{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 0.011836794283129537,
      "learning_rate": 5.333333333333334e-06,
      "loss": 0.1784,
      "step": 1
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.013144169911195151,
      "learning_rate": 1.0666666666666667e-05,
      "loss": 0.183,
      "step": 2
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.0121269303983867,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.1892,
      "step": 3
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.012991239812108061,
      "learning_rate": 2.1333333333333335e-05,
      "loss": 0.1924,
      "step": 4
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.014210684336703932,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.1851,
      "step": 5
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.014497661416210644,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.1858,
      "step": 6
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.01501360143801389,
      "learning_rate": 3.733333333333334e-05,
      "loss": 0.1786,
      "step": 7
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.01545934778539957,
      "learning_rate": 4.266666666666667e-05,
      "loss": 0.1778,
      "step": 8
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.017592772153285995,
      "learning_rate": 4.8e-05,
      "loss": 0.1828,
      "step": 9
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.01918684683158518,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.1783,
      "step": 10
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.02070618658939026,
      "learning_rate": 5.8666666666666665e-05,
      "loss": 0.1677,
      "step": 11
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.020311054637052683,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.1677,
      "step": 12
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.017183460099699004,
      "learning_rate": 6.933333333333334e-05,
      "loss": 0.166,
      "step": 13
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.021310100264076974,
      "learning_rate": 7.466666666666667e-05,
      "loss": 0.1553,
      "step": 14
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.021818518291701307,
      "learning_rate": 8e-05,
      "loss": 0.1567,
      "step": 15
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.018902157014422046,
      "learning_rate": 7.998916964717848e-05,
      "loss": 0.1408,
      "step": 16
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.015623312164157991,
      "learning_rate": 7.9956684453541e-05,
      "loss": 0.1545,
      "step": 17
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.01808723881045501,
      "learning_rate": 7.990256201039297e-05,
      "loss": 0.1372,
      "step": 18
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.01916171140544312,
      "learning_rate": 7.982683162599218e-05,
      "loss": 0.1517,
      "step": 19
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.017730305482550706,
      "learning_rate": 7.972953430967773e-05,
      "loss": 0.1326,
      "step": 20
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.015762369106450024,
      "learning_rate": 7.961072274966282e-05,
      "loss": 0.1197,
      "step": 21
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.014292327322379344,
      "learning_rate": 7.947046128450319e-05,
      "loss": 0.1152,
      "step": 22
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.01437707355914928,
      "learning_rate": 7.930882586825653e-05,
      "loss": 0.1264,
      "step": 23
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.012970610862858245,
      "learning_rate": 7.912590402935223e-05,
      "loss": 0.1102,
      "step": 24
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.012172702786992022,
      "learning_rate": 7.892179482319297e-05,
      "loss": 0.1077,
      "step": 25
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.012798080837211678,
      "learning_rate": 7.869660877851456e-05,
      "loss": 0.1056,
      "step": 26
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.012379439835100994,
      "learning_rate": 7.845046783753276e-05,
      "loss": 0.0935,
      "step": 27
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.012484193428510048,
      "learning_rate": 7.818350528990929e-05,
      "loss": 0.0967,
      "step": 28
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.013072802773236348,
      "learning_rate": 7.789586570057317e-05,
      "loss": 0.0904,
      "step": 29
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.012612278116937011,
      "learning_rate": 7.758770483143634e-05,
      "loss": 0.0759,
      "step": 30
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.011039928859156514,
      "learning_rate": 7.72591895570457e-05,
      "loss": 0.0769,
      "step": 31
