{
  "best_metric": 0.08820422738790512,
  "best_model_checkpoint": "saves/psy-course-doc-info/MentaLLaMA-chat-7B/train/fold4/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": 0.2864079475402832,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.45,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.2501319348812103,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.4041,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.27038833498954773,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.4284,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.30949437618255615,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.4402,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.25852707028388977,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.3962,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.31678858399391174,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.4254,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.3106687664985657,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.412,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.3117520809173584,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.3839,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.29733648896217346,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.3726,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.32165536284446716,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.3967,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.40044641494750977,
      "eval_runtime": 33.2036,
      "eval_samples_per_second": 1.355,
      "eval_steps_per_second": 1.355,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.28638365864753723,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.3502,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.2486184537410736,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.3326,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 1.6050796508789062,
      "learning_rate": 0.0001,
      "loss": 1.5534,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.21871024370193481,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.3018,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.20137463510036469,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.2736,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.19322079420089722,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.2548,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.14261773228645325,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.2253,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.7724708914756775,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.6928,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.20221512019634247,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.2405,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.5923847556114197,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.4552,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.2510680556297302,
      "eval_runtime": 33.1448,
      "eval_samples_per_second": 1.358,
      "eval_steps_per_second": 1.358,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.1860058605670929,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.1958,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.23070134222507477,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.2165,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 1.3865938186645508,
      "learning_rate": 9.804586609725499e-05,
      "loss": 1.0447,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 1.3050363063812256,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.9798,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.2233203947544098,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.1875,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 2.0185348987579346,
      "learning_rate": 9.671244701472999e-05,
      "loss": 1.0297,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.15279987454414368,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1749,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.1621987521648407,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1785,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.1997373253107071,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1701,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.2228480577468872,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.1757,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.18198877573013306,
      "eval_runtime": 33.0582,
      "eval_samples_per_second": 1.361,
      "eval_steps_per_second": 1.361,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.16603508591651917,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.1809,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.32273298501968384,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.2462,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.11671771109104156,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.1287,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.20580708980560303,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1818,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.15228861570358276,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.1301,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.13200409710407257,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.1574,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.15437857806682587,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.162,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.1765257567167282,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.147,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.2215324193239212,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.1464,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.1911460906267166,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.1409,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.14737115800380707,
      "eval_runtime": 33.2202,
      "eval_samples_per_second": 1.355,
      "eval_steps_per_second": 1.355,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.14890165627002716,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.137,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.18511058390140533,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.121,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.24819499254226685,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.1413,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.18696552515029907,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.1463,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 1.5677334070205688,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.4203,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.6637105941772461,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.3808,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.1812775433063507,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.1224,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.4116617739200592,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.2759,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.13273365795612335,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.1117,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.21898424625396729,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.1122,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.1285279244184494,
      "eval_runtime": 33.0918,
      "eval_samples_per_second": 1.36,
      "eval_steps_per_second": 1.36,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.2857193946838379,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.2029,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.1545441746711731,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.1149,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.1880066692829132,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.1228,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.18879888951778412,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0938,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.21605083346366882,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0994,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 6.633823394775391,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.5568,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 1.0602260828018188,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.2832,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.22804833948612213,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.1222,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.1929726004600525,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.1011,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.6908883452415466,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.2986,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.11335887014865875,
      "eval_runtime": 33.318,
      "eval_samples_per_second": 1.351,
      "eval_steps_per_second": 1.351,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.1820519119501114,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0874,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.18469223380088806,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0849,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.1937774121761322,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.1005,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.3839845657348633,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.1172,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.18544647097587585,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.1095,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.16328199207782745,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0839,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.1919257491827011,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0964,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 2.0564634799957275,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.2853,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.222782164812088,
      "learning_rate": 5e-05,
      "loss": 0.1132,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.25919026136398315,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0918,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.10388223081827164,
      "eval_runtime": 33.2829,
      "eval_samples_per_second": 1.352,
      "eval_steps_per_second": 1.352,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.16874097287654877,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0858,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.22614149749279022,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.0907,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.1633305847644806,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.089,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.26879674196243286,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.088,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.29857102036476135,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.1231,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.33389437198638916,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.1488,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.20251235365867615,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0795,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.1788269579410553,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0835,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.19670172035694122,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0816,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.21457433700561523,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0807,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.09658898413181305,
      "eval_runtime": 33.1974,
      "eval_samples_per_second": 1.356,
      "eval_steps_per_second": 1.356,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.19321416318416595,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0866,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.17663411796092987,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0674,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.18844909965991974,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0713,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.6505243182182312,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.2976,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.1973399668931961,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0714,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.4218144118785858,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.2048,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.1768239289522171,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0828,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.2522295415401459,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0854,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.23895029723644257,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0786,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.26684942841529846,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0862,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.09241139143705368,
      "eval_runtime": 33.1029,
      "eval_samples_per_second": 1.359,
      "eval_steps_per_second": 1.359,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.25276875495910645,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0943,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.19660933315753937,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.1047,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.23555438220500946,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0914,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.2653454542160034,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.077,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.23977330327033997,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0898,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.2264566719532013,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0676,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.2858130633831024,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.1508,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.4013102352619171,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.1951,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.31328096985816956,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0825,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.20354343950748444,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.085,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.08913792669773102,
      "eval_runtime": 33.0652,
      "eval_samples_per_second": 1.361,
      "eval_steps_per_second": 1.361,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.24328924715518951,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.079,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.3147973120212555,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.1293,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.20787499845027924,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0858,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.2153196781873703,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0588,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.23134519159793854,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0874,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.1359415054321289,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0498,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.6561051607131958,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.378,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.18904151022434235,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0648,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.19127987325191498,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0703,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.18731221556663513,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.101,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.08827316761016846,
      "eval_runtime": 33.3338,
      "eval_samples_per_second": 1.35,
      "eval_steps_per_second": 1.35,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.19088734686374664,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0742,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.206560879945755,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0687,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.18107952177524567,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0721,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.1885141283273697,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0849,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.17271022498607635,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0684,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.29019680619239807,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.1874,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.20738458633422852,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0856,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.1830822229385376,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0574,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.2173815816640854,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0964,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.20605818927288055,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0736,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.08820422738790512,
      "eval_runtime": 33.2445,
      "eval_samples_per_second": 1.354,
      "eval_steps_per_second": 1.354,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.20129641890525818,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0665,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.172899067401886,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.073,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.19359171390533447,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0595,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.21745343506336212,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0647,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.2023143172264099,
      "learning_rate": 0.0,
      "loss": 0.0751,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.8368006129064346e+17,
      "train_loss": 0.20265533569455146,
      "train_runtime": 6077.0367,
      "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": 1.8368006129064346e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}