{
  "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": 0.011911302528996475,
      "learning_rate": 5.333333333333334e-06,
      "loss": 0.1705,
      "step": 1
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.012206706925884603,
      "learning_rate": 1.0666666666666667e-05,
      "loss": 0.1874,
      "step": 2
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.013044500312297015,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.1859,
      "step": 3
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.012594653035313248,
      "learning_rate": 2.1333333333333335e-05,
      "loss": 0.1887,
      "step": 4
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.014375891035587373,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.1863,
      "step": 5
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.013750628355867864,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.1824,
      "step": 6
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.01616673490349641,
      "learning_rate": 3.733333333333334e-05,
      "loss": 0.1797,
      "step": 7
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.019508622715234483,
      "learning_rate": 4.266666666666667e-05,
      "loss": 0.1913,
      "step": 8
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.02026174616628655,
      "learning_rate": 4.8e-05,
      "loss": 0.18,
      "step": 9
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.02078245060768437,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.1634,
      "step": 10
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.022787002662984522,
      "learning_rate": 5.8666666666666665e-05,
      "loss": 0.1719,
      "step": 11
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.019551837611818095,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.1829,
      "step": 12
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.01897812813021952,
      "learning_rate": 6.933333333333334e-05,
      "loss": 0.1604,
      "step": 13
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.022324183326650256,
      "learning_rate": 7.466666666666667e-05,
      "loss": 0.1551,
      "step": 14
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.022945935480796924,
      "learning_rate": 8e-05,
      "loss": 0.1464,
      "step": 15
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.02105040572783868,
      "learning_rate": 7.998916964717848e-05,
      "loss": 0.1479,
      "step": 16
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.01788416788504264,
      "learning_rate": 7.9956684453541e-05,
      "loss": 0.1429,
      "step": 17
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.014979694268903285,
      "learning_rate": 7.990256201039297e-05,
      "loss": 0.1377,
      "step": 18
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.01778294789304293,
      "learning_rate": 7.982683162599218e-05,
      "loss": 0.1418,
      "step": 19
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.017276055782622007,
      "learning_rate": 7.972953430967773e-05,
      "loss": 0.1335,
      "step": 20
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.02003310246181747,
      "learning_rate": 7.961072274966282e-05,
      "loss": 0.1199,
      "step": 21
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.016012185840303762,
      "learning_rate": 7.947046128450319e-05,
      "loss": 0.1166,
      "step": 22
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.016406705758876712,
      "learning_rate": 7.930882586825653e-05,
      "loss": 0.1196,
      "step": 23
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.015071123203741278,
      "learning_rate": 7.912590402935223e-05,
      "loss": 0.1115,
      "step": 24
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.01348571374058939,
      "learning_rate": 7.892179482319297e-05,
      "loss": 0.1003,
      "step": 25
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.011466814163738155,
      "learning_rate": 7.869660877851456e-05,
      "loss": 0.0964,
      "step": 26
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.012484105977687808,
      "learning_rate": 7.845046783753276e-05,
      "loss": 0.1024,
      "step": 27
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.012373942294379289,
      "learning_rate": 7.818350528990929e-05,
      "loss": 0.0935,
      "step": 28
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.01324955992273974,
      "learning_rate": 7.789586570057317e-05,
      "loss": 0.0924,
      "step": 29
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.014225032090306879,
      "learning_rate": 7.758770483143634e-05,
      "loss": 0.0798,
      "step": 30
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.011773547298084615,
      "learning_rate": 7.72591895570457e-05,
      "loss": 0.0914,
      "step": 31
