{
  "best_metric": 0.06450261175632477,
  "best_model_checkpoint": "saves/psy-course-doc/Ministral-8B-Instruct-2410/train/fold2/checkpoint-80",
  "epoch": 4.938271604938271,
  "eval_steps": 10,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03950617283950617,
      "grad_norm": 0.26913556456565857,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.2006,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.285310298204422,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.266,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.28063321113586426,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.2129,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.2669070065021515,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.2541,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.2797169089317322,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.2365,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.26156190037727356,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.198,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.24613116681575775,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.1615,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.24158886075019836,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.2589,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.21727997064590454,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.1411,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.2128220498561859,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.1276,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.12927325069904327,
      "eval_runtime": 27.5694,
      "eval_samples_per_second": 1.632,
      "eval_steps_per_second": 1.632,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.21854767203330994,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.1143,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.19351953268051147,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.1142,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.1678258180618286,
      "learning_rate": 0.0001,
      "loss": 0.0915,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.20259089767932892,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.0972,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.19976451992988586,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.0897,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.17162996530532837,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.1002,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.12091425806283951,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.0861,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.14733700454235077,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.1015,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.14008742570877075,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.118,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.12193509191274643,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.0702,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.08260064572095871,
      "eval_runtime": 27.2452,
      "eval_samples_per_second": 1.652,
      "eval_steps_per_second": 1.652,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.1628137230873108,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.0904,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.1272239238023758,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.062,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.108433298766613,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.0709,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.1340980976819992,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.0763,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.10518315434455872,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.0755,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.12475432455539703,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.1256,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.11695254594087601,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0445,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.12480654567480087,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.128,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.12785404920578003,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.0767,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.10678201168775558,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.0711,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.07176470756530762,
      "eval_runtime": 27.2,
      "eval_samples_per_second": 1.654,
      "eval_steps_per_second": 1.654,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.1065303161740303,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.0608,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.1353374719619751,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1264,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.15059009194374084,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.0983,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.09791392087936401,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.043,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.07634565234184265,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.0239,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.1318335384130478,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.0744,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.11763341724872589,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0717,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.10532534867525101,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.11,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.10531561821699142,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.0779,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.11543621122837067,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.0673,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.0690891444683075,
      "eval_runtime": 27.2617,
      "eval_samples_per_second": 1.651,
      "eval_steps_per_second": 1.651,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.09605727344751358,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0361,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.11827694624662399,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.0544,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.12034864723682404,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0648,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.10558971017599106,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.1063,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.0954003781080246,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0627,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.10051645338535309,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0593,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.0920804888010025,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0605,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.0942024290561676,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0332,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.10574479401111603,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.0958,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.08927994221448898,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0318,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.06623717397451401,
      "eval_runtime": 27.1936,
      "eval_samples_per_second": 1.655,
      "eval_steps_per_second": 1.655,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.08903991430997849,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.0564,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.10171347111463547,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0627,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.0922081395983696,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0726,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.09607277810573578,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0399,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.10428012162446976,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0874,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.10639767348766327,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.104,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.11205949634313583,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.0819,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.08390183746814728,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0413,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.13168811798095703,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0746,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.1032516360282898,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0346,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.0659543052315712,
      "eval_runtime": 27.2054,
      "eval_samples_per_second": 1.654,
      "eval_steps_per_second": 1.654,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.10528004914522171,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.022,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.09649871289730072,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0666,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.09208326041698456,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0323,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.08293309807777405,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0383,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.13862887024879456,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0777,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.10759341716766357,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0472,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.10398441553115845,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0435,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.11334691196680069,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0749,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.1214270070195198,
      "learning_rate": 5e-05,
      "loss": 0.065,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.11811845749616623,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0679,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.06459692120552063,
      "eval_runtime": 27.1664,
      "eval_samples_per_second": 1.656,
      "eval_steps_per_second": 1.656,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.08990655839443207,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0471,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.12020352482795715,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.1022,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.12341848015785217,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0763,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.09683777391910553,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0452,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.13689376413822174,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0362,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.10987269878387451,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0565,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.10716680437326431,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0825,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.1275666505098343,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.1033,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.0692337155342102,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0249,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.11072943359613419,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0615,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.06450261175632477,
      "eval_runtime": 27.1666,
      "eval_samples_per_second": 1.656,
      "eval_steps_per_second": 1.656,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.08019673079252243,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0373,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.09784046560525894,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0195,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.09976182132959366,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0491,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.13197565078735352,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0546,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.10719714313745499,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0439,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.11504990607500076,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0661,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.09778556227684021,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0301,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.11764923483133316,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0513,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.12408162653446198,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0696,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.0944032147526741,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0273,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.06481973826885223,
      "eval_runtime": 27.0886,
      "eval_samples_per_second": 1.661,
      "eval_steps_per_second": 1.661,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.11824071407318115,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0532,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.10296020656824112,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0479,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.10138469189405441,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.043,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.12097378075122833,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0486,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.11933062970638275,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.059,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.12843367457389832,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0713,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.1417313516139984,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0346,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.11246208846569061,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0534,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.1363964080810547,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0711,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.11797533929347992,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0525,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.06453817337751389,
      "eval_runtime": 26.7776,
      "eval_samples_per_second": 1.681,
      "eval_steps_per_second": 1.681,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.11173367500305176,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0528,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.11435423046350479,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0462,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.11185265332460403,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0351,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.10466836392879486,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0287,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.1452421396970749,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.1038,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.10910621285438538,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0295,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.1269616335630417,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0765,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.10941986739635468,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0351,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.11885248869657516,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0527,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.10920115560293198,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0478,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.06480655819177628,
      "eval_runtime": 27.1916,
      "eval_samples_per_second": 1.655,
      "eval_steps_per_second": 1.655,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.11402563005685806,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0343,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.09165304154157639,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0227,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.08466549962759018,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.016,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.12965551018714905,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0608,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.07232734560966492,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0064,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.08795677125453949,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0221,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.1147284060716629,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0461,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.12485811859369278,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0484,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.12227210402488708,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0516,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.1415911614894867,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0823,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.06499190628528595,
      "eval_runtime": 27.1786,
      "eval_samples_per_second": 1.656,
      "eval_steps_per_second": 1.656,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.1001090332865715,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0356,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.12507213652133942,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0599,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.11626017093658447,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0561,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.12962499260902405,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0703,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.11535727232694626,
      "learning_rate": 0.0,
      "loss": 0.0475,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.5370518671445197e+17,
      "train_loss": 0.07358206696808338,
      "train_runtime": 4396.8602,
      "train_samples_per_second": 0.461,
      "train_steps_per_second": 0.028
    }
  ],
  "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": 1.5370518671445197e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}