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.010319234755387824,
      "learning_rate": 7.69104977742177e-05,
      "loss": 0.0881,
      "step": 32
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.012109271833835127,
      "learning_rate": 7.654181830570404e-05,
      "loss": 0.0775,
      "step": 33
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.009586595074910477,
      "learning_rate": 7.615335079794083e-05,
      "loss": 0.0835,
      "step": 34
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.010025040945538152,
      "learning_rate": 7.57453056129365e-05,
      "loss": 0.066,
      "step": 35
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.011787300617647403,
      "learning_rate": 7.531790371435709e-05,
      "loss": 0.0803,
      "step": 36
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.009810688082093844,
      "learning_rate": 7.48713765478705e-05,
      "loss": 0.0644,
      "step": 37
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.010733020871554734,
      "learning_rate": 7.440596591581463e-05,
      "loss": 0.0628,
      "step": 38
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.010655707774709684,
      "learning_rate": 7.392192384625704e-05,
      "loss": 0.0611,
      "step": 39
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.009510943024388718,
      "learning_rate": 7.341951245651747e-05,
      "loss": 0.065,
      "step": 40
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.010173693871175086,
      "learning_rate": 7.28990038112265e-05,
      "loss": 0.066,
      "step": 41
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.010747361142782984,
      "learning_rate": 7.236067977499791e-05,
      "loss": 0.062,
      "step": 42
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.010882093858595883,
      "learning_rate": 7.180483185979392e-05,
      "loss": 0.0665,
      "step": 43
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.012512937845818453,
      "learning_rate": 7.123176106706638e-05,
      "loss": 0.0784,
      "step": 44
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.010128941659929386,
      "learning_rate": 7.064177772475912e-05,
      "loss": 0.0572,
      "step": 45
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.013042607607054833,
      "learning_rate": 7.003520131925997e-05,
      "loss": 0.0492,
      "step": 46
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.01124029105308844,
      "learning_rate": 6.941236032239316e-05,
      "loss": 0.0645,
      "step": 47
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.010498920210130373,
      "learning_rate": 6.877359201354606e-05,
      "loss": 0.0529,
      "step": 48
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.011375917727348396,
      "learning_rate": 6.811924229702648e-05,
      "loss": 0.0533,
      "step": 49
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.013077996119079647,
      "learning_rate": 6.744966551474936e-05,
      "loss": 0.0496,
      "step": 50
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.01198480727920829,
      "learning_rate": 6.676522425435433e-05,
      "loss": 0.055,
      "step": 51
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.012120833249446987,
      "learning_rate": 6.606628915285822e-05,
      "loss": 0.0454,
      "step": 52
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.010976794460207764,
      "learning_rate": 6.53532386959484e-05,
      "loss": 0.0458,
      "step": 53
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.009461493270210048,
      "learning_rate": 6.462645901302633e-05,
      "loss": 0.0399,
      "step": 54
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.009141191578587225,
      "learning_rate": 6.388634366811146e-05,
      "loss": 0.0481,
      "step": 55
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.012268190521641324,
      "learning_rate": 6.313329344671946e-05,
      "loss": 0.0516,
      "step": 56
    },
    {
      "epoch": 1.1400000000000001,
      "grad_norm": 0.012173840413446102,
      "learning_rate": 6.236771613882987e-05,
      "loss": 0.0547,
      "step": 57
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.011339250919817995,
      "learning_rate": 6.159002631806052e-05,
      "loss": 0.0443,
      "step": 58
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.009875357947909695,
      "learning_rate": 6.0800645117168616e-05,
      "loss": 0.0407,
      "step": 59
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.009050582564290621,
      "learning_rate": 6.000000000000001e-05,
      "loss": 0.0366,
      "step": 60
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.01199662586737057,
      "learning_rate": 5.918852453000986e-05,
      "loss": 0.0516,
      "step": 61
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.009777166655536148,
      "learning_rate": 5.836665813548047e-05,