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.01137016640202357,
      "learning_rate": 7.69104977742177e-05,
      "loss": 0.0827,
      "step": 32
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.012414165316695635,
      "learning_rate": 7.654181830570404e-05,
      "loss": 0.0706,
      "step": 33
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.01060751098799895,
      "learning_rate": 7.615335079794083e-05,
      "loss": 0.0687,
      "step": 34
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.010530735784965703,
      "learning_rate": 7.57453056129365e-05,
      "loss": 0.066,
      "step": 35
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.009703879959279871,
      "learning_rate": 7.531790371435709e-05,
      "loss": 0.0689,
      "step": 36
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.011213103623968941,
      "learning_rate": 7.48713765478705e-05,
      "loss": 0.0619,
      "step": 37
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.011524685225343244,
      "learning_rate": 7.440596591581463e-05,
      "loss": 0.0643,
      "step": 38
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.011590166129605848,
      "learning_rate": 7.392192384625704e-05,
      "loss": 0.0621,
      "step": 39
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.013900460106421517,
      "learning_rate": 7.341951245651747e-05,
      "loss": 0.071,
      "step": 40
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.012405994033493031,
      "learning_rate": 7.28990038112265e-05,
      "loss": 0.0605,
      "step": 41
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.010094381218142698,
      "learning_rate": 7.236067977499791e-05,
      "loss": 0.0644,
      "step": 42
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.012997000412045259,
      "learning_rate": 7.180483185979392e-05,
      "loss": 0.0738,
      "step": 43
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.012657150003750313,
      "learning_rate": 7.123176106706638e-05,
      "loss": 0.0556,
      "step": 44
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.012960633975083425,
      "learning_rate": 7.064177772475912e-05,
      "loss": 0.0522,
      "step": 45
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.011690363137643303,
      "learning_rate": 7.003520131925997e-05,
      "loss": 0.0537,
      "step": 46
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.013650043947172306,
      "learning_rate": 6.941236032239316e-05,
      "loss": 0.0543,
      "step": 47
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.014851347068870622,
      "learning_rate": 6.877359201354606e-05,
      "loss": 0.0575,
      "step": 48
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.014762492771404873,
      "learning_rate": 6.811924229702648e-05,
      "loss": 0.0513,
      "step": 49
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.014245347022754156,
      "learning_rate": 6.744966551474936e-05,
      "loss": 0.0605,
      "step": 50
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.013840031193383966,
      "learning_rate": 6.676522425435433e-05,
      "loss": 0.0507,
      "step": 51
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.012638810107893216,
      "learning_rate": 6.606628915285822e-05,
      "loss": 0.0487,
      "step": 52
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.013224388471006081,
      "learning_rate": 6.53532386959484e-05,
      "loss": 0.0426,
      "step": 53
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.01586495131582543,
      "learning_rate": 6.462645901302633e-05,
      "loss": 0.0386,
      "step": 54
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.013146025743978407,
      "learning_rate": 6.388634366811146e-05,
      "loss": 0.0392,
      "step": 55
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.01172595039440126,
      "learning_rate": 6.313329344671946e-05,
      "loss": 0.0426,
      "step": 56
    },
    {
      "epoch": 1.1400000000000001,
      "grad_norm": 0.015769547957860734,
      "learning_rate": 6.236771613882987e-05,
      "loss": 0.0542,
      "step": 57
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.013173008521016053,
      "learning_rate": 6.159002631806052e-05,
      "loss": 0.0425,
      "step": 58
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.012281196432838922,
      "learning_rate": 6.0800645117168616e-05,
      "loss": 0.0415,
      "step": 59
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.010840800895928919,
      "learning_rate": 6.000000000000001e-05,
      "loss": 0.0404,
      "step": 60
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.01977565053256244,
      "learning_rate": 5.918852453000986e-05,
      "loss": 0.04,
      "step": 61
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.01676703312730875,
      "learning_rate": 5.836665813548047e-05,
