,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.2165,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.21832872927188873,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.227,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.185944065451622,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.1944,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.19040563702583313,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.2096,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.43660667538642883,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.4098,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.1829986870288849,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1822,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.15544240176677704,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1898,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.15270256996154785,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1715,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.1887555569410324,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.1591,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.237600639462471,
      "eval_runtime": 37.2829,
      "eval_samples_per_second": 1.207,
      "eval_steps_per_second": 1.207,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.1557650864124298,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.1301,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.16271787881851196,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1635,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.1461823433637619,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.1571,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.28116416931152344,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1862,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.18258115649223328,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.1629,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.14325492084026337,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.1449,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.1522551327943802,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.137,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.19255264103412628,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.1731,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.22853469848632812,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.1923,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.14163997769355774,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.1508,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.20433823764324188,
      "eval_runtime": 37.3394,
      "eval_samples_per_second": 1.205,
      "eval_steps_per_second": 1.205,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.13477179408073425,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1133,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.18241992592811584,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.143,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.18955275416374207,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.1127,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 1.9911236763000488,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.8088,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.15699243545532227,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.1019,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 1.5966325998306274,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.6964,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.1863326132297516,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.1379,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.4625551402568817,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.2456,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.2909967303276062,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.1864,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.327502965927124,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.1892,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.15607501566410065,
      "eval_runtime": 37.0752,
      "eval_samples_per_second": 1.214,
      "eval_steps_per_second": 1.214,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.3063271641731262,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.1914,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.15363825857639313,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.1174,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.15694397687911987,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0976,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.1797524243593216,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.1062,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 1.3059343099594116,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.4474,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.19788271188735962,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.1155,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.420778751373291,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.2457,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.2539674937725067,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.1481,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.24330070614814758,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.1253,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.17956331372261047,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.1084,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.13163591921329498,
      "eval_runtime": 37.2895,
      "eval_samples_per_second": 1.207,
      "eval_steps_per_second": 1.207,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.22442054748535156,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.1204,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.2051066756248474,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.103,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.23384596407413483,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0884,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.18486401438713074,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0902,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.19836698472499847,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.1051,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.21364741027355194,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0873,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.3081847131252289,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.1141,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.18685472011566162,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.077,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.22902889549732208,
      "learning_rate": 5e-05,
      "loss": 0.0832,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.33006352186203003,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.1061,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.11801360547542572,
      "eval_runtime": 37.2582,
      "eval_samples_per_second": 1.208,
      "eval_steps_per_second": 1.208,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.22618824243545532,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0848,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 1.3273420333862305,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.3641,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.18487593531608582,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0732,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.21916823089122772,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0986,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.2371826320886612,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0847,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.3338267207145691,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.1652,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.19213417172431946,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0763,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.2812848687171936,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.1467,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.17586253583431244,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0732,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.20068304240703583,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0859,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.10677890479564667,
      "eval_runtime": 37.2243,
      "eval_samples_per_second": 1.209,
      "eval_steps_per_second": 1.209,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.5007279515266418,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.2176,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.23054993152618408,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0788,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.5296916961669922,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.2532,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.18650783598423004,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0676,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.1759318858385086,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0765,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.17161837220191956,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0749,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.15263524651527405,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0662,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.18449106812477112,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0759,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.23672793805599213,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.1305,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.31884846091270447,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0751,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.10134319961071014,
      "eval_runtime": 36.8903,
      "eval_samples_per_second": 1.22,
      "eval_steps_per_second": 1.22,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.43228965997695923,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0837,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.21475711464881897,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.071,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.18735326826572418,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.081,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.24974003434181213,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0906,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.2753591239452362,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0814,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.29919445514678955,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.073,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.2631884813308716,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.1397,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.24432265758514404,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0848,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.2444211095571518,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0719,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.3055577278137207,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0576,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.09812791645526886,
      "eval_runtime": 37.0014,
      "eval_samples_per_second": 1.216,
      "eval_steps_per_second": 1.216,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.25219300389289856,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.1082,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.3254637122154236,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.1129,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.2109055072069168,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.07,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.21768319606781006,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.057,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.4739540219306946,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.1905,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.2146158516407013,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0721,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.20378947257995605,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0934,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.24884851276874542,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.066,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.298806369304657,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0859,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.20169201493263245,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.077,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.0967259481549263,
      "eval_runtime": 37.2127,
      "eval_samples_per_second": 1.209,
      "eval_steps_per_second": 1.209,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.20818054676055908,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0638,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.14907006919384003,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0587,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.1918545961380005,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0777,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.25813713669776917,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0832,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.2275128811597824,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0664,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.2025330662727356,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0612,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.21933184564113617,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0824,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.21225275099277496,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0669,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.2199047952890396,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.088,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.17817965149879456,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0733,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.09626130014657974,
      "eval_runtime": 37.4148,
      "eval_samples_per_second": 1.203,
      "eval_steps_per_second": 1.203,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.22890225052833557,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.1301,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.15516045689582825,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0528,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.43907251954078674,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.2204,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.2722800672054291,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.1067,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.1765957921743393,
      "learning_rate": 0.0,
      "loss": 0.0675,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.821785729309737e+17,
      "train_loss": 0.20135136625170708,
      "train_runtime": 6074.841,
      "train_samples_per_second": 0.333,
      "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": 1.821785729309737e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}