{
  "best_metric": 0.13639448583126068,
  "best_model_checkpoint": "saves/psy-course-info/Llama-3.1-8B-Instruct/train/fold1/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": 2.3109540939331055,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.9611,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 2.082308530807495,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 1.0588,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 2.2618260383605957,
      "learning_rate": 2.307692307692308e-05,
      "loss": 1.0562,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 2.406709909439087,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 1.0666,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 2.4938302040100098,
      "learning_rate": 3.846153846153846e-05,
      "loss": 1.1054,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 2.4605789184570312,
      "learning_rate": 4.615384615384616e-05,
      "loss": 1.0038,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 2.292224407196045,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.8254,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 2.185123920440674,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.83,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 2.2921018600463867,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.769,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 1.7463761568069458,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.5097,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.50166916847229,
      "eval_runtime": 20.5269,
      "eval_samples_per_second": 2.192,
      "eval_steps_per_second": 2.192,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 1.1303447484970093,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.4805,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 1.0754010677337646,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.4989,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 1.1934067010879517,
      "learning_rate": 0.0001,
      "loss": 0.4617,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 1.2308547496795654,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.3374,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.9226139783859253,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.3549,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.988841712474823,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.3785,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.7457419037818909,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.2204,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.8741199374198914,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.2605,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.6470901966094971,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.3,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.7841081619262695,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.2785,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.26816752552986145,
      "eval_runtime": 20.3438,
      "eval_samples_per_second": 2.212,
      "eval_steps_per_second": 2.212,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.7524680495262146,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.2056,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.7124984860420227,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.2238,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.6577532887458801,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.1979,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.6914678812026978,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.25,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.5763030648231506,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.2765,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 1.0368987321853638,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.3602,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.5198214054107666,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1786,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.7383129596710205,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.2977,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.5574641227722168,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1681,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.6689660549163818,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.2167,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.2089647352695465,
      "eval_runtime": 20.3465,
      "eval_samples_per_second": 2.212,
      "eval_steps_per_second": 2.212,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.6699718236923218,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.1961,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.7284748554229736,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.2162,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.6915841698646545,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.2124,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.519946813583374,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1442,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.5355948209762573,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.1971,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.6616201996803284,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.1746,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.5256274938583374,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.1296,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.4515187740325928,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.134,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.5253787040710449,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.1659,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.45497235655784607,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.1286,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.1793409287929535,
      "eval_runtime": 20.3258,
      "eval_samples_per_second": 2.214,
      "eval_steps_per_second": 2.214,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.6480584740638733,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1891,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.5718190670013428,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.1378,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.5053886771202087,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.1531,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.4558612108230591,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.1226,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.6837159395217896,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.2131,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.48203045129776,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.1513,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.5914492011070251,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.1374,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.5378906726837158,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.1208,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.6833844780921936,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.208,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.627691924571991,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.1316,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.1629895716905594,
      "eval_runtime": 20.3173,
      "eval_samples_per_second": 2.215,
      "eval_steps_per_second": 2.215,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 1.2937793731689453,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.2278,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.57529616355896,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.1019,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.49444466829299927,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.1099,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.6463546752929688,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.1617,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.5653361082077026,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1249,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.7671560049057007,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.1419,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.5202463865280151,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.0929,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.5105649828910828,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.1009,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.5990962386131287,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0973,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.5300285220146179,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0983,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.15547770261764526,
      "eval_runtime": 20.3176,
      "eval_samples_per_second": 2.215,
      "eval_steps_per_second": 2.215,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.5568869113922119,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.104,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.8138154745101929,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.1856,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.6068644523620605,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.1416,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.5877388715744019,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.1593,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.7030817866325378,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.121,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.5983666777610779,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.1054,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.679406464099884,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.1083,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.48212310671806335,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0894,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.4551392197608948,
      "learning_rate": 5e-05,
      "loss": 0.0734,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.5142531394958496,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0841,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.14099685847759247,
      "eval_runtime": 20.3571,
      "eval_samples_per_second": 2.211,
      "eval_steps_per_second": 2.211,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.5010219216346741,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0726,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.7426236867904663,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.1493,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.7199246883392334,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.1654,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.5517510771751404,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.1061,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.7038676738739014,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.1202,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 1.246543288230896,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.2317,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.5992555618286133,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0716,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.5780710577964783,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.088,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.5821602940559387,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.1024,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.42940643429756165,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0698,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.14060449600219727,
      "eval_runtime": 20.3522,
      "eval_samples_per_second": 2.211,
      "eval_steps_per_second": 2.211,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.45006582140922546,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0754,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.48834219574928284,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0766,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.507691502571106,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.066,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.5751940011978149,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0984,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.6298004984855652,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0933,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.6288267970085144,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0887,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.6801175475120544,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.1088,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.5467590689659119,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0724,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.5094563364982605,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0859,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.64423668384552,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0833,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.14073924720287323,
      "eval_runtime": 20.3477,
      "eval_samples_per_second": 2.212,
      "eval_steps_per_second": 2.212,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.8250247836112976,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.1253,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.6464321613311768,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0873,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.8022705912590027,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0973,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.6564443707466125,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0835,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.6606995463371277,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0786,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.5810480713844299,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0658,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.7227704524993896,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.1003,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.5376269817352295,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0667,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.7949172854423523,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0845,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.6909992694854736,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.1042,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.13755826652050018,
      "eval_runtime": 20.3384,
      "eval_samples_per_second": 2.213,
      "eval_steps_per_second": 2.213,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.8960546255111694,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.1005,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 1.2441284656524658,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.1229,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.42859789729118347,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0632,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.6869874596595764,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0708,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.6626088619232178,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0644,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.5837427973747253,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.084,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.5425164103507996,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0657,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.5814228653907776,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0938,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.6324732303619385,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0699,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.4230460822582245,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0525,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.13639448583126068,
      "eval_runtime": 20.335,
      "eval_samples_per_second": 2.213,
      "eval_steps_per_second": 2.213,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.6080125570297241,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0722,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.5740337371826172,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.075,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.5020829439163208,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0526,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.4903480112552643,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.076,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.49024227261543274,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0623,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.567720890045166,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0591,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.543394923210144,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0669,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.46298304200172424,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.064,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.6411653161048889,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0768,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.5906421542167664,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0578,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.13699409365653992,
      "eval_runtime": 20.3557,
      "eval_samples_per_second": 2.211,
      "eval_steps_per_second": 2.211,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.612849235534668,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0599,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.669669508934021,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0924,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.6300934553146362,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0598,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.7341448664665222,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0854,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.675413966178894,
      "learning_rate": 0.0,
      "loss": 0.1055,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.2628188898630042e+17,
      "train_loss": 0.20478209415078164,
      "train_runtime": 3504.6791,
      "train_samples_per_second": 0.578,
      "train_steps_per_second": 0.036
    }
  ],
  "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": 1.2628188898630042e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}