      "loss": 0.0395,
      "step": 62
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.013475126411242358,
      "learning_rate": 5.75348458715631e-05,
      "loss": 0.0364,
      "step": 63
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.020938812474633004,
      "learning_rate": 5.669353817927272e-05,
      "loss": 0.0408,
      "step": 64
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.011790264246147169,
      "learning_rate": 5.584319064156628e-05,
      "loss": 0.0429,
      "step": 65
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.01395503010844694,
      "learning_rate": 5.4984263736636494e-05,
      "loss": 0.0331,
      "step": 66
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.021066013714159736,
      "learning_rate": 5.4117222588554756e-05,
      "loss": 0.0336,
      "step": 67
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 0.01048351479364522,
      "learning_rate": 5.324253671539833e-05,
      "loss": 0.0381,
      "step": 68
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.015309006167876192,
      "learning_rate": 5.23606797749979e-05,
      "loss": 0.0344,
      "step": 69
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.01408529444319314,
      "learning_rate": 5.1472129308443616e-05,
      "loss": 0.0442,
      "step": 70
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.010829050040535103,
      "learning_rate": 5.05773664814881e-05,
      "loss": 0.0445,
      "step": 71
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.008899382507079999,
      "learning_rate": 4.967687582398671e-05,
      "loss": 0.0344,
      "step": 72
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.010248354442879373,
      "learning_rate": 4.877114496751613e-05,
      "loss": 0.0362,
      "step": 73
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.010627887171704332,
      "learning_rate": 4.786066438131321e-05,
      "loss": 0.0392,
      "step": 74
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.011371982475775656,
      "learning_rate": 4.694592710667723e-05,
      "loss": 0.0325,
      "step": 75
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.009005160032615558,
      "learning_rate": 4.602742848997933e-05,
      "loss": 0.0312,
      "step": 76
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.00882822987822379,
      "learning_rate": 4.51056659144238e-05,
      "loss": 0.0447,
      "step": 77
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.009489129284399935,
      "learning_rate": 4.418113853070614e-05,
      "loss": 0.0381,
      "step": 78
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.008929469225844974,
      "learning_rate": 4.3254346986714334e-05,
      "loss": 0.0398,
      "step": 79
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.010002934317869428,
      "learning_rate": 4.2325793156419035e-05,
      "loss": 0.0359,
      "step": 80
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.008048608843879267,
      "learning_rate": 4.139597986810005e-05,
      "loss": 0.0437,
      "step": 81
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.009654039338339675,
      "learning_rate": 4.046541063205589e-05,
      "loss": 0.0434,
      "step": 82
    },
    {
      "epoch": 1.6600000000000001,
      "grad_norm": 0.009825166950730758,
      "learning_rate": 3.953458936794413e-05,
      "loss": 0.0309,
      "step": 83
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 0.01011831730015219,
      "learning_rate": 3.860402013189998e-05,
      "loss": 0.0403,
      "step": 84
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.008342628721123957,
      "learning_rate": 3.767420684358097e-05,
      "loss": 0.0355,
      "step": 85
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.008395413350976013,
      "learning_rate": 3.674565301328568e-05,
      "loss": 0.0305,
      "step": 86
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.009680572837522848,
      "learning_rate": 3.581886146929387e-05,
      "loss": 0.0397,
      "step": 87
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.00918823325232613,
      "learning_rate": 3.4894334085576215e-05,
      "loss": 0.0318,
      "step": 88
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.00970715463941373,
      "learning_rate": 3.397257151002068e-05,
      "loss": 0.0439,
      "step": 89
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.008767237512146092,
      "learning_rate": 3.305407289332279e-05,
      "loss": 0.044,
      "step": 90
    },
    {
      "epoch": 1.8199999999999998,
      "grad_norm": 0.010868872381483766,
      "learning_rate": 3.213933561868679e-05,
      "loss": 0.0377,
      "step": 91
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.00751467134435651,
      "learning_rate": 3.122885503248386e-05,
      "loss": 0.0381,
      "step": 92
    },
    {
