{
  "best_metric": 0.05012108013033867,
  "best_model_checkpoint": "saves/psy-course-doc-info/Llama3-OpenBioLLM-8B/train/fold7/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": 0.5354031920433044,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.3958,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.5070397257804871,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.3585,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.5866089463233948,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.4308,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.5285331606864929,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.3996,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.5112156271934509,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.3607,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.5264824032783508,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.3499,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.5132115483283997,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.3219,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.6112033128738403,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.358,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.47284358739852905,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.3234,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.37108930945396423,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.2622,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.2341378927230835,
      "eval_runtime": 31.5744,
      "eval_samples_per_second": 1.425,
      "eval_steps_per_second": 1.425,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.4319024085998535,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.2825,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.33626413345336914,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.2143,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.3938014507293701,
      "learning_rate": 0.0001,
      "loss": 0.2144,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.506651759147644,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.2451,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.44404199719429016,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.206,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.3496975302696228,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.1848,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.4039447009563446,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.1645,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.28632500767707825,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.1564,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.42247113585472107,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.1492,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.3069323003292084,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1266,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.12377350777387619,
      "eval_runtime": 31.207,
      "eval_samples_per_second": 1.442,
      "eval_steps_per_second": 1.442,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.3039754629135132,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.1413,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.35694512724876404,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.1397,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.30024152994155884,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.1235,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.40304237604141235,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.1166,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.31560492515563965,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.1179,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.5667579174041748,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.182,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.3464951813220978,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1236,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.2695602476596832,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1065,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.23058056831359863,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1044,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.32276666164398193,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.1058,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.08889171481132507,
      "eval_runtime": 31.1333,
      "eval_samples_per_second": 1.445,
      "eval_steps_per_second": 1.445,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.31484416127204895,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.0867,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.30033451318740845,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1073,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.255688339471817,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.0851,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.7650148868560791,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0881,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.4066060185432434,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.1014,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.30761420726776123,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.0911,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.5172439813613892,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0807,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.2418249547481537,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.0802,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.5056638121604919,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.1033,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.2614700496196747,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.0751,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.07223936915397644,
      "eval_runtime": 31.206,
      "eval_samples_per_second": 1.442,
      "eval_steps_per_second": 1.442,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.28243035078048706,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0702,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.2100849151611328,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.0676,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.26649242639541626,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0764,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.2505638003349304,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.0793,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.2665546238422394,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.072,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.28549477458000183,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0744,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.32879549264907837,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0928,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.285145103931427,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.067,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.31100359559059143,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.0801,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.3343387544155121,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0674,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.06236826628446579,
      "eval_runtime": 31.1941,
      "eval_samples_per_second": 1.443,
      "eval_steps_per_second": 1.443,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.4498831331729889,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.1069,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.24977947771549225,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0597,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.21155261993408203,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0538,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.3834046721458435,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0764,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.23536165058612823,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0697,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.26679831743240356,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.0521,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.3392380177974701,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.0766,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.1934727430343628,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0543,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.3572760820388794,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.063,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.33235102891921997,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0526,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.057809919118881226,
      "eval_runtime": 31.2266,
      "eval_samples_per_second": 1.441,
      "eval_steps_per_second": 1.441,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.31730955839157104,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0781,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.2108856737613678,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0568,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.31121575832366943,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0579,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.26088234782218933,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.054,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.290484756231308,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0771,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.2399476021528244,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0584,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.23358240723609924,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0536,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.26274558901786804,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0479,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.2726583778858185,
      "learning_rate": 5e-05,
      "loss": 0.0484,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.25958022475242615,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.055,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.054998841136693954,
      "eval_runtime": 31.2261,
      "eval_samples_per_second": 1.441,
      "eval_steps_per_second": 1.441,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.25248223543167114,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.054,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.2525966167449951,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.0609,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.20039941370487213,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0465,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.34340164065361023,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0548,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.30104881525039673,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.046,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.4601658284664154,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0803,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.2191132754087448,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0494,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.3178640305995941,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0507,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.2749124765396118,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0477,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.36052703857421875,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0604,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.05243762955069542,
      "eval_runtime": 31.2933,
      "eval_samples_per_second": 1.438,
      "eval_steps_per_second": 1.438,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.18446949124336243,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0452,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.19876934587955475,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0556,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.19416245818138123,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0468,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.3248305320739746,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0391,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.2887552082538605,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0419,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.21067270636558533,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.045,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.17638160288333893,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0473,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.2189824879169464,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0475,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.22130730748176575,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0462,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.21260493993759155,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.058,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.051208700984716415,
      "eval_runtime": 31.2835,
      "eval_samples_per_second": 1.438,
      "eval_steps_per_second": 1.438,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.2118651568889618,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0463,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.1650245487689972,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0439,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.2624209225177765,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0474,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.21472086012363434,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0526,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.27900996804237366,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0505,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.2455338090658188,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0494,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.18640311062335968,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0397,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.18621033430099487,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0447,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.28754183650016785,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0546,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.2237851917743683,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0424,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.05029147118330002,
      "eval_runtime": 31.1771,
      "eval_samples_per_second": 1.443,
      "eval_steps_per_second": 1.443,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.26582634449005127,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0577,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.24797669053077698,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0605,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.26055851578712463,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0424,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.1771554797887802,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0403,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.17685915529727936,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0395,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.19387584924697876,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0363,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.2059469074010849,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0473,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.21382050216197968,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0486,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.19290558993816376,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0504,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.17509382963180542,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0433,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.05058818310499191,
      "eval_runtime": 31.1314,
      "eval_samples_per_second": 1.445,
      "eval_steps_per_second": 1.445,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.19377271831035614,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0351,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.20347005128860474,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0523,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.1949450969696045,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0445,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.22525034844875336,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.051,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.23986102640628815,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0425,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.17025865614414215,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0429,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.21758796274662018,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0413,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.17769429087638855,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0374,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.15323984622955322,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0298,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.20436695218086243,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0502,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.05012108013033867,
      "eval_runtime": 31.137,
      "eval_samples_per_second": 1.445,
      "eval_steps_per_second": 1.445,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.19653387367725372,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0463,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.1696522831916809,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0423,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.17393799126148224,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0475,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.1743329018354416,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.041,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.15723799169063568,
      "learning_rate": 0.0,
      "loss": 0.0399,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.67332461733675e+17,
      "train_loss": 0.098157874584198,
      "train_runtime": 4820.9525,
      "train_samples_per_second": 0.42,
      "train_steps_per_second": 0.026
    }
  ],
  "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": 1.67332461733675e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}