{
  "best_metric": 0.08390260487794876,
  "best_model_checkpoint": "saves/psy-course-info-chain/Llama3-OpenBioLLM-8B/train/fold7/checkpoint-60",
  "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": 1.1806713342666626,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.288,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 1.0484390258789062,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.3131,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 1.0367388725280762,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.265,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 1.2483952045440674,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.3116,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 1.2094054222106934,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.2764,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 1.2935822010040283,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.302,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 1.2795156240463257,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.2756,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 1.187157154083252,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.2702,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 1.3406668901443481,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.2421,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 1.0839544534683228,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.2445,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.21648824214935303,
      "eval_runtime": 24.3122,
      "eval_samples_per_second": 1.851,
      "eval_steps_per_second": 1.851,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.9160342216491699,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.1893,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 1.1992653608322144,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.2356,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.8872559666633606,
      "learning_rate": 0.0001,
      "loss": 0.2449,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.8659822940826416,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.2038,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 1.0144299268722534,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.2581,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.6357647180557251,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.1919,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.7810993194580078,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.1798,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.5312777757644653,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.1454,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.5145490765571594,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.0981,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.5032801628112793,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.124,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.12906982004642487,
      "eval_runtime": 24.1838,
      "eval_samples_per_second": 1.861,
      "eval_steps_per_second": 1.861,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.4054643213748932,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.1104,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.6089802980422974,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.1565,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.4835517406463623,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.0979,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.43317705392837524,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.1028,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.5609086751937866,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.1159,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.9287205934524536,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.2119,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.5420944690704346,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1225,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.666694164276123,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1319,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.5219086408615112,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.0877,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.519935131072998,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.0764,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.1014765128493309,
      "eval_runtime": 24.1992,
      "eval_samples_per_second": 1.86,
      "eval_steps_per_second": 1.86,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.5370399951934814,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.0996,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.6387835144996643,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1211,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.7629647254943848,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.1157,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.6251450777053833,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0939,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.596269428730011,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.0873,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.4895249009132385,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.114,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.5027954578399658,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.1006,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.4760744273662567,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.0645,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.4417288601398468,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.0709,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.5032643675804138,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.1,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.0960058644413948,
      "eval_runtime": 24.1987,
      "eval_samples_per_second": 1.86,
      "eval_steps_per_second": 1.86,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.4028047025203705,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0544,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.511874258518219,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.0811,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.3556227385997772,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0748,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.5346131324768066,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.0718,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.5659101605415344,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.1205,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.40491482615470886,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0937,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.3927440047264099,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0764,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.5787460207939148,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.1142,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.4545140266418457,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.0769,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.4096144437789917,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0866,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.08659014105796814,
      "eval_runtime": 24.2216,
      "eval_samples_per_second": 1.858,
      "eval_steps_per_second": 1.858,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.7415802478790283,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.1435,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.3738727569580078,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0892,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.42306503653526306,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0687,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.5214022397994995,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.1048,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.5406847596168518,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0525,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.5543375015258789,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.0532,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.6803284883499146,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.1018,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.38236933946609497,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0559,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.7199466824531555,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0629,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.41650477051734924,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0537,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.08390260487794876,
      "eval_runtime": 24.1777,
      "eval_samples_per_second": 1.861,
      "eval_steps_per_second": 1.861,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.6671504378318787,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.101,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.6260353326797485,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0669,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.7001354694366455,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.076,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.5249097347259521,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0569,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.458969384431839,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0765,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.627208948135376,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0762,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.5014646053314209,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0588,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.4230410158634186,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0455,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.6313385367393494,
      "learning_rate": 5e-05,
      "loss": 0.0498,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.6061316728591919,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0573,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.09060803800821304,
      "eval_runtime": 24.1902,
      "eval_samples_per_second": 1.86,
      "eval_steps_per_second": 1.86,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.5609913468360901,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0458,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.6831892728805542,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.0702,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.5892418026924133,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0647,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.5666311979293823,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0662,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.48018068075180054,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0432,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.7797537446022034,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.061,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.47118204832077026,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0403,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.33783844113349915,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.045,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.2938908040523529,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0342,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.34969860315322876,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0385,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.08899123221635818,
      "eval_runtime": 24.213,
      "eval_samples_per_second": 1.859,
      "eval_steps_per_second": 1.859,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.3877992033958435,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0299,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.40463685989379883,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0504,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.3232952058315277,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0345,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.5345374941825867,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0534,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.5388840436935425,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0579,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.4066038727760315,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0432,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.5287349820137024,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0606,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.36572274565696716,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0443,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.619735598564148,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0516,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.5443248152732849,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0484,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.08655188977718353,
      "eval_runtime": 24.2239,
      "eval_samples_per_second": 1.858,
      "eval_steps_per_second": 1.858,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.462795615196228,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0233,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.695302426815033,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0842,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.4530799090862274,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0392,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.47037702798843384,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0452,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.4655075967311859,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0431,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.45599281787872314,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0316,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.7820488214492798,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.031,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.5876951217651367,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.051,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.5233835577964783,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.064,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.3183065950870514,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0276,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.08624985814094543,
      "eval_runtime": 24.1965,
      "eval_samples_per_second": 1.86,
      "eval_steps_per_second": 1.86,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.9779932498931885,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0779,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.8647805452346802,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0939,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.4105539619922638,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0345,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.36540207266807556,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0293,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.4269641935825348,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0421,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.4021141827106476,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0331,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.3993336260318756,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0332,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.39435645937919617,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0488,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.43844789266586304,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0448,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.6968348622322083,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0531,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.08883793652057648,
      "eval_runtime": 24.2298,
      "eval_samples_per_second": 1.857,
      "eval_steps_per_second": 1.857,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.4178405702114105,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0336,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.5745713710784912,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0588,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.29211971163749695,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0261,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.4134243130683899,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0363,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.29582110047340393,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0182,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.5015717148780823,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0376,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.4682711362838745,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.031,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.3672045171260834,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0317,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.4047904312610626,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0332,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.4341714382171631,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0393,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.08763202279806137,
      "eval_runtime": 24.227,
      "eval_samples_per_second": 1.857,
      "eval_steps_per_second": 1.857,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.34060919284820557,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0229,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.5206224322319031,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0402,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.47210654616355896,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0455,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.47075942158699036,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0435,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.40829339623451233,
      "learning_rate": 0.0,
      "loss": 0.0299,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.314270732805079e+17,
      "train_loss": 0.09267389588057995,
      "train_runtime": 3684.1136,
      "train_samples_per_second": 0.55,
      "train_steps_per_second": 0.034
    }
  ],
  "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": 1.314270732805079e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}