      "epoch": 1.8599999999999999,
      "grad_norm": 0.009141355425230173,
      "learning_rate": 3.0323124176013297e-05,
      "loss": 0.0391,
      "step": 93
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.010132566604065644,
      "learning_rate": 2.9422633518511926e-05,
      "loss": 0.0354,
      "step": 94
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.009051316934399098,
      "learning_rate": 2.8527870691556404e-05,
      "loss": 0.0314,
      "step": 95
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.009845541601449482,
      "learning_rate": 2.7639320225002108e-05,
      "loss": 0.0319,
      "step": 96
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.008121961729707784,
      "learning_rate": 2.6757463284601682e-05,
      "loss": 0.0411,
      "step": 97
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.008609570072069866,
      "learning_rate": 2.5882777411445254e-05,
      "loss": 0.0375,
      "step": 98
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.009692212440055616,
      "learning_rate": 2.501573626336352e-05,
      "loss": 0.0371,
      "step": 99
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.008909184429849067,
      "learning_rate": 2.4156809358433728e-05,
      "loss": 0.0322,
      "step": 100
    },
    {
      "epoch": 2.02,
      "grad_norm": 0.008895068000302762,
      "learning_rate": 2.330646182072729e-05,
      "loss": 0.0307,
      "step": 101
    },
    {
      "epoch": 2.04,
      "grad_norm": 0.007862312140045057,
      "learning_rate": 2.24651541284369e-05,
      "loss": 0.0289,
      "step": 102
    },
    {
      "epoch": 2.06,
      "grad_norm": 0.007879775759144237,
      "learning_rate": 2.1633341864519526e-05,
      "loss": 0.0306,
      "step": 103
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.00780499153646595,
      "learning_rate": 2.0811475469990167e-05,
      "loss": 0.0359,
      "step": 104
    },
    {
      "epoch": 2.1,
      "grad_norm": 0.007958492826186138,
      "learning_rate": 2.0000000000000012e-05,
      "loss": 0.0459,
      "step": 105
    },
    {
      "epoch": 2.12,
      "grad_norm": 0.008427636578886736,
      "learning_rate": 1.9199354882831387e-05,
      "loss": 0.0389,
      "step": 106
    },
    {
      "epoch": 2.14,
      "grad_norm": 0.007985453190828898,
      "learning_rate": 1.8409973681939498e-05,
      "loss": 0.034,
      "step": 107
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.008379938607597564,
      "learning_rate": 1.7632283861170135e-05,
      "loss": 0.0287,
      "step": 108
    },
    {
      "epoch": 2.18,
      "grad_norm": 0.008868124418044696,
      "learning_rate": 1.686670655328054e-05,
      "loss": 0.0342,
      "step": 109
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.00800607947935041,
      "learning_rate": 1.6113656331888563e-05,
      "loss": 0.0389,
      "step": 110
    },
    {
      "epoch": 2.22,
      "grad_norm": 0.007439903576175219,
      "learning_rate": 1.537354098697367e-05,
      "loss": 0.0336,
      "step": 111
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.007520612029941438,
      "learning_rate": 1.4646761304051587e-05,
      "loss": 0.0347,
      "step": 112
    },
    {
      "epoch": 2.26,
      "grad_norm": 0.005990359487082578,
      "learning_rate": 1.3933710847141795e-05,
      "loss": 0.0264,
      "step": 113
    },
    {
      "epoch": 2.2800000000000002,
      "grad_norm": 0.007569215684138879,
      "learning_rate": 1.3234775745645684e-05,
      "loss": 0.0283,
      "step": 114
    },
    {
      "epoch": 2.3,
      "grad_norm": 0.007944558601329376,
      "learning_rate": 1.2550334485250661e-05,
      "loss": 0.0453,
      "step": 115
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.00833467253781868,
      "learning_rate": 1.1880757702973531e-05,
      "loss": 0.0287,
      "step": 116
    },
    {
      "epoch": 2.34,
      "grad_norm": 0.009661963699669245,
      "learning_rate": 1.1226407986453963e-05,
      "loss": 0.0394,
      "step": 117
    },
    {
      "epoch": 2.36,
      "grad_norm": 0.00842746036022119,
      "learning_rate": 1.0587639677606857e-05,
      "loss": 0.0439,
      "step": 118
    },
    {
      "epoch": 2.38,
      "grad_norm": 0.011047842898588532,
      "learning_rate": 9.964798680740033e-06,
      "loss": 0.0557,
      "step": 119
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.007763258068240781,
      "learning_rate": 9.358222275240884e-06,
      "loss": 0.0313,
      "step": 120
    },
    {
      "epoch": 2.42,
      "grad_norm": 0.008326129463978758,
      "learning_rate": 8.768238932933632e-06,
      "loss": 0.0267,
      "step": 121
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.007696601217825679,
      "learning_rate": 8.195168140206084e-06,
      "loss": 0.0316,
      "step": 122
    },
    {