      "loss": 0.0366,
      "step": 62
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.009680688543701936,
      "learning_rate": 5.75348458715631e-05,
      "loss": 0.05,
      "step": 63
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.010134572008227292,
      "learning_rate": 5.669353817927272e-05,
      "loss": 0.0487,
      "step": 64
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.008083377755641951,
      "learning_rate": 5.584319064156628e-05,
      "loss": 0.042,
      "step": 65
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.008575428314508896,
      "learning_rate": 5.4984263736636494e-05,
      "loss": 0.0439,
      "step": 66
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.007817885855081317,
      "learning_rate": 5.4117222588554756e-05,
      "loss": 0.0518,
      "step": 67
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 0.009674626271834803,
      "learning_rate": 5.324253671539833e-05,
      "loss": 0.0507,
      "step": 68
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.009225628045924186,
      "learning_rate": 5.23606797749979e-05,
      "loss": 0.0463,
      "step": 69
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.007217961376662902,
      "learning_rate": 5.1472129308443616e-05,
      "loss": 0.0385,
      "step": 70
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.0099798783808331,
      "learning_rate": 5.05773664814881e-05,
      "loss": 0.041,
      "step": 71
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.00789103284123039,
      "learning_rate": 4.967687582398671e-05,
      "loss": 0.0438,
      "step": 72
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.008448213641863288,
      "learning_rate": 4.877114496751613e-05,
      "loss": 0.0448,
      "step": 73
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.0077635722344695,
      "learning_rate": 4.786066438131321e-05,
      "loss": 0.0432,
      "step": 74
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.008728997096493834,
      "learning_rate": 4.694592710667723e-05,
      "loss": 0.0432,
      "step": 75
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.008621728116344941,
      "learning_rate": 4.602742848997933e-05,
      "loss": 0.0367,
      "step": 76
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.008119565893153342,
      "learning_rate": 4.51056659144238e-05,
      "loss": 0.0565,
      "step": 77
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.008502699325342705,
      "learning_rate": 4.418113853070614e-05,
      "loss": 0.0435,
      "step": 78
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.007186727244466837,
      "learning_rate": 4.3254346986714334e-05,
      "loss": 0.0448,
      "step": 79
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.006984309685806434,
      "learning_rate": 4.2325793156419035e-05,
      "loss": 0.0449,
      "step": 80
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.007613270974160622,
      "learning_rate": 4.139597986810005e-05,
      "loss": 0.04,
      "step": 81
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.008747731426528158,
      "learning_rate": 4.046541063205589e-05,
      "loss": 0.0477,
      "step": 82
    },
    {
      "epoch": 1.6600000000000001,
      "grad_norm": 0.007713687203062809,
      "learning_rate": 3.953458936794413e-05,
      "loss": 0.0361,
      "step": 83
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 0.007469803525700852,
      "learning_rate": 3.860402013189998e-05,
      "loss": 0.0398,
      "step": 84
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.008054987299454733,
      "learning_rate": 3.767420684358097e-05,
      "loss": 0.0374,
      "step": 85
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.0069550147082264755,
      "learning_rate": 3.674565301328568e-05,
      "loss": 0.0375,
      "step": 86
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.008574658064169316,
      "learning_rate": 3.581886146929387e-05,
      "loss": 0.0344,
      "step": 87
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.008065675246990847,
      "learning_rate": 3.4894334085576215e-05,
      "loss": 0.0503,
      "step": 88
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.008449200255129663,
      "learning_rate": 3.397257151002068e-05,
      "loss": 0.0497,
      "step": 89
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.008214620799597373,
      "learning_rate": 3.305407289332279e-05,
      "loss": 0.0431,
      "step": 90
    },
    {
      "epoch": 1.8199999999999998,
      "grad_norm": 0.008181828575926744,
      "learning_rate": 3.213933561868679e-05,
      "loss": 0.0407,
      "step": 91
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.0075980985532412984,
      "learning_rate": 3.122885503248386e-05,
      "loss": 0.0384,
      "step": 92
    },
    {