      "epoch": 2.46,
      "grad_norm": 0.012521506493148007,
      "learning_rate": 7.639320225002106e-06,
      "loss": 0.0539,
      "step": 123
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.007937877565569516,
      "learning_rate": 7.1009961887735075e-06,
      "loss": 0.0316,
      "step": 124
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.0076159243747823124,
      "learning_rate": 6.58048754348255e-06,
      "loss": 0.0314,
      "step": 125
    },
    {
      "epoch": 2.52,
      "grad_norm": 0.008541760571238307,
      "learning_rate": 6.078076153742962e-06,
      "loss": 0.0256,
      "step": 126
    },
    {
      "epoch": 2.54,
      "grad_norm": 0.007826678527406395,
      "learning_rate": 5.5940340841853915e-06,
      "loss": 0.03,
      "step": 127
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.008078146426941808,
      "learning_rate": 5.128623452129508e-06,
      "loss": 0.0308,
      "step": 128
    },
    {
      "epoch": 2.58,
      "grad_norm": 0.008422086816340638,
      "learning_rate": 4.6820962856429205e-06,
      "loss": 0.0484,
      "step": 129
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.007655449974877537,
      "learning_rate": 4.254694387063514e-06,
      "loss": 0.0319,
      "step": 130
    },
    {
      "epoch": 2.62,
      "grad_norm": 0.008547884605625135,
      "learning_rate": 3.846649202059181e-06,
      "loss": 0.0331,
      "step": 131
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.007299647970244858,
      "learning_rate": 3.458181694295961e-06,
      "loss": 0.032,
      "step": 132
    },
    {
      "epoch": 2.66,
      "grad_norm": 0.007551684687314103,
      "learning_rate": 3.0895022257823083e-06,
      "loss": 0.0404,
      "step": 133
    },
    {
      "epoch": 2.68,
      "grad_norm": 0.008968895077805678,
      "learning_rate": 2.7408104429543025e-06,
      "loss": 0.0296,
      "step": 134
    },
    {
      "epoch": 2.7,
      "grad_norm": 0.00834243467343918,
      "learning_rate": 2.4122951685636674e-06,
      "loss": 0.039,
      "step": 135
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 0.008176408259480739,
      "learning_rate": 2.104134299426832e-06,
      "loss": 0.0343,
      "step": 136
    },
    {
      "epoch": 2.74,
      "grad_norm": 0.007939904654369884,
      "learning_rate": 1.8164947100907238e-06,
      "loss": 0.0427,
      "step": 137
    },
    {
      "epoch": 2.76,
      "grad_norm": 0.007268218877243585,
      "learning_rate": 1.5495321624672443e-06,
      "loss": 0.0293,
      "step": 138
    },
    {
      "epoch": 2.7800000000000002,
      "grad_norm": 0.007519455837502596,
      "learning_rate": 1.3033912214854482e-06,
      "loss": 0.0324,
      "step": 139
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.007804654807392293,
      "learning_rate": 1.0782051768070477e-06,
      "loss": 0.0327,
      "step": 140
    },
    {
      "epoch": 2.82,
      "grad_norm": 0.007375688919893182,
      "learning_rate": 8.740959706477725e-07,
      "loss": 0.0288,
      "step": 141
    },
    {
      "epoch": 2.84,
      "grad_norm": 0.007913585415966564,
      "learning_rate": 6.911741317434706e-07,
      "loss": 0.0268,
      "step": 142
    },
    {
      "epoch": 2.86,
      "grad_norm": 0.007722997857155117,
      "learning_rate": 5.295387154968312e-07,
      "loss": 0.029,
      "step": 143
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.008386698116940192,
      "learning_rate": 3.8927725033718553e-07,
      "loss": 0.0447,
      "step": 144
    },
    {
      "epoch": 2.9,
      "grad_norm": 0.008182341984883466,
      "learning_rate": 2.704656903222791e-07,
      "loss": 0.0336,
      "step": 145
    },
    {
      "epoch": 2.92,
      "grad_norm": 0.00918100254492902,
      "learning_rate": 1.7316837400782604e-07,
      "loss": 0.0324,
      "step": 146
    },
    {
      "epoch": 2.94,
      "grad_norm": 0.00864343737118756,
      "learning_rate": 9.74379896070321e-08,
      "loss": 0.0325,
      "step": 147
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.007248507954206739,
      "learning_rate": 4.331554645901737e-08,
      "loss": 0.0316,
      "step": 148
    },
    {
      "epoch": 2.98,
      "grad_norm": 0.008187544832969976,
      "learning_rate": 1.0830352821531442e-08,
      "loss": 0.0333,
      "step": 149
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.007486718183158735,
      "learning_rate": 0.0,
      "loss": 0.0269,
      "step": 150
    },
    {
      "epoch": 3.0,
      "step": 150,
      "total_flos": 114376832057344.0,
      "train_loss": 0.062178082118431725,
      "train_runtime": 1367.1715,
      "train_samples_per_second": 0.878,
      "train_steps_per_second": 0.11
    }
  ],
  "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": 114376832057344.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}