      "epoch": 1.8599999999999999,
      "grad_norm": 0.007753220913052338,
      "learning_rate": 3.0323124176013297e-05,
      "loss": 0.0339,
      "step": 93
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.006840530142098034,
      "learning_rate": 2.9422633518511926e-05,
      "loss": 0.0481,
      "step": 94
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.006332360472268186,
      "learning_rate": 2.8527870691556404e-05,
      "loss": 0.0339,
      "step": 95
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.007235145781102665,
      "learning_rate": 2.7639320225002108e-05,
      "loss": 0.0397,
      "step": 96
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.007012760963826127,
      "learning_rate": 2.6757463284601682e-05,
      "loss": 0.0393,
      "step": 97
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.007270176750961782,
      "learning_rate": 2.5882777411445254e-05,
      "loss": 0.0415,
      "step": 98
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.007105912194783928,
      "learning_rate": 2.501573626336352e-05,
      "loss": 0.0409,
      "step": 99
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.0075041296466497555,
      "learning_rate": 2.4156809358433728e-05,
      "loss": 0.0476,
      "step": 100
    },
    {
      "epoch": 2.02,
      "grad_norm": 0.007229987336226452,
      "learning_rate": 2.330646182072729e-05,
      "loss": 0.0369,
      "step": 101
    },
    {
      "epoch": 2.04,
      "grad_norm": 0.00725928334005231,
      "learning_rate": 2.24651541284369e-05,
      "loss": 0.0519,
      "step": 102
    },
    {
      "epoch": 2.06,
      "grad_norm": 0.007680057407335098,
      "learning_rate": 2.1633341864519526e-05,
      "loss": 0.0432,
      "step": 103
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.0065582180188280504,
      "learning_rate": 2.0811475469990167e-05,
      "loss": 0.0414,
      "step": 104
    },
    {
      "epoch": 2.1,
      "grad_norm": 0.006539240271346896,
      "learning_rate": 2.0000000000000012e-05,
      "loss": 0.0457,
      "step": 105
    },
    {
      "epoch": 2.12,
      "grad_norm": 0.006512737641412582,
      "learning_rate": 1.9199354882831387e-05,
      "loss": 0.0325,
      "step": 106
    },
    {
      "epoch": 2.14,
      "grad_norm": 0.007145394245016067,
      "learning_rate": 1.8409973681939498e-05,
      "loss": 0.0374,
      "step": 107
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.006813685747154185,
      "learning_rate": 1.7632283861170135e-05,
      "loss": 0.0346,
      "step": 108
    },
    {
      "epoch": 2.18,
      "grad_norm": 0.006675567706173568,
      "learning_rate": 1.686670655328054e-05,
      "loss": 0.0412,
      "step": 109
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.007655830729660499,
      "learning_rate": 1.6113656331888563e-05,
      "loss": 0.0393,
      "step": 110
    },
    {
      "epoch": 2.22,
      "grad_norm": 0.0067588437862823765,
      "learning_rate": 1.537354098697367e-05,
      "loss": 0.0408,
      "step": 111
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.006829173089207945,
      "learning_rate": 1.4646761304051587e-05,
      "loss": 0.0462,
      "step": 112
    },
    {
      "epoch": 2.26,
      "grad_norm": 0.00776530999834305,
      "learning_rate": 1.3933710847141795e-05,
      "loss": 0.0468,
      "step": 113
    },
    {
      "epoch": 2.2800000000000002,
      "grad_norm": 0.007504157880790311,
      "learning_rate": 1.3234775745645684e-05,
      "loss": 0.0321,
      "step": 114
    },
    {
      "epoch": 2.3,
      "grad_norm": 0.007952302277823793,
      "learning_rate": 1.2550334485250661e-05,
      "loss": 0.0385,
      "step": 115
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.006915155236149041,
      "learning_rate": 1.1880757702973531e-05,
      "loss": 0.0347,
      "step": 116
    },
    {
      "epoch": 2.34,
      "grad_norm": 0.007020779505852696,
      "learning_rate": 1.1226407986453963e-05,
      "loss": 0.0342,
      "step": 117
    },
    {
      "epoch": 2.36,
      "grad_norm": 0.007151568178165054,
      "learning_rate": 1.0587639677606857e-05,
      "loss": 0.037,
      "step": 118
    },
    {
      "epoch": 2.38,
      "grad_norm": 0.006821852843524058,
      "learning_rate": 9.964798680740033e-06,
      "loss": 0.0354,
      "step": 119
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.007044562968171477,
      "learning_rate": 9.358222275240884e-06,
      "loss": 0.0527,
      "step": 120
    },
    {
      "epoch": 2.42,
      "grad_norm": 0.006561647136472767,
      "learning_rate": 8.768238932933632e-06,
      "loss": 0.0325,
      "step": 121
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.0067862182517935375,
      "learning_rate": 8.195168140206084e-06,
      "loss": 0.0392,
      "step": 122
    },
    {
      "epoch": 2.46,
      "grad_norm": 0.007679758074906389,
      "learning_rate": 7.639320225002106e-06,
      "loss": 0.0366,
      "step": 123
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.007059203376016052,
      "learning_rate": 7.1009961887735075e-06,
      "loss": 0.0451,
      "step": 124
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.0068122235401948195,
      "learning_rate": 6.58048754348255e-06,
      "loss": 0.0466,
      "step": 125
    },
    {
      "epoch": 2.52,
      "grad_norm": 0.006459633695720914,
      "learning_rate": 6.078076153742962e-06,
      "loss": 0.0438,
      "step": 126
    },
    {
      "epoch": 2.54,
      "grad_norm": 0.0066282359320979705,
      "learning_rate": 5.5940340841853915e-06,
      "loss": 0.0345,
      "step": 127
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.007692912237975653,
      "learning_rate": 5.128623452129508e-06,
      "loss": 0.0397,
      "step": 128
    },
    {
      "epoch": 2.58,
      "grad_norm": 0.006824212526305754,
      "learning_rate": 4.6820962856429205e-06,
      "loss": 0.0347,
      "step": 129
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.007239649090287155,
      "learning_rate": 4.254694387063514e-06,
      "loss": 0.0333,
      "step": 130
    },
    {
      "epoch": 2.62,
      "grad_norm": 0.00793644072068399,
      "learning_rate": 3.846649202059181e-06,
      "loss": 0.0412,
      "step": 131
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.007215797336986897,
      "learning_rate": 3.458181694295961e-06,
      "loss": 0.0325,
      "step": 132
    },
    {
      "epoch": 2.66,
      "grad_norm": 0.008398503063860334,
      "learning_rate": 3.0895022257823083e-06,
      "loss": 0.0396,
      "step": 133
    },
    {
      "epoch": 2.68,
      "grad_norm": 0.00708248023260857,
      "learning_rate": 2.7408104429543025e-06,
      "loss": 0.0363,
      "step": 134
    },
    {
      "epoch": 2.7,
      "grad_norm": 0.007119394542491576,
      "learning_rate": 2.4122951685636674e-06,
      "loss": 0.0346,
      "step": 135
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 0.007078140341139728,
      "learning_rate": 2.104134299426832e-06,
      "loss": 0.0348,
      "step": 136
    },
    {
      "epoch": 2.74,
      "grad_norm": 0.006784084855431164,
      "learning_rate": 1.8164947100907238e-06,
      "loss": 0.0422,
      "step": 137
    },
    {
      "epoch": 2.76,
      "grad_norm": 0.00769139233532723,
      "learning_rate": 1.5495321624672443e-06,
      "loss": 0.0505,
      "step": 138
    },
    {
      "epoch": 2.7800000000000002,
      "grad_norm": 0.00647599020300139,
      "learning_rate": 1.3033912214854482e-06,
      "loss": 0.0486,
      "step": 139
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.007093377884829064,
      "learning_rate": 1.0782051768070477e-06,
      "loss": 0.0369,
      "step": 140
    },
    {
      "epoch": 2.82,
      "grad_norm": 0.00691704950619504,
      "learning_rate": 8.740959706477725e-07,
      "loss": 0.04,
      "step": 141
    },
    {
      "epoch": 2.84,
      "grad_norm": 0.006718766519716148,
      "learning_rate": 6.911741317434706e-07,
      "loss": 0.0438,
      "step": 142
    },
    {
      "epoch": 2.86,
      "grad_norm": 0.0064257013556098756,
      "learning_rate": 5.295387154968312e-07,
      "loss": 0.0338,
      "step": 143
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.006571050709996742,
      "learning_rate": 3.8927725033718553e-07,
      "loss": 0.0341,
      "step": 144
    },
    {
      "epoch": 2.9,
      "grad_norm": 0.007149178655125779,
      "learning_rate": 2.704656903222791e-07,
      "loss": 0.0345,
      "step": 145
    },
    {
      "epoch": 2.92,
      "grad_norm": 0.007436951516971702,
      "learning_rate": 1.7316837400782604e-07,
      "loss": 0.0342,
      "step": 146
    },
    {
      "epoch": 2.94,
      "grad_norm": 0.008394531157711207,
      "learning_rate": 9.74379896070321e-08,
      "loss": 0.047,
      "step": 147
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.0072046735629130165,
      "learning_rate": 4.331554645901737e-08,
      "loss": 0.0404,
      "step": 148
    },
    {
      "epoch": 2.98,
      "grad_norm": 0.006777657382950411,
      "learning_rate": 1.0830352821531442e-08,
      "loss": 0.0376,
      "step": 149
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.007529332702697721,
      "learning_rate": 0.0,
      "loss": 0.039,
      "step": 150
    },
    {
      "epoch": 3.0,
      "step": 150,
      "total_flos": 109013455077376.0,
      "train_loss": 0.06588543598850569,
      "train_runtime": 1227.8596,
      "train_samples_per_second": 0.977,
      "train_steps_per_second": 0.122
    }
  ],
  "logging_steps": 1,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 109013455077376.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}